def test_H_observed_EC2_variants():
"""Illustrate the variants of H_observed"""
print(
"\n\n-- test_H_observed_EC2_variants(): 'H_observed', 'M_observed', uses: 'planted_distribution_model_H' --"
)
# --- Parameters for graph
n = 3000
a = 1
h = 8
d = 2
k = 3
f = 0.2
distribution = 'uniform'
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
# --- Create graph
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(
seed=RANDOMSEED
) # seeds the actually used numpy random generator; both are used and thus needed
W, Xd = planted_distribution_model_H(n,
alpha=alpha0,
H=H0,
d_out=d,
distribution=distribution,
exponent=None,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
X1, _ = replace_fraction_of_rows(X0, f, avoidNeighbors=False)
# --- Print first rows of matrices
distance = 3
print("First rows of powers of H0:")
for k in range(1, distance + 1):
print("{}: {}".format(k, np.linalg.matrix_power(H0, k)[0]))
print("\nNumber of observed edges between labels (M_observed):")
M = M_observed(W, X1, distance=distance, NB=True)
print("M[0]:\n{}".format(M[0]))
print("M[2]:\n{}".format(M[1]))
for EC in [False, True]:
for variant in [1, 2]:
print("\nP (H observed): variant {} with EC={}".format(
variant, EC))
H_vec = H_observed(W,
X1,
distance=distance,
NB=EC,
variant=variant)
for i, H in enumerate(H_vec):
print("{}:\n{}".format(i, H))
def calculate_nVec_from_Xd(Xd):
"""Calculates 'n_vec': the number of times each node class occurs in graph.
Given graph with explicit beliefs in dictionary format 'Xd'.
Assumes zeroindexing.
"""
X0 = from_dictionary_beliefs(Xd)
return X0.sum(axis=0)
def calculate_Ptot_from_graph(W, Xd, zeroindexing=True):
"""Calculates [k x k] array 'P_tot': the number of times each edge type occurs in graph.
Uses a sparse directed (incl. undirected) [n x n] adjacency matrix 'W' and explicit beliefs in dictionary format 'Xd'.
[Does not ignore weights of 'W'. Updated with simpler multiplication]
Assumes zeroindexing.
If normalizing is required later:
m = sum(P_tot.flatten()) # sum of all entries = number of edges
Pot = 1. * P_tot / m # Potential: normalized sum = 1
P_tot = Pot
"""
X0 = from_dictionary_beliefs(Xd, zeroindexing=zeroindexing)
return X0.transpose().dot(W.dot(X0))
def calculate_outdegree_distribution_from_graph(W, Xd=None):
"""Given a graph 'W', returns a dictionary {degree -> number of nodes with that degree}.
If a dictionary 'Xd' of explicit beliefs is given, then returns a list of dictionaries, one for each node class.
Takes weight into acount [OLD: Ignores weights of 'W'. Assumes zeroindexing.]
Transpose W to get indegrees.
"""
n, _ = W.shape
countDegrees = W.dot(np.ones((n, 1))).flatten().astype(int)
# # OLD version that ignored the weight
# row, col = W.nonzero() # transform the sparse W back to row col format
# countNodes = collections.Counter(row) # count number of times every node appears in rows
# # Add all nodes to the counter (thus nodes with 0 ocurrences have "node key -> 0", important for later statistics)
# for key in range(n):
# countNodes.setdefault(key, 0)
if Xd is None:
countIndegrees = collections.Counter(countDegrees) # count multiplicies of nodes classes
return countIndegrees
# # OLD version
# countIndegrees = collections.Counter(countNodes.values()) # count multiplicies of nodes classes
else:
listCountIndegrees = []
X0 = from_dictionary_beliefs(Xd)
for col in X0.transpose():
countDegreesInClass = countDegrees*col # entry-wise multiplication
countDegreesInClass = countDegreesInClass[np.nonzero(countDegreesInClass)]
countIndegreesInClass = collections.Counter(countDegreesInClass)
listCountIndegrees.append(countIndegreesInClass)
# # OLD version
# k = max(Xd.values()) + 1
# listCounterNodes = [{} for _ in range(k)]
# for key, value in countNodes.iteritems():
# j = Xd[key]
# listCounterNodes[j][key] = value
# for dict in listCounterNodes:
# countIndegrees = collections.Counter(dict.values()) # count multiplicies of nodes classes
# # listCountIndegrees.append(countIndegrees)
return listCountIndegrees
def test_M_observed():
"""Illustrate M_observed: non-backtracking or not
Also shows that W^2 is denser for powerlaw graphs than uniform
"""
print(
"\n-- test_M_observed(): 'M_observed', uses: 'planted_distribution_model_H' --"
)
# --- Parameters for graph
n = 3000
a = 1
h = 8
d = 10 # variant 2
d = 2 # variant 1
k = 3
distribution = 'powerlaw' # variant 2
distribution = 'uniform' # variant 1
exponent = -0.5
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
# --- Create graph
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(
seed=RANDOMSEED
) # seeds the actually used numpy random generator; both are used and thus needed
W, Xd = planted_distribution_model_H(n,
alpha=alpha0,
H=H0,
d_out=d,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
# --- Print results
distance = 8
M_vec = M_observed(W, X0, distance=distance, NB=False)
M_vec_EC = M_observed(W, X0, distance=distance, NB=True)
print("Graph with n={} nodes and uniform d={} degrees".format(n, d))
print("\nSum of entries and first rows of M_vec (without NB)")
for i, M in enumerate(M_vec): # M_vec[1:] to skip the first entry in list
print("{}: {}, {}".format(i, np.sum(M), M[0]))
print("\nSum of entries and first rows of M_vec (with NB)")
for i, M in enumerate(M_vec_EC):
print("{}: {}, {}".format(i, np.sum(M), M[0]))
if True:
print("\nFull matrices:")
print("M_vec")
for i, M in enumerate(M_vec): # skip the first entry in list
print("{}: \n{}".format(i, M))
print("\nM_vec_EC")
for i, M in enumerate(M_vec_EC): # skip the first entry in list
print("{}: \n{}".format(i, M))
def test_gradient_optimization2():
print(
"\n-- 'estimateH, define_gradient_energy_H, define_energy_H, uses: planted_distribution_model_H, H_observed, M_observed, --"
)
# --- Parameters for graph
n = 10000
a = 1
h = 2
d = 10
k = 7
distribution = 'powerlaw'
exponent = -0.3
np.set_printoptions(precision=4)
alpha0 = create_parameterized_alpha(k, a)
H0 = create_parameterized_H(k, h, symmetric=True)
f = 0.02
print("Graph n={}, d={}, f={}".format(n, d, f))
print("H0:\n{}".format(H0))
# --- Create graph
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(
seed=RANDOMSEED
) # seeds the actually used numpy random generator; both are used and thus needed
W, Xd = planted_distribution_model_H(n,
alpha=alpha0,
H=H0,
d_out=d,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
X1, ind = replace_fraction_of_rows(X0, 1 - f)
# --- M_vec, H_vec statistics
distance = 5
print("M_vec:")
M_vec = M_observed(W, X1, distance=distance)
for i, M in enumerate(M_vec):
print("{}:\n{}".format(i, M))
print("\nH_vec_observed:")
H_vec = H_observed(W, X1, distance=distance)
for i, H in enumerate(H_vec):
print("{}:\n{}".format(i, H))
# --- estimate_H based on distance 1 and uninformative point
distance = 1
weights = [1, 0, 0, 0, 0]
print(
"\n= Estimate H based on X1 and distance={} from uninformative point:".
format(distance))
h0 = np.ones(int(k * (k - 1) / 2)).dot(
1 / k) # use uninformative matrix to start with
energy_H = define_energy_H(H_vec_observed=H_vec,
weights=weights,
distance=distance)
gradient_energy_H = define_gradient_energy_H(H_vec_observed=H_vec,
weights=weights,
distance=distance)
start = time.time()
H1 = estimateH(X1, W, distance=distance, weights=weights, gradient=False)
time_est = time.time() - start
print("Estimated H without gradient:\n{}".format(H1))
print("Time :{}".format(time_est))
e = energy_H(H1)
print("Energy at estimated point: {}".format(e))
start = time.time()
H2 = estimateH(X1, W, distance=distance, weights=weights, gradient=True)
time_est = time.time() - start
print("Estimated H with gradient:\n{}".format(H2))
print("Time :{}".format(time_est))
e = energy_H(H2)
print("Energy at estimated point: {}".format(e))
G = gradient_energy_H(H2)
h = derivative_H_to_h(G)
print("Gradient matrix at estimated point:\n{}".format(G))
print("Gradient vector at estimated point:\n{}".format(h))
def test_gradient_optimization():
print(
"\n-- 'estimateH, define_gradient_energy_H, define_energy_H, uses: planted_distribution_model_H, H_observed, M_observed, --"
)
# --- Parameters for graph
n = 1000
a = 1
h = 8
d = 25
k = 3
distribution = 'powerlaw'
exponent = -0.3
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
f = 0.1
print("Graph n={}, d={}, f={}".format(n, d, f))
print("H0:\n{}".format(H0))
# --- Create graph
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(
seed=RANDOMSEED
) # seeds the actually used numpy random generator; both are used and thus needed
W, Xd = planted_distribution_model_H(n,
alpha=alpha0,
H=H0,
d_out=d,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
X1, ind = replace_fraction_of_rows(X0, 1 - f)
# --- M_vec, H_vec statistics
distance = 5
print("\nH_vec_observed:")
H_vec = H_observed(W, X1, distance=distance)
for i, H in enumerate(H_vec):
print("{}:\n{}".format(i, H))
# --- estimate_H based on distance 1
print(
"\n= Estimate H based on X1 and distance=1 (old without or with gradient):"
)
distance = 1
weights = [1, 0, 0, 0, 0]
start = time.time()
H1 = estimateH(X1, W, distance=distance, weights=weights, gradient=False)
time_est = time.time() - start
print("Estimated H without gradient:\n{}".format(H1))
print("Time :{}".format(time_est))
start = time.time()
H2 = estimateH(X1, W, distance=distance, weights=weights, gradient=True)
time_est = time.time() - start
print("Estimated H with gradient:\n{}".format(H2))
print("Time :{}".format(time_est))
# --- estimate_H based on distance 5 and uninformative point
print(
"\n= Estimate H based on X1 and distance=5 (ignoring distances 1-4) from various points (old without or with gradient):"
)
print(
"From uninformative point (all methods get stuck, even with gradient !!!:"
)
distance = 5
weights = [0, 0, 0, 0, 1]
h0 = np.ones(3).dot(1 / k) # use uninformative matrix to start with
start = time.time()
H1 = estimateH(X1, W, distance=distance, weights=weights, gradient=False)
time_est = time.time() - start
print("Estimated H without gradient:\n{}".format(H1))
print("Time :{}".format(time_est))
start = time.time()
H2 = estimateH(X1, W, distance=distance, weights=weights, gradient=True)
time_est = time.time() - start
print("Estimated H with gradient:\n{}".format(H2))
print("Time :{}".format(time_est))
gradient_energy_H = define_gradient_energy_H(H_vec_observed=H_vec,
weights=weights,
distance=distance)
g = gradient_energy_H(transform_hToH(h0, 3))
h = derivative_H_to_h(g)
print("Gradient at uninformative point:\n{}".format(g))
print("Gradient at uninformative point: {}".format(h))
energy_H = define_energy_H(H_vec_observed=H_vec,
weights=weights,
distance=distance)
e = energy_H(H2)
print("Energy at estimated point: {}".format(e))
# --- estimate_H based on distance 5 and wrong point
print(
"\n= From wrong point (gradient method with BFGS can fix it, SLSQP stays stuck !!!"
)
distance = 5
weights = [0, 0, 0, 0, 1]
h0 = np.array([0.4, 0.3, 0.3])
start = time.time()
H1 = estimateH(X1,
W,
distance=distance,
weights=weights,
gradient=False,
initial_h0=h0)
time_est = time.time() - start
print("Estimated H without gradient:\n{}".format(H1))
print("Time :{}".format(time_est))
start = time.time()
H2 = estimateH(X1,
W,
distance=distance,
weights=weights,
gradient=True,
initial_h0=h0)
time_est = time.time() - start
print("Estimated H with gradient:\n{}".format(H2))
print("Time :{}".format(time_est))
gradient_energy_H = define_gradient_energy_H(H_vec_observed=H_vec,
weights=weights,
distance=distance)
g = gradient_energy_H(transform_hToH(h0, 3))
h = derivative_H_to_h(g)
print("Gradient at wrong point:\n{}".format(g))
print("Gradient at wrong point: {}".format(h))
energy_H = define_energy_H(H_vec_observed=H_vec,
weights=weights,
distance=distance)
e = energy_H(H2)
print("Energy at estimated point: {}".format(e))
# --- estimate_H based on distance 5 and some closer point
print(
"\n= From closer point (converges for BFGS, but not always for SLSQP!!!):"
)
distance = 5
weights = [0, 0, 0, 0, 1]
h0 = np.array([0.3, 0.4, 0.3])
start = time.time()
H1 = estimateH(X1,
W,
distance=distance,
weights=weights,
gradient=False,
initial_h0=h0)
time_est = time.time() - start
print("Estimated H without gradient:\n{}".format(H1))
print("Time :{}".format(time_est))
start = time.time()
H2 = estimateH(X1,
W,
distance=distance,
weights=weights,
gradient=True,
initial_h0=h0)
time_est = time.time() - start
print("Estimated H with gradient:\n{}".format(H2))
print("Time :{}".format(time_est))
gradient_energy_H = define_gradient_energy_H(H_vec_observed=H_vec,
weights=weights,
distance=distance)
g = gradient_energy_H(transform_hToH(h0, 3))
h = derivative_H_to_h(g)
print("Gradient at closer point:\n{}".format(g))
print("Gradient at closer point: {}".format(h))
energy_H = define_energy_H(H_vec_observed=H_vec,
weights=weights,
distance=distance)
e = energy_H(H2)
print("Energy at estimated point: {}".format(e))
# --- estimate_H based on distance 5 and some closer point
print("\n= From even closer point:")
distance = 5
weights = [0, 0, 0, 0, 1]
h0 = np.array([0.2, 0.4, 0.2])
start = time.time()
H1 = estimateH(X1,
W,
distance=distance,
weights=weights,
gradient=False,
initial_h0=h0)
time_est = time.time() - start
print("Estimated H without gradient:\n{}".format(H1))
print("Time :{}".format(time_est))
start = time.time()
H2 = estimateH(X1,
W,
distance=distance,
weights=weights,
gradient=True,
initial_h0=h0)
time_est = time.time() - start
print("Estimated H with gradient:\n{}".format(H2))
print("Time :{}".format(time_est))
gradient_energy_H = define_gradient_energy_H(H_vec_observed=H_vec,
weights=weights,
distance=distance)
g = gradient_energy_H(transform_hToH(h0, 3))
h = derivative_H_to_h(g)
print("Gradient at closer point:\n{}".format(g))
print("Gradient at closer point: {}".format(h))
energy_H = define_energy_H(H_vec_observed=H_vec,
weights=weights,
distance=distance)
e = energy_H(H2)
print("Energy at estimated point: {}".format(e))
# --- estimate_H based on distance 5 and some closer point
print(
"\n= Variant with constraints (constraints only work with SLSQP !!!):")
start = time.time()
H2 = estimateH(X1,
W,
distance=distance,
weights=weights,
gradient=True,
initial_h0=h0,
constraints=True)
time_est = time.time() - start
print("Estimated H with gradient and constraints:\n{}".format(H2))
print("Time :{}".format(time_est))
e = energy_H(H2)
print("Energy at estimated point: {}".format(e))
def forced_block_model(n, d, H, alpha, directed=True, clamped=True):
"""Returns a graph with n nodes and n*b edges.
Nodes are divided into classes exactly according to alpha (no uncertainty).
Each node as source actively tries to connect to exactly b other nodes as targets. Thus outdegree = b.
Targets are chosen according to row-normalized H matrix.
Parameters
----------
n : int
The number of nodes
d : int
The exact [!!! average???] outdegree of each node, thus the number of edges per node
H : [k,k] ndarray
row-normalized homophily matrix
alpha : k ndarray
a prior probability distribution of classes
seed : int, optional
seed for random number generator (default=None)
directed : bool, optional (Default = true)
model creates directed edges.
clamped : bool, optional (Default = true)
new model with fixed Potential. If False, then original model with expected alpha and H
Returns
-------
W : sparse.csr_matrix
sparse weighted adjacency matrix
X : np.array int
Explicit belief matrix
! maybe should be better Xd
Notes
-----
Some nodes may be more incoming edges than others. But average indegree is also b.
Uses function weighted_sample for random neighbor draws.
Directed edges are drawn as to never go in both directions (!!! may want to put a flag later)
internal parameter repMax: edge node tries to connect to randomly chosen node type.
If not possible repMax times, then it gives up. Thus can lead to graphs with fewer edges b than expected
"""
repMax = 10 # !!! max number of times of attempts connect to a certain node type
k = len(alpha)
# Determine node classes
# Xl: list that maps each index i to the respective class k of that node i
# Xd, X
if clamped: # clamp the number of nodes for each class exactly
classNum = np.array(alpha*n, int) # array of number of nodes in each class
delta = np.sum(classNum) - n
classNum[k-1] = classNum[k-1] - delta # make sure sum(N)=n, in case there are rounding errors, correct the last entry
Xl = [ [i]*classNum[i] for i in range(k) ] # create a list of that maps for each index of a node to its class, in 3 steps
Xl = np.hstack(Xl) # flatten nested array
np.random.shuffle(Xl) # random order of those classes. Array that maps i -> k
else: # old code that chooses independently. Led to random instantiaton for actual alpha
Xl = np.random.choice(k, n, replace=True, p=alpha) # Array that maps i -> k
Xd = {i : Xl[i] for i in range(n)} # Xd: dictionary that maps i -> k
X = from_dictionary_beliefs(Xd, n, k)
# ClassNodes [maps k -> array of nodes of class k]
classNodes =[[] for i in range(k)]
for c in range(k):
classNodes[c] = np.array([i for (i,j) in Xd.items() if j == c])
# legacy
if not clamped:
classNum = []
for c in range(k):
classNum.append( np.size(classNodes[c]) )
assert(min(classNum) > 0) # at least one node for each class
# row, col: index structure for edges
# edges: set of edges
# He: count edge matrix
# T: T[j] is list T[j,i] of node types to which the i-th edge links
row = []
col = []
edges = set() # set of edges, used to verify if edge already exists
# Determine end classes for each edge with a given edge source type
if clamped:
He = [] # Count edge matrix
for j in range(k):
Z = np.array(H[j]*classNum[j]*d, int) # number of nodes in each class
delta = np.sum(Z) - classNum[j]*d # balancing due to rounding possible errors
Z[k-1] = Z[k-1] - delta
He.append(Z)
# T[j]
He = np.array(He)
delta = np.sum(He) - n*d # balancing due to rounding possible errors
He[k-1,k-1] = He[k-1,k-1] - delta
T = [] # list of lists (for a given source node class) of edge target node classes for each edge
id_T = [] # list of indexes
for j in range(k):
Z1 = [ [i]*He[j,i] for i in range(k) ]
Z2 = np.hstack(Z1).astype(np.int64) # flatten nested array. Then make sure it is integer
np.random.shuffle(Z2) # random order of those classes. Array that maps i -> k
T.append(Z2)
id_T.append(0)
# determine actual edges
for i in range(n):
j = Xd[i] # class of start node
for l in range(d):
c = T[j][id_T[j]] # class of end node
connected = False # has the new node already found another node to connect to
l=1 # l-th attempt to connect this node type
while l <= repMax and not connected:
v = random.choice(classNodes[c]) # choose a random node of that class
if (not v==i and # don't connect to any node if edge exists in either direction
not (i,v) in edges and
not (v,i) in edges):
connected = True
row.append(i)
col.append(v)
edges.add((i,v))
l += 1
id_T[j] += 1
else:
# Actual loop for each node and edge
# !!! better use: to_scipy_sparse_matrix(G,nodelist=None,dtype=None):
for i in range(n):
pk = X[i].dot(H)
pk = np.squeeze(np.asarray(pk)) # probability distribuion of neighbor
for j in range(d):
c = weighted_sample(pk) # class of next neighbor to connect to
connected = False # has the new node already found another node to connect to
l=1 # l-th attempt to connect this node type
while l <= repMax and not connected:
v = random.choice(classNodes[c])
if (not v==i and
not (i,v) in edges and
not (v,i) in edges):
connected = True
row.append(i)
col.append(v)
edges.add((i,v))
l += 1
# Create sparse matrix. If directed=False then insert edges in both directions => symmetric W
if directed is False:
row2 = list(row) # need to make a temp copy
row.extend(col)
col.extend(row2)
Ws = csr_matrix(([1]*len(row), (row, col)), shape=(n, n))
return Ws, X
def run(choice,
create_data=False,
add_data=False,
create_fig=True,
show_plot=False,
create_pdf=False,
show_pdf=False,
shorten_length=False,
show_arrows=True):
# -- Setup
CHOICE = choice
CREATE_DATA = create_data
ADD_DATA = add_data
SHOW_PDF = show_pdf
SHOW_PLOT = show_plot
CREATE_PDF = create_pdf
csv_filename = 'Fig_MHE_Optimal_ScalingFactor_d_{}.csv'.format(CHOICE)
header = [
'currenttime',
'option', # one option corresponds to one choice of weight vector. In practice, one choice of scaling factor (for weight vector)
'd',
'scaling',
'diff'
] # L2 norm between H and estimate
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename),
header,
append=False)
# -- Default Graph parameters
randomize = False
initial_h0 = None # initial vector to start finding optimal H
exponent = -0.3
length = 5
variant = 1
rep = 26
EC = True
scaling_vec = [0] + [0.1 * pow(10, 1 / 8)**x for x in range(33)]
num_options = len(scaling_vec)
scaling_vec = np.array(scaling_vec)
weight = np.array([np.power(scaling_vec, i) for i in range(5)])
weight = weight.transpose()
d_vec = list(range(3, 9)) + [10 * pow(10, 1 / 12)**x for x in range(13)]
# print(d_vec)
d_vec = [int(i) for i in d_vec]
fraction_of_minimum = 1.1 # scaling parameters that lead to optimum except for this scaling factor are included
ymin2 = 0.3
ymax2 = 500
xmin1 = 3
xmax1 = 100
xmin2 = 2.87
xmax2 = 105
xtick_lab = [3, 5, 10, 30, 100]
# ytick_lab1 = np.arange(0, 1, 0.1)
ytick_lab1 = [0.001, 0.01, 0.1, 1]
ytick_lab2 = [0.3, 1, 10, 100, 1000]
ymax1 = 0.2
ymin1 = 0.001
k = 3
a = 1
# -- Options
if CHOICE == 1: # #=100
n = 1000
h = 8
f = 0.1
distribution = 'uniform'
ytick_lab1 = [0.01, 0.1, 0.5]
ymax1 = 0.5
ymin1 = 0.01
elif CHOICE == 2: # selection #=124
n = 10000
h = 8
f = 0.1
distribution = 'powerlaw'
ymin1 = 0.003
elif CHOICE == 3: # special selection #=100
n = 10000
h = 8
f = 0.05
distribution = 'powerlaw'
ymin1 = 0.005
ymax1 = 0.5
elif CHOICE == 4: # selection #=100
n = 10000
h = 3
f = 0.1
distribution = 'powerlaw'
ymin1 = 0.003
elif CHOICE == 5: # #=5
n = 10000
h = 3
f = 0.1
distribution = 'uniform'
elif CHOICE == 6: # #=5
n = 10000
h = 8
f = 0.1
distribution = 'uniform'
elif CHOICE == 7: # special selection #=100
n = 10000
h = 3
f = 0.05
distribution = 'powerlaw'
ymax1 = 0.401
ymin1 = 0.003
else:
raise Warning("Incorrect choice!")
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(
seed=RANDOMSEED
) # seeds the actually used numpy random generator; both are used and thus needed
#print("CHOICE: {}".format(CHOICE))
# -- Create data
if CREATE_DATA or ADD_DATA:
for r in range(1, rep + 1):
# print('Repetition {}'.format(r))
for d in d_vec:
# print('d: {}'.format(d))
# -- Create graph
W, Xd = planted_distribution_model_H(n,
alpha=alpha0,
H=H0,
d_out=d,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
X1, ind = replace_fraction_of_rows(X0, 1 - f)
# -- Create estimates and compare against GT
for option in range(num_options):
H_est = estimateH(X1,
W,
method='MHE',
variant=variant,
distance=length,
EC=EC,
weights=weight[option],
randomize=randomize,
initial_h0=initial_h0)
diff = LA.norm(H_est - H0)
tuple = [str(datetime.datetime.now())]
text = [option, d, scaling_vec[option], diff]
tuple.extend(text)
save_csv_record(join(data_directory, csv_filename), tuple)
# -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
#print("\n-- df1: (length {}):\n{}".format(len(df1.index), df1.head(15)))
# Aggregate repetitions
df2 = df1.groupby(['d', 'scaling']).agg \
({'diff': [np.mean, np.std, np.size], # Multiple Aggregates
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values
] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'diff_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(15)))
# find minimum diff for each d, then join it back into df2
df3 = df2.groupby(['d']).agg \
({'diff_mean': [np.min], # Multiple Aggregates
})
df3.columns = ['_'.join(col).strip() for col in df3.columns.values
] # flatten the column hierarchy
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(90)))
df4 = pd.merge(
df2, df3, left_on='d', right_index=True
) # ! join df2 and df3 on column "d" from df2, and index (=d) from df3
# df4 = df4.drop(['index'], axis=1) # does not work
# print("\n-- df4 (length {}):\n{}".format(len(df4.index), df4.head(25)))
# Select columns for energy comparison plot: H0
df5 = df4.query('scaling==0')
# print("\n-- df5 (length {}):\n{}".format(len(df5.index), df5.head(90)))
# df5.drop('option', axis=1, inplace=True) # gives warning
df5 = df5.drop(['diff_mean_amin'], axis=1)
# print("\n-- df5: scaling==0 (length {}):\n{}".format(len(df5.index), df5.head(90)))
X_d = df5['d'].values # plot value
Y_diff0 = df5['diff_mean'].values # plot value
Y_diff0_std = df5['diff_std'].values # plot value
# Select columns for energy comparison plot: H5 optimal
df6 = df4.copy()
# print("\n-- df6 (length {}):\n{}".format(len(df6.index), df6.head(90)))
df6['cond'] = np.where((df6['diff_mean'] == df6['diff_mean_amin']), True,
False)
df6 = df6.query('cond==True')
df6.drop([
'cond',
], axis=1, inplace=True)
# print("\n-- df6: best scaling (length {}):\n{}".format(len(df6.index), df6.head(90)))
Y_diff1 = df6['diff_mean'].values # plot value
Y_diff1_std = df6['diff_std'].values # plot value
Y_scaling = df6['scaling'].values # plot value
# Select all (d, scaling) combinations that are close to optimal
df4['cond'] = np.where(
(df4['diff_mean'] <= fraction_of_minimum * df4['diff_mean_amin']),
True, False)
df7 = df4.query('cond==True')
df7.drop([
'cond',
], axis=1, inplace=True)
# print("\n-- df7: all good data points(length {}):\n{}".format(len(df7.index), df7.head(90)))
X_points = df7['d'].values # plot value
Y_points = df7['scaling'].values # plot value
# Select average (and lower and upper bound) on good data points
df8 = df7.groupby(['d']).agg \
({'scaling': [np.mean, np.amin, np.amax, ], # Multiple Aggregates
})
df8.columns = ['_'.join(col).strip() for col in df8.columns.values
] # flatten the column hierarchy
df8.reset_index(inplace=True) # remove the index hierarchy
# print("\n-- df8: input for moving average (length {}):\n{}".format(len(df8.index), df8.head(15)))
Y_point_mean = df8['scaling_mean'].values # plot value
if SHOW_PLOT or SHOW_PDF or CREATE_PDF:
# -- Setup figure
fig_filename = 'Fig_MHE_Optimal_ScalingFactor_diff_d_{}.pdf'.format(
CHOICE)
mpl.rcParams['backend'] = 'pdf'
mpl.rcParams['lines.linewidth'] = 3
mpl.rcParams['font.size'] = 14
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 16
mpl.rcParams['axes.edgecolor'] = '111111' # axes edge color
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['figure.figsize'] = [4, 4]
mpl.rcParams[
'xtick.major.pad'] = 4 # padding of tick labels: default = 4
mpl.rcParams[
'ytick.major.pad'] = 4 # padding of tick labels: default = 4
fig = plt.figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
# -- Draw the plots
p1 = ax.plot(X_d, Y_diff0, color='blue', linewidth=2)
ax.fill_between(X_d,
Y_diff0 + Y_diff0_std,
Y_diff0 - Y_diff0_std,
facecolor='blue',
alpha=0.2,
edgecolor='none',
label=r'$\tilde {\mathbf{H}}$')
p2 = ax.plot(X_d, Y_diff1, color='red', linewidth=2)
ax.fill_between(X_d,
Y_diff1 + Y_diff1_std,
Y_diff1 - Y_diff1_std,
facecolor='red',
alpha=0.2,
edgecolor='none',
label=r'$\tilde {\mathbf{H}}^{\ell}_{\mathrm{EC}}$')
plt.xscale('log')
plt.yscale('log')
# -- Title and legend
if distribution == 'uniform':
distribution_label = ',$uniform'
else:
distribution_label = '$'
plt.title(r'$\!\!\!n\!=\!{}\mathrm{{k}}, h\!=\!{}, f\!=\!{}{}'.format(
int(n / 1000), h, f, distribution_label))
handles, labels = ax.get_legend_handles_labels()
legend = plt.legend(
handles,
labels,
loc='upper right', # 'upper right'
handlelength=1.5,
labelspacing=0, # distance between label entries
handletextpad=
0.3, # distance between label and the line representation
# title='Variants',
borderaxespad=0.2, # distance between legend and the outer axes
borderpad=0.3, # padding inside legend box
)
frame = legend.get_frame()
# frame.set_linewidth(0.0)
frame.set_alpha(0.9) # 0.8
# -- Figure settings and save
plt.xticks(xtick_lab, xtick_lab)
plt.yticks(ytick_lab1, ytick_lab1)
plt.grid(b=True,
which='minor',
axis='both',
alpha=0.2,
linestyle='solid',
linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
plt.grid(b=True,
which='major',
axis='y',
alpha=0.2,
linestyle='solid',
linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
plt.xlabel(r'$d$', labelpad=0) # labelpad=0
plt.ylabel(r'L$^2$ norm', labelpad=-5)
if xmin1 is None:
xmin1 = plt.xlim()[0]
if xmax1 is None:
xmax1 = plt.xlim()[1]
if ymin1 is None:
ymin1 = plt.ylim()[1]
if ymax1 is None:
ymax1 = plt.ylim()[1]
plt.xlim(xmin1, xmax1)
plt.ylim(ymin1, ymax1)
if CREATE_PDF:
plt.savefig(join(figure_directory, fig_filename),
format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
frameon=None)
if SHOW_PDF:
showfig(join(figure_directory,
fig_filename)) # shows actually created PDF
if SHOW_PLOT:
plt.show()
if SHOW_PLOT or SHOW_PDF or CREATE_PDF:
# -- Setup figure
fig_filename = 'Fig_MHE_Optimal_ScalingFactor_lambda_d_{}.pdf'.format(
CHOICE)
mpl.rcParams['backend'] = 'pdf'
mpl.rcParams['lines.linewidth'] = 3
mpl.rcParams['font.size'] = 14
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 14
mpl.rcParams['axes.edgecolor'] = '111111' # axes edge color
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['figure.figsize'] = [4, 4]
mpl.rcParams[
'xtick.major.pad'] = 4 # padding of tick labels: default = 4
mpl.rcParams[
'ytick.major.pad'] = 4 # padding of tick labels: default = 4
fig = plt.figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
# -- Draw the plots
p1 = ax.plot(
X_points,
Y_points,
color='0.8',
linewidth=0,
marker='o',
markeredgewidth=0.0,
clip_on=False, # cut off data points outside of plot area
zorder=9,
markevery=1,
label=r'$\!\leq${} Opt'.format(fraction_of_minimum))
p2 = ax.plot(
X_d,
Y_scaling,
color='red',
linewidth=0,
marker='o',
clip_on=False, # cut off data points outside of plot area
zorder=10,
markevery=1,
label=r'Opt$(\lambda|d)$')
plt.xscale('log')
plt.yscale('log')
# Draw the moving average from Y_point_mean
def movingaverage(interval, window_size):
window = np.ones(int(window_size)) / float(window_size)
return np.convolve(interval, window, 'same')
Y_point_mean_window = movingaverage(Y_point_mean, 3)
p5 = ax.plot(X_d,
Y_point_mean_window,
color='red',
linewidth=1,
marker=None)
# p3 = ax.plot(X_d, Y_point_mean, color='red', linewidth=1, marker=None)
# -- Title and legend
if distribution == 'uniform':
distribution_label = ',$uniform'
else:
distribution_label = '$'
plt.title(r'$\!\!\!n\!=\!{}\mathrm{{k}}, h\!=\!{}, f\!=\!{}{}'.format(
int(n / 1000), h, f, distribution_label))
handles, labels = ax.get_legend_handles_labels()
legend = plt.legend(
handles[::-1],
labels[::-1],
loc='upper left', # 'upper right'
handlelength=1,
labelspacing=0, # distance between label entries
handletextpad=
0.3, # distance between label and the line representation
borderaxespad=0.3, # distance between legend and the outer axes
borderpad=0.1, # padding inside legend box
numpoints=1, # put the marker only once
)
frame = legend.get_frame()
# frame.set_linewidth(0.0)
frame.set_alpha(0.9) # 0.8
# -- Figure settings and save
plt.xticks(xtick_lab, xtick_lab)
plt.yticks(ytick_lab2, ytick_lab2)
plt.grid(b=True,
which='minor',
alpha=0.2,
linestyle='solid',
linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
plt.xlabel(r'$d$', labelpad=0) # labelpad=0
plt.ylabel(r'$\lambda$', labelpad=0, rotation=0)
if xmin2 is None:
xmin2 = plt.xlim()[0]
if xmax2 is None:
xmax2 = plt.xlim()[1]
if ymin2 is None:
ymin2 = plt.ylim()[0]
if ymax2 is None:
ymax2 = plt.ylim()[1]
plt.xlim(xmin2, xmax2)
plt.ylim(ymin2, ymax2)
if CREATE_PDF:
plt.savefig(join(figure_directory, fig_filename),
format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
frameon=None)
if SHOW_PDF:
showfig(join(figure_directory,
fig_filename)) # shows actually created PDF
if SHOW_PLOT:
plt.show()
def test_dictionary_transform():
print("\n-- 'check_dictionary_beliefs', 'from_dictionary_beliefs' --")
Xd = {1: 1, 2: 2, 3: 3, 5: 1}
print("Xd:", Xd)
print("zeroindexing=True:")
print("X:\n", from_dictionary_beliefs(Xd,
n=None,
k=None,
zeroindexing=True))
print("zeroindexing=False:")
print("X:\n",
from_dictionary_beliefs(Xd, n=None, k=None, zeroindexing=False))
print("zeroindexing=True, n=7, k=5:")
print("X:\n", from_dictionary_beliefs(Xd, n=7, k=5, zeroindexing=True))
print("\nzeroindexing=False, fullBeliefs=True:")
X1 = {1: 1, 2: 2, 3: 3, 4: 1}
assert check_dictionary_beliefs(X1,
n=None,
k=None,
zeroindexing=False,
fullBeliefs=True)
print("X1:", X1)
print("zeroindexing=True, fullBeliefs=True:")
X2 = {0: 0, 1: 1, 2: 2, 3: 0}
assert check_dictionary_beliefs(X2,
n=None,
k=None,
zeroindexing=True,
fullBeliefs=True)
print("X2:", X2)
print("zeroindexing=True, fullBeliefs=False:")
X3 = {0: 0, 1: 1, 2: 2, 4: 0}
assert check_dictionary_beliefs(X3,
n=None,
k=None,
zeroindexing=True,
fullBeliefs=False)
print("X3:", X3)
print("zeroindexing=True, fullBeliefs=False:")
X4 = {0: 1, 2: 2, 4: 0}
assert check_dictionary_beliefs(X4,
n=None,
k=None,
zeroindexing=True,
fullBeliefs=False)
print("X4:", X4)
print("\nerrors:")
X5 = {0: 0, 1: 1, 2: 3, 3: 0}
print("X5:", X5)
assert not check_dictionary_beliefs(
X5, n=None, k=None, zeroindexing=False, fullBeliefs=True)
X6 = {0: 1, 1: 1, 2: 2, 4: 1}
print("X6:", X6)
assert not check_dictionary_beliefs(
X6, n=None, k=None, zeroindexing=True, fullBeliefs=True)
print("\n-- 'check_explicit_beliefs', 'to_dictionary_beliefs' --")
X = np.array([
[1., 0, 0],
[0, 0, 0],
[0, 0, 1],
])
print("original X:\n", X)
print("Stacked X:\n", np.hstack(X))
print("List of X entires:\n", set(np.hstack(X)))
print("Verify: ", set(np.hstack(X)) == {0, 1})
print("Verify: ", {0., 1.} == {0, 1})
assert check_explicit_beliefs(X)
Y = np.array([1., 0, 0])
assert check_explicit_beliefs(Y)
Xd = to_dictionary_beliefs(X)
print("Xd: ", Xd)
def run(choice, create_data=False, add_data=False, show_plot=False, create_pdf=False, show_pdf=False, shorten_length=False,
show_arrows=False):
# -- Setup
CHOICE = choice
CREATE_DATA = create_data
ADD_DATA = add_data
SHOW_PLOT = show_plot
SHOW_PDF = show_pdf
CREATE_PDF = create_pdf
SHOW_STD = True ## FALSE for just scatter plot points
SHOW_ARROWS = show_arrows
# -- Default Graph parameters
rep_SameGraph = 1 # iterations on same graph
distribution = 'powerlaw'
exponent = -0.3
length = 5
variant = 1
EC = False
numberOfSplits = 1
scaling_vec = [None]*10
ymin = 0.3
ymax = 1
xmin = 1e-3
xmax = 1e3
xtick_lab = [1e-3, 0.01, 0.1, 1, 10, 100, 1000]
xtick_labels = [r'$10^{-3}$', r'$10^{-2}$', r'$10^{-1}$', r'$1$', r'$10$', r'$10^{2}$', r'$10^{3}$']
ytick_lab = np.arange(0, 1.1, 0.1)
k = 3
a = 1
rep_DifferentGraphs = 1 # iterations on different graphs
err = 0
avoidNeighbors = False
convergencePercentage_W = 0.99
facecolor_vec = ["#4C72B0", "#55A868", "#8172B2", "#C44E52", "#CCB974", "#64B5CD"]
label_vec = ['MCE', 'LCE', 'DCE', 'Holdout']
linewidth_vec = [4, 3, 1, 2, 2, 1]
# clip_ons = [True, True, True, True, True, True]
FILEZNAME = 'Fig_timing_accuracy_learning'
marker_vec = ['s', '^', 'v', 'o', 'x', '+', 'None'] #'^'
length_vec = [5]
stratified = True
f = 0.01
numMaxIt_vec = [10]*7
alpha_vec = [0] * 7
beta_vec = [0] * 7 # TODO: LinBP does not use beta. Also SSLH uses alpha, but not beta for W^row! Now fixed
gamma_vec = [0] * 7
s_vec = [0.5] * 7
# -- Main Options
if CHOICE == 1: # Main graph
n = 1000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['MHE'] + ['LHE'] + ['DHE'] + ['DHE'] + ['Holdout'] + ['GS']
label_vec = ['MCE', 'LCE', 'DCE', 'DCE r', 'Holdout', 'GS']
randomize_vec = [False]*3 + [True] + [None]*2
scaling_vec = [None]*2 + [10, 100] + [None]*2
splits_vec = [1, 2, 4, 8]
elif CHOICE == 2:
n = 1000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['MHE'] + ['LHE'] + ['DHE'] + ['DHE'] + ['GS']
label_vec = ['MCE', 'LCE', 'DCE', 'DCE r', 'GS']
randomize_vec = [False]*3 + [True] + [None]
scaling_vec = [None]*2 + [10, 100] + [None]
elif CHOICE == 3:
n = 1000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['MHE'] + ['LHE'] + ['DHE'] + ['DHE'] + ['GS']
label_vec = ['MCE', 'LCE', 'DCE', 'DCE r', 'GS']
randomize_vec = [False]*3 + [True] + [None]
scaling_vec = [None]*2 + [10, 100] + [None]
f = 0.02
elif CHOICE == 4: # TODO: Overnight Wolfgang
n = 1000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['MHE'] + ['LHE'] + ['DHE'] + ['DHE'] + ['Holdout'] + ['GS']
label_vec = ['MCE', 'LCE', 'DCE', 'DCE r', 'Holdout', 'GS']
randomize_vec = [False]*3 + [True] + [None]*2
scaling_vec = [None]*2 + [10, 100] + [None]*2
splits_vec = [1, 2, 4, 8, 16]
elif CHOICE == 5: # Toy graph with 100 nodes
n = 100
h = 3
d = 8
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['MHE'] + ['LHE'] + ['DHE'] + ['DHE'] + ['Holdout'] + ['GS']
label_vec = ['MCE', 'LCE', 'DCE', 'DCE r', 'Holdout', 'GS']
randomize_vec = [False]*3 + [True] + [None]*2
scaling_vec = [None]*2 + [10, 100] + [None]*2
splits_vec = [1, 2, 4, 8]
f=0.05
elif CHOICE == 6: # To be run by Prakhar on Cluster
n = 10000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['MHE'] + ['LHE'] + ['DHE'] + ['DHE'] + ['Holdout'] + ['GS']
label_vec = ['MCE', 'LCE', 'DCE', 'DCEr', 'Holdout', 'GS']
randomize_vec = [False]*3 + [True] + [None]*2
scaling_vec = [None]*2 + [10, 100] + [None]*2
splits_vec = [1, 2, 4, 8]
f=0.003
xmin = 1e-2
# ymax = 0.9
ymin = 0.2
ymax = 0.9
xmin = 1e-2
xmax = 1e3
elif CHOICE == 7:
n = 1000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['MHE'] + ['LHE'] + ['DHE'] + ['DHE'] + ['Holdout'] + ['GS']
label_vec = ['MCE', 'LCE', 'DCE', 'DCE r', 'Holdout', 'GS']
randomize_vec = [False]*3 + [True] + [None]*2
scaling_vec = [None]*2 + [10, 100] + [None]*2
splits_vec = [1, 2, 4, 8, 16]
f=0.009
# elif CHOICE == 8: # not working well
# n = 1000
# h = 3
# d = 25
# option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
# learning_method_vec = ['MHE'] + ['LHE'] + ['DHE'] + ['DHE'] + ['Holdout'] + ['GS']
# label_vec = ['MCE', 'LCE', 'DCE', 'DCE r', 'Holdout', 'GS']
# randomize_vec = [False]*3 + [True] + [None]*2
# scaling_vec = [None]*2 + [10, 100] + [None]*2
# splits_vec = [1, 2, 4, 8, 16]
# f=0.005
else:
raise Warning("Incorrect choice!")
csv_filename = '{}_{}.csv'.format(FILEZNAME, CHOICE)
header = ['currenttime',
'option',
'lensplit',
'f',
'accuracy',
'timetaken']
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename), header, append=False)
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
H0c = to_centering_beliefs(H0)
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(seed=RANDOMSEED) # seeds the actually used numpy random generator; both are used and thus needed
# print("CHOICE: {}".format(CHOICE))
# -- Create data
if CREATE_DATA or ADD_DATA:
for i in range(rep_DifferentGraphs): # create several graphs with same parameters
# print("\ni: {}".format(i))
W, Xd = planted_distribution_model_H(n, alpha=alpha0, H=H0, d_out=d,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
for j in range(rep_SameGraph): # repeat several times for same graph
# print("j: {}".format(j))
ind = None
X1, ind = replace_fraction_of_rows(X0, 1-f, avoidNeighbors=avoidNeighbors, W=W, ind_prior=ind, stratified = stratified) # TODO: stratified sampling option = True
X2 = introduce_errors(X1, ind, err)
for option_index, (learning_method, alpha, beta, gamma, s, numMaxIt, weight, randomize, option) in \
enumerate(zip(learning_method_vec, alpha_vec, beta_vec, gamma_vec, s_vec, numMaxIt_vec, scaling_vec, randomize_vec, option_vec)):
# weight = np.array([np.power(scaling, i) for i in range(5)]) # TODO: now enough to specify weight as a scalar!
H_est_dict = {}
timeTaken_dict = {}
# -- Learning
if learning_method == 'Holdout' :
for numberOfSplits in splits_vec:
prev_time = time.time()
H_est_dict[numberOfSplits] = estimateH_baseline_serial(X2, ind, W, numMax=numMaxIt,
# ignore_rows=ind,
numberOfSplits=numberOfSplits,
# method=learning_method, variant=1, distance=length,
EC=EC,
weights=weight, alpha=alpha, beta=beta, gamma=gamma)
timeTaken = time.time() - prev_time
timeTaken_dict[numberOfSplits] = timeTaken
elif learning_method in ['LHE', 'MHE', 'DHE']: # TODO: no smartInit, just randomization as option
for length in length_vec:
prev_time = time.time()
H_est_dict[length] = estimateH(X2, W, method=learning_method, variant=1, randomize=randomize, distance=length, EC=EC, weights=weight)
timeTaken = time.time() - prev_time
timeTaken_dict[length] = timeTaken
elif learning_method == 'GS':
H_est_dict['GS'] = H0
for key in H_est_dict:
H_est = H_est_dict[key]
H2c = to_centering_beliefs(H_est)
# print("H_estimated by {} is \n".format(learning_method), H_est)
# print("H0 is \n", H0)
# print("randomize was: ", randomize)
# Propagation
X2c = to_centering_beliefs(X2, ignoreZeroRows=True) # try without
eps_max = eps_convergence_linbp_parameterized(H2c, W,
method='noecho',
alpha=alpha, beta=beta, gamma=gamma,
X=X2)
eps = s * eps_max
# print("Max Eps ", eps_max)
try:
F, actualIt, actualPercentageConverged = \
linBP_symmetric_parameterized(X2, W, H2c * eps,
method='noecho',
alpha=alpha, beta=beta, gamma=gamma,
numMaxIt=numMaxIt,
convergencePercentage=convergencePercentage_W,
convergenceThreshold=0.99,
debug=2)
except ValueError as e:
print(
"ERROR: {} with {}: d={}, h={}".format(e, learning_method, d, h))
else:
accuracy_X = matrix_difference(X0, F, ignore_rows=ind)
tuple = [str(datetime.datetime.now())]
if learning_method == 'Holdout':
text = [option,"split{}".format(key), f, accuracy_X, timeTaken_dict[key]]
elif learning_method in ['MHE', 'DHE', 'LHE']:
text = [option, "len{}".format(key), f, accuracy_X, timeTaken_dict[key]]
elif learning_method == 'GS':
text = [option, 0, f, accuracy_X, 0]
tuple.extend(text)
# print("option: {}, f: {}, actualIt: {}, accuracy: {}".format(option, f, actualIt, accuracy_X))
save_csv_record(join(data_directory, csv_filename), tuple)
# -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1: (length {}):\n{}".format(len(df1.index), df1.head(15)))
# Aggregate repetitions
df2 = df1.groupby(['option', 'lensplit', 'f']).agg \
({'accuracy': [np.mean, np.std, np.size], # Multiple Aggregates
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'accuracy_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(15)))
df3 = df1.groupby(['option', 'lensplit', 'f']).agg({'timetaken': [np.median] })
df3.columns = ['_'.join(col).strip() for col in df3.columns.values] # flatten the column hierarchy
df3.reset_index(inplace=True) # remove the index hierarchy
# resultdf3 = df3.sort(['timetaken'], ascending=1)
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(15)))
X_time_median_dict = {}
Y_acc_dict = {}
Y_std_dict = {}
for option in option_vec:
Y_acc_dict[option] = df2.loc[(df2['option'] == option), "accuracy_mean"].values
Y_std_dict[option] = df2.loc[(df2['option'] == option), "accuracy_std"].values
X_time_median_dict[option] = df3.loc[(df3['option'] == option), "timetaken_median"].values
# print("option: ", option)
# print("Y_acc_dict[option]: ", Y_acc_dict[option])
# print("Y_std_dict[option]: ", Y_std_dict[option])
# print("X_time_median_dict[option]: ", X_time_median_dict[option])
# -- Setup figure
fig_filename = '{}_{}.pdf'.format(FILEZNAME, CHOICE)
mpl.rc('font', **{'family': 'sans-serif', 'sans-serif': [u'Arial', u'Liberation Sans']})
mpl.rcParams['axes.labelsize'] = 18
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['legend.fontsize'] = 14
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['xtick.major.pad'] = 2 # padding of tick labels: default = 4
mpl.rcParams['ytick.major.pad'] = 1 # padding of tick labels: default = 4
mpl.rcParams['xtick.direction'] = 'out' # default: 'in'
mpl.rcParams['ytick.direction'] = 'out' # default: 'in'
mpl.rcParams['figure.figsize'] = [4, 4]
fig = figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
SHOW_ARROWS = True
for choice, color, learning_method, label, linewidth, marker in \
zip(option_vec, facecolor_vec, learning_method_vec, label_vec, linewidth_vec, marker_vec):
if learning_method == 'Holdout':
# Draw std
X1 = X_time_median_dict[choice]
s = X1.argsort()
X1 = X1[s]
Y1 = Y_acc_dict[choice][s]
Y2 = Y_std_dict[choice][s]
if SHOW_STD:
ax.fill_between(X1, Y1 + Y2, Y1 - Y2, facecolor=color, alpha=0.2, edgecolor=None, linewidth=0)
ax.plot(X1, Y1 + Y2, linewidth=0.5, color='0.8', linestyle='solid')
ax.plot(X1, Y1 - Y2, linewidth=0.5, color='0.8', linestyle='solid')
ax.set_ylim(bottom=ymin)
ax.plot(X1, Y1, linewidth=linewidth, color=color, linestyle='solid', label=label, zorder=20, marker='x', markersize=linewidth + 5, markeredgewidth=1)
ax.annotate(np.round(X1[1], decimals=1), xy=(X1[1], Y1[1] - 0.05), color=color, va='center', annotation_clip=False, zorder=5)
else:
ax.scatter(list(X1), list(Y1),
color=color, label=label, marker='x', s=42)
elif learning_method == 'GS':
ax.plot([1e-4, 1e4], [Y_acc_dict[choice], Y_acc_dict[choice]],
linewidth=1, color='black',
linestyle='dashed', zorder=0,
marker=None,
label=label,
)
else: # For all other
if SHOW_STD:
ax.errorbar(list(X_time_median_dict[choice]), list(Y_acc_dict[choice]), yerr=Y_std_dict[choice],
fmt='-o', linewidth=2, color=color,
label=label, marker=marker, markersize=8)
ax.annotate(np.round(X_time_median_dict[choice], decimals=2), xy=(X_time_median_dict[choice], Y_acc_dict[choice]-0.05), color=color, va='center',
annotation_clip=False, zorder=5)
else:
ax.scatter(list(X_time_median_dict[choice]), list(Y_acc_dict[choice]),
color=color, label=label, marker=marker, s=42)
if SHOW_ARROWS:
dce_opt = 'opt4'
holdout_opt = 'opt5'
ax.annotate(s='', xy=(X_time_median_dict[dce_opt], Y_acc_dict[dce_opt]-0.3), xytext=(X_time_median_dict[holdout_opt][2]+0.02, Y_acc_dict[dce_opt]-0.3), arrowprops=dict(arrowstyle='<->'))
ax.annotate(str(int(np.round(X_time_median_dict[holdout_opt][2] / X_time_median_dict[dce_opt]))) + 'x', xy=((X_time_median_dict[dce_opt] + X_time_median_dict[holdout_opt][2])/100, Y_acc_dict[dce_opt]-0.28),
color='black', va='center',
# bbox = dict(boxstyle="round,pad=0.3", fc="w"),
annotation_clip=False, zorder=5)
# -- Title and legend
title(r'$\!\!\!n\!=\!{}\mathrm{{k}}, d\!=\!{}, h\!=\!{}, f\!=\!{}$'.format(int(n / 1000), d, h, f))
handles, label_vec = ax.get_legend_handles_labels()
for i, (h, learning_method) in enumerate(zip(handles, learning_method_vec)): # remove error bars in legend
if isinstance(handles[i], collections.Container):
handles[i] = handles[i][0]
# plt.legend(loc='upper left', numpoints=1, ncol=3, fontsize=8, bbox_to_anchor=(0, 0))
SHOW_STD = False
legend = plt.legend(handles, label_vec,
loc='upper right', # 'upper right'
handlelength=2,
fontsize=12,
labelspacing=0.2, # distance between label entries
handletextpad=0.3, # distance between label and the line representation
borderaxespad=0.2, # distance between legend and the outer axes
borderpad=0.3, # padding inside legend box
numpoints=1, # put the marker only once
)
if not(SHOW_STD):
legend = plt.legend(handles, label_vec,
loc='upper right', # 'upper right'
handlelength=2,
fontsize=10,
labelspacing=0.2, # distance between label entries
handletextpad=0.3, # distance between label and the line representation
borderaxespad=0.2, # distance between legend and the outer axes
borderpad=0.3, # padding inside legend box
numpoints=1, # put the marker only once
scatterpoints=1 # display only one-scatter point in legend
)
# # legend.set_zorder(1)
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.9) # 0.8
# -- Figure settings and save
plt.xscale('log')
plt.xticks(xtick_lab, xtick_labels)
plt.yticks(ytick_lab, ytick_lab)
ax.yaxis.set_major_formatter(mpl.ticker.FormatStrFormatter('%.1f'))
ax.yaxis.set_ticks_position('left')
ax.xaxis.set_ticks_position('bottom')
ax.set_ylim(bottom=ymin)
grid(b=True, which='major', axis='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
grid(b=True, which='minor', axis='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
xlim(xmin, xmax)
ylim(ymin, ymax)
xlabel(r'Time Median (sec)', labelpad=0) # labelpad=0
ylabel(r'Accuracy', labelpad=0)
if CREATE_PDF:
savefig(join(figure_directory, fig_filename), format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
frameon=None)
if SHOW_PDF:
showfig(join(figure_directory, fig_filename))
if SHOW_PLOT:
plt.show()
def run(choice,
create_data=False,
add_data=False,
show_plot=False,
create_pdf=False,
show_pdf=False,
show_fig=True):
# -- Setup
CHOICE = choice
CREATE_DATA = create_data
ADD_DATA = add_data
SHOW_PLOT = show_plot
CREATE_PDF = create_pdf
SHOW_PDF = show_pdf
SHOW_FIG1 = show_fig
SHOW_FIG2 = show_fig
csv_filename = 'Fig_MHE_Optimal_ScalingFactor_f_lambda10_{}.csv'.format(
CHOICE)
header = [
'currenttime',
'option', # one option corresponds to one choice of weight vector. In practice, one choice of scaling factor (for weight vector)
'f',
'scaling',
'diff'
] # L2 norm between H and estimate
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename),
header,
append=False)
# -- Default Graph parameters
rep = 100
randomize = False
initial_h0 = None # initial vector to start finding optimal H
distribution = 'powerlaw'
exponent = -0.3
rep_differentGraphs = 1
EC = True
f_vec = [0.9 * pow(0.1, 1 / 12)**x for x in range(42)]
fraction_of_minimum = 1.1 # scaling parameters that lead to optimum except for this scaling factor are included
ymin2 = 0.28
ymax2 = 500
xmin = 0.001
# xmin = 0.0005
xmax = None
xtick_lab = [0.001, 0.01, 0.1, 1]
# ytick_lab1 = np.arange(0, 1, 0.1)
ytick_lab2 = [0.3, 1, 10, 100, 1000]
ymax1 = 1.2
ymin1 = 0.001
# ytick_lab1 = [0.001, 0.01, 0.1, 1]
k = 3
a = 1
stratified = True
gradient = False
n = 10000
# color_vec = ['blue', 'orange', 'red']
color_vec = ["#4C72B0", "#55A868", "#C44E52", "#CCB974", "#64B5CD"]
color_vec = ["#4C72B0", "#8172B2", "#C44E52"]
# label_vec = [r'$\tilde {\mathbf{H}}$', r'$\tilde{\mathbf{H}}^{(5)}_{\mathrm{NB}}$', r'$\tilde {\mathbf{H}}^{(5)}_{\mathrm{NB}}$ r']
label_vec = ['MCE', 'DCE', 'DCEr']
marker_vec = ['s', 'x', 'o']
legendPosition = 'upper right'
# -- Options
if CHOICE == 11:
h = 8
d = 25
option_vec = ['opt1', 'opt2', 'opt3']
scaling_vec = [0, 10, 10]
randomize_vec = [False, False, True]
length_vec = [1, 5, 5]
elif CHOICE == 12:
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3']
scaling_vec = [0, 10, 10]
randomize_vec = [False, False, True]
length_vec = [1, 5, 5]
elif CHOICE == 13:
h = 8
d = 10
option_vec = ['opt1', 'opt2', 'opt3']
scaling_vec = [0, 10, 10]
randomize_vec = [False, False, True]
length_vec = [1, 5, 5]
elif CHOICE == 14:
h = 3
d = 10
option_vec = ['opt1', 'opt2', 'opt3']
scaling_vec = [0, 10, 10]
randomize_vec = [False, False, True]
length_vec = [1, 5, 5]
elif CHOICE == 15:
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3']
scaling_vec = [0, 10, 100]
randomize_vec = [False, False, True]
length_vec = [1, 5, 5]
# elif CHOICE == 16:
# n = 10000
# h = 3
# d = 10
# option_vec = ['opt1', 'opt2', 'opt3']
# scaling_vec = [0, 50, 50]
# randomize_vec = [False, False, True]
# length_vec = [1, 5, 5]
elif CHOICE == 17:
n = 1000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3']
scaling_vec = [0, 10, 100]
randomize_vec = [False, False, True]
length_vec = [1, 5, 5]
elif CHOICE == 18:
n = 1000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3']
scaling_vec = [0, 10, 10]
randomize_vec = [False, False, True]
length_vec = [1, 5, 5]
# -- Options
elif CHOICE == 19:
h = 8
d = 25
option_vec = ['opt1', 'opt2', 'opt3']
scaling_vec = [0, 10, 100]
randomize_vec = [False, False, True]
length_vec = [1, 5, 5]
elif CHOICE == 20:
h = 8
d = 25
option_vec = ['opt1', 'opt2', 'opt3']
scaling_vec = [0, 10, 100]
randomize_vec = [False, False, True]
length_vec = [1, 5, 5]
gradient = True
legendPosition = 'center right'
else:
raise Warning("Incorrect choice!")
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(
seed=RANDOMSEED
) # seeds the actually used numpy random generator; both are used and thus needed
# print("CHOICE: {}".format(CHOICE))
# -- Create data
if CREATE_DATA or ADD_DATA:
for rs in range(1, rep_differentGraphs + 1):
# print('Graph {}'.format(rs))
# -- Create graph
W, Xd = planted_distribution_model_H(n,
alpha=alpha0,
H=H0,
d_out=d,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
for r in range(1, rep + 1):
# print('Repetition {}'.format(r))
for f in f_vec:
# -- Sample labeled data
X1, ind = replace_fraction_of_rows(X0,
1 - f,
stratified=stratified)
# -- Calculate number of labeled neighbors
M_vec = M_observed(W, X1, distance=5, NB=True)
M = M_vec[1]
num_N = np.sum(M)
# print("f={:1.4f}, number labeled neighbors={}".format(f, num_N))
# print("M_vec:\n{}".format(M_vec))
# -- Create estimates and compare against GT
for option, scaling, randomize, length in zip(
option_vec, scaling_vec, randomize_vec,
length_vec):
H_est = estimateH(X1,
W,
method='DHE',
variant=1,
distance=length,
EC=EC,
weights=scaling,
randomize=randomize,
initial_H0=initial_h0,
gradient=gradient)
diff = LA.norm(H_est - H0)
tuple = [str(datetime.datetime.now())]
text = [option, f, scaling, diff]
tuple.extend(text)
save_csv_record(join(data_directory, csv_filename),
tuple)
# print("diff={:1.4f}, H_est:\n{}".format(diff, H_est))
# -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1: (length {}):\n{}".format(len(df1.index), df1.head(15)))
# Aggregate repetitions
df2 = df1.groupby(['option', 'f']).agg \
({'diff': [np.mean, np.std, np.size], # Multiple Aggregates
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values
] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'diff_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(15)))
# Pivot table
df3 = pd.pivot_table(df2,
index=['f'],
columns=['option'],
values=['diff_mean', 'diff_std']) # Pivot
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
df3.columns = ['_'.join(col).strip() for col in df3.columns.values
] # flatten the column hierarchy
df3.reset_index(inplace=True) # remove the index hierarchy
# df2.rename(columns={'time_size': 'count'}, inplace=True)
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
# Extract values
X_f = df3['f'].values # plot x values
Y = []
Y_std = []
for option in option_vec:
Y.append(df3['diff_mean_{}'.format(option)].values)
Y_std.append(df3['diff_std_{}'.format(option)].values)
# print("X_f:\n", X_f)
# print("Y:\n", Y)
# print("Y_std:\n", Y_std)
if SHOW_FIG1:
# -- Setup figure
fig_filename = 'Fig_MHE_Optimal_ScalingFactor_diff_f_lambda10_{}.pdf'.format(
CHOICE)
mpl.rcParams['backend'] = 'pdf'
mpl.rcParams['lines.linewidth'] = 3
mpl.rcParams['font.size'] = 14
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 16
mpl.rcParams['axes.edgecolor'] = '111111' # axes edge color
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['figure.figsize'] = [4, 4]
mpl.rcParams[
'xtick.major.pad'] = 4 # padding of tick labels: default = 4
mpl.rcParams[
'ytick.major.pad'] = 4 # padding of tick labels: default = 4
fig = plt.figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
# -- Draw the plots
for i, (color, marker) in enumerate(zip(color_vec, marker_vec)):
p = ax.plot(X_f,
Y[i],
color=color,
linewidth=3,
label=label_vec[i],
marker=marker)
if i != 1:
ax.fill_between(X_f,
Y[i] + Y_std[i],
Y[i] - Y_std[i],
facecolor=color,
alpha=0.2,
edgecolor='none')
plt.xscale('log')
plt.yscale('log')
# -- Title and legend
if distribution == 'uniform':
distribution_label = ',$uniform'
else:
distribution_label = '$'
plt.title(r'$\!\!\!n\!=\!{}\mathrm{{k}}, h\!=\!{}, d\!=\!{}{}'.format(
int(n / 1000), h, d, distribution_label))
handles, labels = ax.get_legend_handles_labels()
legend = plt.legend(
handles,
labels,
loc=legendPosition, # 'upper right'
handlelength=1.5,
labelspacing=0, # distance between label entries
handletextpad=
0.3, # distance between label and the line representation
# title='Variants',
borderaxespad=0.2, # distance between legend and the outer axes
borderpad=0.1, # padding inside legend box
)
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.9) # 0.8
# -- Figure settings and save
plt.xticks(xtick_lab, xtick_lab)
# plt.yticks(ytick_lab1, ytick_lab1)
plt.grid(b=True,
which='minor',
axis='both',
alpha=0.2,
linestyle='solid',
linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
plt.grid(b=True,
which='major',
axis='y',
alpha=0.2,
linestyle='solid',
linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
plt.xlabel(r'Label Sparsity $(f)$', labelpad=0) # labelpad=0
plt.ylabel(r'L2 norm', labelpad=-5)
if xmin is None:
xmin = plt.xlim()[0]
if xmax is None:
xmax = plt.xlim()[1]
if ymin1 is None:
ymin1 = plt.ylim()[1]
if ymax1 is None:
ymax1 = plt.ylim()[1]
plt.xlim(xmin, xmax)
plt.ylim(ymin1, ymax1)
if CREATE_PDF:
plt.savefig(join(figure_directory, fig_filename),
format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
frameon=None)
if SHOW_FIG1:
plt.show()
if SHOW_PDF:
os.system('{} "'.format(open_cmd[sys.platform]) +
join(figure_directory, fig_filename) +
'"') # shows actually created PDF
def run(choice,
create_data=False,
add_data=False,
show_plot=False,
create_pdf=False,
show_pdf=False,
shorten_length=False):
# -- Setup
CHOICE = choice
CREATE_DATA = create_data
ADD_DATA = add_data
SHOW_PLOT = show_plot
SHOW_PDF = show_pdf
CREATE_PDF = create_pdf
SHOW_ARROWS = False
STD_FILL = False
CALCULATE_DATA_STATISTICS = False
csv_filename = 'Fig_timing_VaryK_{}.csv'.format(CHOICE)
header = ['currenttime', 'option', 'k', 'f', 'time']
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename),
header,
append=False)
# -- Default Graph parameters
rep_SameGraph = 2 # iterations on same graph
initial_h0 = None # initial vector to start finding optimal H
distribution = 'powerlaw'
exponent = -0.3
length = 5
variant = 1
EC = True # Non-backtracking for learning
ymin = 0.0
ymax = 1
xmin = 2
xmax = 7.5
xtick_lab = [2, 3, 4, 5, 6, 7, 8]
xtick_labels = ['2', '3', '4', '5', '6', '7', '8']
ytick_lab = [1e-3, 1e-2, 1e-1, 1, 10, 50]
ytick_labels = [
r'$10^{-3}$', r'$10^{-2}$', r'$10^{-1}$', r'$1$', r'$10$', r'$50$'
]
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
k_vec = [3, 4, 5]
rep_DifferentGraphs = 1000 # iterations on different graphs
err = 0
avoidNeighbors = False
gradient = False
convergencePercentage_W = None
stratified = True
label_vec = ['*'] * 10
clip_on_vec = [True] * 15
draw_std_vec = range(10)
numberOfSplits = 1
linestyle_vec = ['solid'] * 15
linewidth_vec = [3, 2, 4, 2, 3, 2] + [3] * 15
marker_vec = ['^', 's', 'o', 'x', 'o', '+', 's'] * 3
markersize_vec = [8, 7, 8, 10, 7, 6] + [10] * 10
facecolor_vec = [
"#CCB974", "#55A868", "#4C72B0", "#8172B2", "#C44E52", "#64B5CD"
]
legend_location = 'upper right'
# -- Options with propagation variants
if CHOICE == 600: ## 1k nodes
n = 1000
h = 8
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4']
learning_method_vec = ['GT', 'MHE', 'DHE', 'Holdout']
weight_vec = [10] * 4
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True]
xmin = 3.
xmax = 10.
ymin = 0.
ymax = 50.
label_vec = ['GT', 'MCE', 'DCE', 'Holdout']
facecolor_vec = [
'black'
] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 4
f_vec = [0.03, 0.01, 0.001]
k_vec = [3, 4, 5, 6]
ytick_lab = [0, 1e-3, 1e-2, 1e-1, 1, 10, 50]
ytick_labels = [
r'$0$', r'$10^{-3}$', r'$10^{-2}$', r'$10^{-1}$', r'$1$', r'$10$',
r'$50$'
]
elif CHOICE == 601: ## 10k nodes
n = 10000
h = 8
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4']
learning_method_vec = ['GT', 'MHE', 'DHE', 'Holdout']
weight_vec = [10] * 4
alpha_vec = [0] * 20
beta_vec = [0] * 20
gamma_vec = [0] * 20
s_vec = [0.5] * 20
numMaxIt_vec = [10] * 20
randomize_vec = [False] * 15 + [True]
xmin = 3.
xmax = 8.
ymin = 0.
ymax = 500.
label_vec = ['GT', 'MCE', 'DCE', 'Holdout']
facecolor_vec = [
'black'
] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 4
f_vec = [0.03, 0.01, 0.001]
k_vec = [3, 4, 5]
ytick_lab = [0, 1e-3, 1e-2, 1e-1, 1, 10, 100, 300]
ytick_labels = [
r'$0$', r'$10^{-3}$', r'$10^{-2}$', r'$10^{-1}$', r'$1$', r'$10$',
r'$100$', r'$300$'
]
elif CHOICE == 602: ## 10k nodes
n = 10000
h = 8
d = 25
weight_vec = [10] * 20
alpha_vec = [0] * 20
beta_vec = [0] * 20
gamma_vec = [0] * 20
s_vec = [0.5] * 20
numMaxIt_vec = [10] * 20
randomize_vec = [False] * 3 + [True] + [False]
ymin = 0.01
ymax = 500
label_vec = ['Holdout', 'LCE', 'MCE', 'DCE', 'DHEr']
facecolor_vec = [
"#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"
] * 4
f_vec = [0.01]
k_vec = [3, 4, 5]
ytick_lab = [1e-3, 1e-2, 1e-1, 1, 10, 100, 500]
ytick_labels = [
r'$10^{-3}$', r'$10^{-2}$', r'$10^{-1}$', r'$1$', r'$10$',
r'$100$', r'$500$'
]
option_vec = ['opt5', 'opt6', 'opt2', 'opt3', 'opt4']
learning_method_vec = ['Holdout', 'LHE', 'MHE', 'DHE', 'DHE']
k_vec = [2, 3, 4, 5, 6, 7, 8]
# option_vec = ['opt2', 'opt3', 'opt6']
# learning_method_vec = ['MHE', 'DHE', 'LHE']
# k_vec = [2, 3, 4, 5]
elif CHOICE == 603: ## 10k nodes
n = 10000
h = 3
d = 25
weight_vec = [10] * 20
alpha_vec = [0] * 20
beta_vec = [0] * 20
gamma_vec = [0] * 20
s_vec = [0.5] * 20
numMaxIt_vec = [10] * 20
randomize_vec = [False] * 4 + [True]
xmin = 1.8
xmax = 8.2
ymin = 0.01
ymax = 500
label_vec = ['Holdout', 'LCE', 'MCE', 'DCE', 'DCEr']
facecolor_vec = [
"#CCB974", "#55A868", "#4C72B0", "#8172B2", "#C44E52"
] * 4
f_vec = [0.01]
k_vec = [3, 4, 5]
ytick_lab = [1e-3, 1e-2, 1e-1, 1, 10, 100, 500]
ytick_labels = [
r'$10^{-3}$', r'$10^{-2}$', r'$10^{-1}$', r'$1$', r'$10$',
r'$100$', r'$500$'
]
option_vec = ['opt5', 'opt6', 'opt2', 'opt3', 'opt4']
learning_method_vec = ['Holdout', 'LHE', 'MHE', 'DHE', 'DHE']
k_vec = [2, 3, 4, 5, 6, 7, 8]
legend_location = 'upper right'
# option_vec = ['opt2', 'opt3', 'opt6']
# learning_method_vec = ['MHE', 'DHE', 'LHE']
# k_vec = [2, 3, 4, 5]
# option_vec = ['opt4', 'opt3']
# learning_method_vec = ['MHE', 'MHE']
# randomize_vec = [True, False]
# k_vec = [2, 3, 4, 5]
elif CHOICE == 604: ## 10k nodes with Gradient
n = 10000
h = 3
d = 25
weight_vec = [10] * 20
alpha_vec = [0] * 20
beta_vec = [0] * 20
gamma_vec = [0] * 20
s_vec = [0.5] * 20
numMaxIt_vec = [10] * 20
randomize_vec = [False] * 4 + [True]
ymin = 0.00
ymax = 800
label_vec = ['Holdout', 'LCE', 'MCE', 'DCE', 'DCEr']
facecolor_vec = [
"#CCB974", "#55A868", "#4C72B0", "#8172B2", "#C44E52"
] * 4
f_vec = [0.01]
k_vec = [3, 4, 5]
ytick_lab = [1e-3, 1e-2, 1e-1, 1, 10, 100, 500]
ytick_labels = [
r'$10^{-3}$', r'$10^{-2}$', r'$10^{-1}$', r'$1$', r'$10$',
r'$100$', r'$500$'
]
option_vec = ['opt5', 'opt6', 'opt2', 'opt3', 'opt4']
learning_method_vec = ['Holdout', 'LHE', 'MHE', 'DHE', 'DHE']
k_vec = [2, 3, 4, 5, 6, 7, 8]
# k_vec = [7, 8]
gradient = True
legend_location = 'center right'
elif CHOICE == 605: ## 10k nodes with Gradient with f = 0.005
n = 10000
h = 3
d = 25
weight_vec = [10] * 20
alpha_vec = [0] * 20
beta_vec = [0] * 20
gamma_vec = [0] * 20
s_vec = [0.5] * 20
numMaxIt_vec = [10] * 20
randomize_vec = [False] * 4 + [True]
ymin = 0.00
ymax = 800
label_vec = ['Holdout', 'LCE', 'MCE', 'DCE', 'DCEr']
facecolor_vec = [
"#CCB974", "#55A868", "#4C72B0", "#8172B2", "#C44E52"
] * 4
f_vec = [0.005]
k_vec = [3, 4, 5]
ytick_lab = [1e-3, 1e-2, 1e-1, 1, 10, 100, 500]
ytick_labels = [
r'$10^{-3}$', r'$10^{-2}$', r'$10^{-1}$', r'$1$', r'$10$',
r'$100$', r'$500$'
]
option_vec = ['opt5', 'opt6', 'opt2', 'opt3', 'opt4']
learning_method_vec = ['Holdout', 'LHE', 'MHE', 'DHE', 'DHE']
k_vec = [2, 3, 4, 5, 6, 7]
# k_vec = [7, 8]
gradient = True
legend_location = 'center right'
elif CHOICE == 606: ## 10k nodes with Gradient with f = 0.005 and Gradient and PruneRandom
n = 10000
h = 3
d = 25
weight_vec = [10] * 20
alpha_vec = [0] * 20
beta_vec = [0] * 20
gamma_vec = [0] * 20
s_vec = [0.5] * 20
numMaxIt_vec = [10] * 20
randomize_vec = [False] * 4 + [True]
xmin = 1.8
xmax = 7.2
ymin = 0.01
ymax = 800
label_vec = ['Holdout', 'LCE', 'MCE', 'DCE', 'DCEr']
facecolor_vec = [
"#CCB974", "#55A868", "#4C72B0", "#8172B2", "#C44E52"
] * 4
f_vec = [0.005]
k_vec = [3, 4, 5]
ytick_lab = [1e-3, 1e-2, 1e-1, 1, 10, 100, 500]
ytick_labels = [
r'$10^{-3}$', r'$10^{-2}$', r'$10^{-1}$', r'$1$', r'$10$',
r'$100$', r'$500$'
]
option_vec = ['opt5', 'opt6', 'opt2', 'opt3', 'opt4']
learning_method_vec = ['Holdout', 'LHE', 'MHE', 'DHE', 'DHE']
k_vec = [2, 3, 4, 5, 6, 7]
gradient = True
pruneRandom = True
legend_location = 'upper right'
elif CHOICE == 607: ## 10k nodes with gradient and PruneRandom
n = 10000
h = 3
d = 25
option_vec = ['opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['LHE', 'MHE', 'DHE', 'DHE', 'Holdout']
weight_vec = [10] * 10
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 3 + [True] + [False]
xmin = 1.8
xmax = 7.
ymin = 0.01
ymax = 800
label_vec = ['LCE', 'MCE', 'DCE', 'DCEr', 'Holdout']
facecolor_vec = [
"#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"
] * 4
legend_location = 'upper left'
marker_vec = [None, 's', 'x', 'o', '^', '+'] * 3
markersize_vec = [8, 7, 10, 8, 7, 6] + [10] * 10
f_vec = [0.01]
k_vec = [2, 3, 4, 5, 6, 7, 8]
clip_on_vec = [True] * 10
gradient = True
pruneRandom = True
ytick_lab = [1e-3, 1e-2, 1e-1, 1, 10, 100, 500]
ytick_labels = [
r'$10^{-3}$', r'$10^{-2}$', r'$10^{-1}$', r'$1$', r'$10$',
r'$100$', r'$500$'
]
elif CHOICE == 608: ## 10k nodes with gradient and PruneRandom
n = 10000
h = 3
d = 25
option_vec = ['opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['LHE', 'MHE', 'DHE', 'DHE', 'Holdout']
weight_vec = [10] * 10
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 3 + [True] + [False]
xmin = 1.8
xmax = 7.2
ymin = 0.01
ymax = 800
label_vec = ['LCE', 'MCE', 'DCE', 'DCEr', 'Holdout']
facecolor_vec = [
"#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"
] * 4
legend_location = 'upper left'
marker_vec = [None, 's', 'x', 'o', '^', '+'] * 3
markersize_vec = [8, 7, 10, 8, 7, 6] + [10] * 10
f_vec = [0.01]
k_vec = [2, 3, 4, 5, 6, 7, 8]
clip_on_vec = [True] * 10
gradient = True
pruneRandom = True
ytick_lab = [1e-3, 1e-2, 1e-1, 1, 10, 100, 500]
ytick_labels = [
r'$10^{-3}$', r'$10^{-2}$', r'$10^{-1}$', r'$1$', r'$10$',
r'$100$', r'$500$'
]
rep_DifferentGraphs = 10
else:
raise Warning("Incorrect choice!")
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(
seed=RANDOMSEED
) # seeds the actually used numpy random generator; both are used and thus needed
# print("CHOICE: {}".format(CHOICE))
# -- Create data
if CREATE_DATA or ADD_DATA:
for i in range(rep_DifferentGraphs
): # create several graphs with same parameters
# print("\ni: {}".format(i))
for k in k_vec:
# print("\nk: {}".format(k))
H0 = create_parameterized_H(k, h, symmetric=True)
H0c = to_centering_beliefs(H0)
a = [1.] * k
alpha0 = np.array(a)
alpha0 = alpha0 / np.sum(alpha0)
W, Xd = planted_distribution_model_H(n,
alpha=alpha0,
H=H0,
d_out=d,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
for j in range(
rep_SameGraph): # repeat several times for same graph
# print("j: {}".format(j))
ind = None
for f in f_vec: # Remove fraction (1-f) of rows from X0 (notice that different from first implementation)
X1, ind = replace_fraction_of_rows(
X0,
1 - f,
avoidNeighbors=avoidNeighbors,
W=W,
ind_prior=ind,
stratified=stratified)
X2 = introduce_errors(X1, ind, err)
for option_index, (learning_method, alpha, beta, gamma, s, numMaxIt, weights, randomize) in \
enumerate(zip(learning_method_vec, alpha_vec, beta_vec, gamma_vec, s_vec, numMaxIt_vec, weight_vec, randomize_vec)):
# -- Learning
if learning_method == 'GT':
timeTaken = 0.0
elif learning_method == 'Holdout':
prev_time = time.time()
H2 = estimateH_baseline_serial(
X2,
ind,
W,
numMax=numMaxIt,
numberOfSplits=numberOfSplits,
EC=EC,
alpha=alpha,
beta=beta,
gamma=gamma)
timeTaken = time.time() - prev_time
else:
prev_time = time.time()
if gradient and pruneRandom:
H2 = estimateH(X2,
W,
method=learning_method,
variant=1,
distance=length,
EC=EC,
weights=weights,
randomize=randomize,
gradient=gradient)
else:
H2 = estimateH(X2,
W,
method=learning_method,
variant=1,
distance=length,
EC=EC,
weights=weights,
randomize=randomize)
timeTaken = time.time() - prev_time
tuple = [str(datetime.datetime.now())]
text = [option_vec[option_index], k, f, timeTaken]
tuple.extend(text)
# print("option: {}, f: {}, timeTaken: {}".format(option_vec[option_index], f, timeTaken))
save_csv_record(join(data_directory, csv_filename),
tuple)
# -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1: (length {}):\n{}".format(len(df1.index), df1.head(15)))
# -- Aggregate repetitions
df2 = df1.groupby(['option', 'k', 'f']).agg \
({'time': [np.mean, np.std, np.size, np.median], # Multiple Aggregates
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values
] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'time_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(15)))
# -- Pivot table
df3 = pd.pivot_table(df2,
index=['f', 'k'],
columns=['option'],
values=['time_mean', 'time_std',
'time_median']) # Pivot
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
df3.columns = ['_'.join(col).strip() for col in df3.columns.values
] # flatten the column hierarchy
df3.reset_index(inplace=True) # remove the index hierarchy
# df2.rename(columns={'time_size': 'count'}, inplace=True)
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(100)))
# X_f = k_vec
X_f = df3['k'].values # read k from values instead
Y_hash = defaultdict(dict)
Y_hash_std = defaultdict(dict)
for f in f_vec:
for option in option_vec:
Y_hash[f][option] = list()
Y_hash_std[f][option] = list()
for f in f_vec:
for option in option_vec:
Y_hash[f][option] = df3.loc[df3['f'] == f]['time_mean_{}'.format(
option)].values # mean
# Y_hash[f][option] = df3.loc[df3['f'] == f]['time_median_{}'.format(option)].values # median
Y_hash_std[f][option] = df3.loc[df3['f'] == f][
'time_std_{}'.format(option)].values
if SHOW_PLOT or SHOW_PDF or CREATE_PDF:
# -- Setup figure
fig_filename = 'Fig_Time_varyK_{}.pdf'.format(CHOICE)
mpl.rc(
'font', **{
'family': 'sans-serif',
'sans-serif': [u'Arial', u'Liberation Sans']
})
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 14
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams[
'xtick.major.pad'] = 2 # padding of tick labels: default = 4
mpl.rcParams[
'ytick.major.pad'] = 1 # padding of tick labels: default = 4
mpl.rcParams['xtick.direction'] = 'out' # default: 'in'
mpl.rcParams['ytick.direction'] = 'out' # default: 'in'
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['figure.figsize'] = [4, 4]
fig = figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
opt_f_vecs = [(option, f) for option in option_vec for f in f_vec]
for ((option, f), color, linewidth, clip_on, linestyle, marker, markersize) in \
zip(opt_f_vecs, facecolor_vec, linewidth_vec, clip_on_vec, linestyle_vec, marker_vec, markersize_vec):
label = label_vec[option_vec.index(option)]
# label = label + " " + str(f)
if STD_FILL:
ax.fill_between(X_f,
Y_hash[f][option] + Y_hash_std[f][option],
Y_hash[f][option] - Y_hash_std[f][option],
facecolor=color,
alpha=0.2,
edgecolor=None,
linewidth=0)
ax.plot(X_f,
Y_hash[f][option] + Y_hash_std[f][option],
linewidth=0.5,
color='0.8',
linestyle='solid')
ax.plot(X_f,
Y_hash[f][option] - Y_hash_std[f][option],
linewidth=0.5,
color='0.8',
linestyle='solid')
ax.plot(X_f,
Y_hash[f][option],
linewidth=linewidth,
color=color,
linestyle=linestyle,
label=label,
zorder=4,
marker=marker,
markersize=markersize,
markeredgecolor='black',
markeredgewidth=1,
clip_on=clip_on)
if SHOW_ARROWS:
for indx in [2, 3]:
ax.annotate(s='',
xy=(X_f[indx] - 0.05, Y_hash[f]['opt4'][indx]),
xytext=(X_f[indx] - 0.05, Y_hash[f]['opt5'][indx]),
arrowprops=dict(facecolor='blue',
arrowstyle='<->'))
ax.annotate(
str(
int(
np.round(Y_hash[f]['opt5'][indx] /
Y_hash[f]['opt4'][indx]))) + 'x',
xy=(X_f[indx] - 0.4,
(Y_hash[f]['opt5'][indx] + Y_hash[f]['opt4'][indx]) /
10),
color='black',
va='center',
annotation_clip=False,
zorder=5)
# -- Title and legend
if distribution == 'uniform':
distribution_label = ',$uniform'
else:
distribution_label = '$'
if n < 1000:
n_label = '{}'.format(n)
else:
n_label = '{}k'.format(int(n / 1000))
title(r'$\!\!\!n\!=\!{}, d\!=\!{}, h\!=\!{}, f\!=\!{}{}'.format(
n_label, d, h, f, distribution_label))
handles, label_vec = ax.get_legend_handles_labels()
legend = plt.legend(
handles,
label_vec,
loc=legend_location, # 'upper right'
handlelength=2,
labelspacing=0, # distance between label entries
handletextpad=
0.3, # distance between label and the line representation
borderaxespad=0.2, # distance between legend and the outer axes
borderpad=0.3, # padding inside legend box
numpoints=1, # put the marker only once
)
# # legend.set_zorder(1)
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.9) # 0.8
# -- Figure settings and save
plt.yscale('log')
plt.xticks(xtick_lab, xtick_labels)
plt.yticks(ytick_lab, ytick_lab)
# Only show ticks on the left and bottom spines
ax.yaxis.set_ticks_position('left')
ax.xaxis.set_ticks_position('bottom')
plt.xlim(xmin, xmax)
plt.ylim(ymin, ymax)
grid(b=True,
which='major',
axis='both',
alpha=0.2,
linestyle='solid',
linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
grid(b=True,
which='minor',
axis='both',
alpha=0.2,
linestyle='solid',
linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
xlabel(r'Number of Classes $(k)$', labelpad=0) # labelpad=0
ylabel(r'Time [sec]', labelpad=0)
if CREATE_PDF:
savefig(join(figure_directory, fig_filename),
format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
frameon=None)
if SHOW_PLOT:
plt.show()
if SHOW_PDF:
showfig(join(figure_directory,
fig_filename)) # shows actually created PDF
def run(option, create_data=False, add_data=False, show_plot=False, create_pdf=False, show_pdf=False, show_fig=True):
# -- Setup
OPTION = option
CREATE_DATA = create_data
ADD_DATA = add_data
SHOW_PLOT=show_plot
CREATE_PDF=create_pdf
SHOW_PDF=show_pdf
SHOW_FIG2 = show_fig # curve
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(seed=RANDOMSEED) # seeds the actually used numpy random generator; both are used and thus needed
header = ['currenttime',
'option', # one option corresponds to one choice of weight vector. In practice, one choice of scaling factor (for weight vector)
'variant', # 1, 2, 3 (against GT), and 1-2, 1-3, 2-3 (against each other)
'length',
'diff',
'time'] # L2 norm between H and estimate
# Default Graph parameters and options
n = 10000
d = 25
h = 8
distribution = 'powerlaw'
randomize = False
initial_h0 = None # initial vector to start finding optimal H
initial_H0 = None
exponent = -0.3
length = 5
rep_differentGraphs = 1
rep = 10 #
EC = [False] + [True] * 35
# scaling_vec = [1, 0.1, 0.14, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1, 1.4, 2, 3, 4, 5, 6, 7, 8, 9, 10, 14, 20, 30, 40, 50, 60, 70, 80, 90, 100]
scaling_vec = [1] + [round(0.1 * pow(10, 1/8)**x, 4) for x in range(33)]
num_options = len(scaling_vec)
scaling_vec = np.array(scaling_vec)
# weight = np.array([np.power(scaling_vec, i) for i in range(5)])
# weight = weight.transpose()
# ymin1 = None
# ymax1 = None
xmin2 = 0.1
xmax2 = 1000
ymax2 = 1.
ymin2 = 0
stratified = False
xtick_lab = [0.1, 1, 10, 100, 1000]
# ytick_lab = [0.05, 0.1, 0.5, 1]
# fig1_index = [0, 11, 16, 21, 23, 24, 25, 26] # which index of scaling options to display if CHOICE_FIG_BAR_VARIANT==True
smartInit = False
smartInitRandomize = False
delta = 0.1
variant = 1 # for figure 2, to speed up calculations
logarithm = False
if OPTION == 1:
CHOICE_vec = [18, 50, 51, 52, 53, 54]
initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 4
randomize_vec = [False]*2 + [True]*4
delta_vec = [None]*2 + [0.1, 0.2, 0.3] + [0.1]
constraints_vec = [False]*5 + [True]
# elif OPTION == 0:
# CHOICE_vec = [54]
# initial_H0_vec = [None]
# randomize_vec = [True]
# delta_vec = [0.1]
# constraints_vec = [True]
#
# elif OPTION == 2:
# f = 0.003
# CHOICE_vec = [101, 102, 103, 104, 105]
# initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 3
# randomize_vec = [False]*2 + [True]*3
# delta_vec = [None]*2 + [0.1, 0.3] + [0.1]
# constraints_vec = [False]*4 + [True]
#
# elif OPTION == 3:
# f = 0.003
# h = 3
# CHOICE_vec = [111, 112, 113, 114, 115]
# initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 3
# randomize_vec = [False]*2 + [True]*3
# delta_vec = [None]*2 + [0.1, 0.3] + [0.1]
# constraints_vec = [False]*4 + [True]
# elif OPTION == 4:
# f = 0.001
# h = 8
# CHOICE_vec = [121, 122, 123, 124]
# initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 2
# randomize_vec = [False]*2 + [True]*2
# delta_vec = [None]*2 + [0.1, 0.3]
# constraints_vec = [False]*4
elif OPTION == 5:
f = 0.001
h = 8
ymax2 = 2
ymin2 = 4e-2
CHOICE_vec = [131, 132, 133]
initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 1
randomize_vec = [False]*2 + [True]*1
delta_vec = [None]*2 + [0.1]
constraints_vec = [False]*3
stratified = True
# CHOICE_vec = [131, 132, 133, 134]
# initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 2
# randomize_vec = [False]*2 + [True]*2
# delta_vec = [None]*2 + [0.1, 0.3]
# constraints_vec = [False]*4
# stratified = True
# elif OPTION == 6:
# f = 0.003
# h = 8
# CHOICE_vec = [141, 142, 143]
# initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 1
# randomize_vec = [False]*2 + [True]*1
# delta_vec = [None]*2 + [0.1]
# constraints_vec = [False]*3
# # CHOICE_vec = [141, 142, 143, 144]
# # initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 2
# # randomize_vec = [False]*2 + [True]*2
# # delta_vec = [None]*2 + [0.1, 0.3]
# # constraints_vec = [False]*4
elif OPTION == 7:
f = 0.003
h = 8
CHOICE_vec = [151, 152, 153]
initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 1
randomize_vec = [False]*2 + [True]*1
delta_vec = [None]*2 + [0.1]
constraints_vec = [False]*3
stratified = True
# CHOICE_vec = [151, 152, 153, 154]
# initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 2
# randomize_vec = [False]*2 + [True]*2
# delta_vec = [None]*2 + [0.1, 0.3]
# constraints_vec = [False]*4
# stratified = True
# elif OPTION == 8:
# f = 0.001
# h = 3
# CHOICE_vec = [161, 162, 163]
# initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 1
# randomize_vec = [False]*2 + [True]*1
# delta_vec = [None]*2 + [0.1]
# constraints_vec = [False]*3
# # CHOICE_vec = [161, 162, 163, 164]
# # initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 2
# # randomize_vec = [False]*2 + [True]*2
# # delta_vec = [None]*2 + [0.1, 0.3]
# # constraints_vec = [False]*4
elif OPTION == 9:
f = 0.001
h = 3
CHOICE_vec = [171, 172, 173]
initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 1
randomize_vec = [False]*2 + [True]*1
delta_vec = [None]*2 + [0.1]
constraints_vec = [False]*3
stratified = True
ymin2 = 6e-2
ymax2 = 1
# CHOICE_vec = [171, 172, 173, 174]
# initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 2
# randomize_vec = [False]*2 + [True]*2
# delta_vec = [None]*2 + [0.1, 0.3]
# constraints_vec = [False]*4
elif OPTION == 10:
f = 0.001
h = 3
d = 10
CHOICE_vec = [181, 182, 183]
initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 1
randomize_vec = [False] * 2 + [True] * 1
delta_vec = [None] * 2 + [0.1]
constraints_vec = [False] * 3
stratified = True
elif OPTION == 11:
f = 0.05
h = 8
d = 25
ymax2 = 0.08
CHOICE_vec = [191, 192, 193]
initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 1
randomize_vec = [False] * 2 + [True] * 1
delta_vec = [None] * 2 + [0.1]
constraints_vec = [False] * 3
stratified = True
elif OPTION == 12:
f = 0.05
h = 3
d = 25
ymax2 = 0.08
CHOICE_vec = [201, 202, 203]
initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 1
randomize_vec = [False] * 2 + [True] * 1
delta_vec = [None] * 2 + [0.1]
constraints_vec = [False] * 3
stratified = True
elif OPTION == 13:
n=1000
f = 0.01
h = 3
CHOICE_vec = [211, 212, 213]
initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 1
randomize_vec = [False]*2 + [True]*1
delta_vec = [None]*2 + [0.1]
constraints_vec = [False]*3
stratified = True
ymin2 = 6e-2
ymax2 = 1
elif OPTION == 15:
n=100000
f = 0.01
h = 3
CHOICE_vec = [221, 222, 223]
initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 1
randomize_vec = [False]*2 + [True]*1
delta_vec = [None]*2 + [0.1]
constraints_vec = [False]*3
stratified = True
ymin2 = 5e-3
ymax2 = 2e-1
elif OPTION == 16: # variant on 13 with logarithm
n=1000
f = 0.01
h = 3
CHOICE_vec = [231, 232, 233]
initial_H0_vec = [None] + [create_parameterized_H(3, h)] + [None] * 1
randomize_vec = [False]*2 + [True]*1
delta_vec = [None]*2 + [0.1]
constraints_vec = [False]*3
stratified = True
ymin2 = 6e-2
ymax2 = 1
logarithm = True
elif OPTION == 17:
f = 0.001
h = 8
ymax2 = 2
ymin2 = 4e-2
CHOICE_vec = [133]
initial_H0_vec = [None] * 1
randomize_vec = [True]*1
delta_vec = [0.1]
constraints_vec = [False]*3
stratified = True
else:
raise Warning("Incorrect choice!")
k = 3
a = 1
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
if CREATE_DATA:
for CHOICE in CHOICE_vec:
csv_filename = 'Fig_MHE_Variants_{}.csv'.format(CHOICE)
save_csv_record(join(data_directory, csv_filename), header, append=False)
# print("OPTION: {}".format(OPTION))
# -- Create data
if CREATE_DATA or ADD_DATA:
for rs in range(1, rep_differentGraphs+1):
# print('Graph {}'.format(rs))
# -- Create graph
W, Xd = planted_distribution_model_H(n, alpha=alpha0, H=H0, d_out=d,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
for r in range(1, rep + 1):
# print('Repetition {}'.format(r))
X1, ind = replace_fraction_of_rows(X0, 1 - f, stratified=stratified)
for CHOICE, initial_H0, randomize, delta, constraints in zip(CHOICE_vec, initial_H0_vec, randomize_vec, delta_vec, constraints_vec):
csv_filename = 'Fig_MHE_Variants_{}.csv'.format(CHOICE)
# -- Create estimates and compare against GT, or against each other
for length in range(1, length + 1):
for option in range(num_options):
start = time.time()
if smartInit:
startWeight = 0.2
initial_H0 = estimateH(X1, W, method='DHE', variant=variant,
distance=5,
EC=EC[option], weights=startWeight,
randomize=smartInitRandomize,
logarithm=logarithm)
# print(option)
# print(scaling_vec)
# print(scaling_vec[option])
H_est = estimateH(X1, W, method='DHE', variant=variant,
distance=length, EC=EC[option], weights=scaling_vec[option],
randomize=randomize,
initial_H0=initial_H0,
constraints = constraints,
delta = delta
)
time_est = time.time() - start
diff = LA.norm(H_est - H0)
# if np.amin(H_est) < 0:
# if True:
# print("\nCHOICE: {}, weight: {}".format(CHOICE, scaling_vec[option]))
# print("length:{}".format(length))
# print("H_est:\n{}".format(H_est))
# print("diff: {}".format(diff))
tuple = [str(datetime.datetime.now())]
text = [option, variant, length, diff, time_est]
# text = np.asarray(text) # (without np, entries get ugly format) not used here because it transforms integers to float !!
tuple.extend(text)
save_csv_record(join(data_directory, csv_filename), tuple)
if SHOW_FIG2:
for CHOICE, initial_h0, randomize, delta in zip(CHOICE_vec, initial_H0_vec, randomize_vec, delta_vec):
csv_filename = 'Fig_MHE_Variants_{}.csv'.format(CHOICE)
# -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1 (length {}):\n{}".format(len(df1.index), df1.head(15)))
df2 = df1.groupby(['option', 'variant', 'length']).agg \
({'diff': [np.mean, np.std, np.size], # Multiple Aggregates
'time': [np.mean, np.std],
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'diff_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(30)))
df2['length'] = df2['length'].astype(str) # transform numbers into string for later join: '.join(col).strip()'
df3 = df2.query('variant=="1"') # We only focus on variant 1 (as close to row stochastic matrix as possible)
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(n=20)))
df4 = pd.pivot_table(df3, index=['option'], columns=['length'], values=['diff_mean', 'diff_std']) # Pivot
# print("\n-- df4 (length {}):\n{}".format(len(df4.index), df4.head(30)))
df4.columns = ['_'.join(col).strip() for col in df4.columns.values] # flatten the column hierarchy, requires to have only strings
df4.reset_index(level=0, inplace=True) # get length into columns
# print("\n-- df4 (length {}):\n{}".format(len(df4.index), df4.head(30)))
# Add scaling factor for each row
option = df4['option'].values # extract the values from dataframe
scaling = scaling_vec[option] # look up the scaling factor in original list
scaling = pd.Series(scaling)
# print("scaling:\n{}".format(scaling))
df5 = df4.assign(scaling=scaling.values)
# print("\n-- df5 (length {}):\n{}".format(len(df5.index), df5.head(30)))
# Filter rows
select_rows = [i for i in range(num_options) if EC[i]] # only those values for EC being tru
df6 = df5[df5['option'].isin(select_rows)]
# print("\n-- df6 (length {}):\n{}".format(len(df6.index), df6.head(30)))
fig_filename = 'Fig_MHE_ScalingFactor_{}.pdf'.format(CHOICE)
# -- Setup figure
mpl.rcParams['backend'] = 'pdf'
mpl.rcParams['lines.linewidth'] = 3
mpl.rcParams['font.size'] = 14
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 14
mpl.rcParams['axes.edgecolor'] = '111111' # axes edge color
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['figure.figsize'] = [4, 4]
mpl.rcParams['xtick.major.pad'] = 4 # padding of tick labels: default = 4
mpl.rcParams['ytick.major.pad'] = 4 # padding of tick labels: default = 4
fig = plt.figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
# -- Extract values into columns (plotting dataframew with bars plus error lines and lines gave troubles)
scaling = df6['scaling'].values # .tolist() does not work with bar plot, requires np.array
diff_mean_1 = df6['diff_mean_1'].values
diff_mean_2 = df6['diff_mean_2'].values
diff_mean_3 = df6['diff_mean_3'].values
diff_mean_4 = df6['diff_mean_4'].values
diff_mean_5 = df6['diff_mean_5'].values
diff_std_5 = df6['diff_std_5'].values
# -- Draw the plots
p1 = ax.plot(scaling, diff_mean_1, color='black', linewidth=1, linestyle='--', label=r'$\ell_\mathrm{max} = 1$')
p2 = ax.plot(scaling, diff_mean_2, color='orange', label=r'$\ell_\mathrm{max} = 2$')
p3 = ax.plot(scaling, diff_mean_3, color='blue', label=r'$\ell_\mathrm{max} = 3$')
p4 = ax.plot(scaling, diff_mean_4, color='green', label=r'$\ell_\mathrm{max} = 4$')
p5 = ax.plot(scaling, diff_mean_5, color='red', marker='o', label=r'$\ell_\mathrm{max} = 5$')
plt.xscale('log')
plt.yscale('log')
upper = diff_mean_5 + diff_std_5
lower = diff_mean_5 - diff_std_5
ax.fill_between(scaling, upper, lower, facecolor='red', alpha=0.2, edgecolor='none')
# -- Title and legend
if distribution == 'uniform':
distribution_label = ',$uniform'
else:
distribution_label = '$'
plt.title(r'$\!\!\!\!n\!=\!{}\mathrm{{k}}, d\!=\!{}, h\!=\!{}, f\!=\!{}{}'.format(int(n / 1000), d, h, f, distribution_label))
handles, labels = ax.get_legend_handles_labels()
# print("labels: {}".format(labels))
legend = plt.legend(handles, labels,
loc='upper center', # 'upper right'
handlelength=2,
labelspacing=0, # distance between label entries
handletextpad=0.3, # distance between label and the line representation
# title='Variants',
borderaxespad=0.3, # distance between legend and the outer axes
borderpad=0.1, # padding inside legend box
)
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.9) # 0.8
# -- Figure settings
# ax.set_xticks(range(10))
plt.grid(b=True, which='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
plt.xlabel(r'Scaling factor $(\lambda)$', labelpad=0)
plt.ylabel(r'L2 norm', labelpad=0)
if xmin2 is None:
xmin2 = plt.xlim()[0]
if xmax2 is None:
xmax2 = plt.xlim()[1]
if ymin2 is None:
ymin2 = plt.ylim()[0]
ymin2 = max(ymin2, 0)
if ymax2 is None:
ymax2 = plt.ylim()[1]
plt.xlim(xmin2, xmax2)
plt.ylim(ymin2, ymax2)
plt.tick_params(
axis='x', # changes apply to the x-axis
which='both', # both major and minor ticks are affected
# bottom='off', # ticks along the bottom edge are off
top='off', # ticks along the top edge are off
right='off', # ticks along the top edge are off
# labelbottom='off', # labels along the bottom edge are off
)
plt.xticks(xtick_lab)
# plt.yticks(ytick_lab, ytick_lab)
if SHOW_PLOT:
plt.show()
if CREATE_PDF:
plt.savefig(join(figure_directory, fig_filename), format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
frameon=None)
if SHOW_PDF:
showfig(join(figure_directory, fig_filename))
def run(choice,
create_data=False,
add_data=False,
show_plot=False,
create_pdf=False,
show_pdf=False):
# -- Setup
CHOICE = choice
#300 Prop37, 400 MovieLens, 500 Yelp, 600 Flickr, 700 DBLP, 800 Enron
experiments = [CHOICE]
CREATE_DATA = create_data
ADD_DATA = add_data
SHOW_PDF = show_pdf
SHOW_PLOT = show_plot
CREATE_PDF = create_pdf
SHOW_FIG = SHOW_PLOT or SHOW_PDF or CREATE_PDF
STD_FILL = True
TIMING = False
CALCULATE_DATA_STATISTICS = False
# -- Default Graph parameters
rep_SameGraph = 10 # iterations on same graph
initial_h0 = None # initial vector to start finding optimal H
exponent = -0.3
length = 5
variant = 1
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
clip_on_vec = [True] * 10
numMaxIt_vec = [10] * 10
# Plotting Parameters
xtick_lab = [0.001, 0.01, 0.1, 1]
xtick_labels = ['0.1\%', '1\%', '10\%', '100\%']
ytick_lab = np.arange(0, 1.1, 0.1)
xmax = 1
xmin = 0.0001
ymin = 0.3
ymax = 0.7
labels = ['GS', 'LCE', 'MCE', 'DCE', 'DCEr']
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974",
"#64B5CD"
]
draw_std_vec = [False] * 4 + [True]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [4, 4, 2, 1, 2, 2]
marker_vec = [None, 'o', 'x', '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8]
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
Macro_Accuracy = False
EC = True # Non-backtracking for learning
constraints = True # True
weight_vec = [None] * 3 + [10, 10] * 2
randomize_vec = [False] * 4 + [True] * 2
k = 3
err = 0
avoidNeighbors = False
convergencePercentage_W = None
stratified = True
gradient = True
doubly_stochastic = True
num_restarts = None
raw_std_vec = range(10)
numberOfSplits = 1
select_lambda_vec = [False] * 20
lambda_vec = None
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
FILENAMEZ = ""
legend_location = ""
fig_label = ""
H_heuristic = ""
def choose(choice):
# -- Default Graph parameters
nonlocal n
nonlocal d
nonlocal rep_SameGraph
nonlocal FILENAMEZ
nonlocal initial_h0
nonlocal exponent
nonlocal length
nonlocal variant
nonlocal alpha_vec
nonlocal beta_vec
nonlocal gamma_vec
nonlocal s_vec
nonlocal clip_on_vec
nonlocal numMaxIt_vec
# Plotting Parameters
nonlocal xtick_lab
nonlocal xtick_labels
nonlocal ytick_lab
nonlocal xmax
nonlocal xmin
nonlocal ymin
nonlocal ymax
nonlocal labels
nonlocal facecolor_vec
nonlocal draw_std_vec
nonlocal linestyle_vec
nonlocal linewidth_vec
nonlocal marker_vec
nonlocal markersize_vec
nonlocal legend_location
nonlocal option_vec
nonlocal learning_method_vec
nonlocal Macro_Accuracy
nonlocal EC
nonlocal constraints
nonlocal weight_vec
nonlocal randomize_vec
nonlocal k
nonlocal err
nonlocal avoidNeighbors
nonlocal convergencePercentage_W
nonlocal stratified
nonlocal gradient
nonlocal doubly_stochastic
nonlocal num_restarts
nonlocal numberOfSplits
nonlocal H_heuristic
nonlocal select_lambda_vec
nonlocal lambda_vec
nonlocal f_vec
if choice == 0:
None
elif choice == 304: ## with varying weights
FILENAMEZ = 'prop37'
Macro_Accuracy = True
gradient = True
fig_label = 'Prop37'
legend_location = 'lower right'
n = 62000
d = 34.8
select_lambda_vec = [False] * 5
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
elif choice == 305: # DCEr Only experiment
choose(605)
choose(304)
select_lambda_vec = [False] * 6
elif choice == 306:
choose(304)
select_lambda_vec = [False] * 3 + [True] * 3
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
learning_method_vec.append('Holdout')
labels.append('Holdout')
elif choice == 307: # heuristic comparison
choose(304)
select_lambda_vec = [False] * 3 + [True] * 3
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
learning_method_vec.append('Heuristic')
labels.append('Heuristic')
H_heuristic = np.array([[.476, .0476, .476], [.476, .0476, .476],
[.476, .476, .0476]])
# -- MovieLens dataset
elif choice == 401:
FILENAMEZ = 'movielens'
Macro_Accuracy = True
gradient = True
fig_label = 'MovieLens'
legend_location = 'upper left'
n = 26850
d = 25.0832029795
elif choice == 402:
choose(401)
select_lambda_vec = [False] * 3 + [
True
] * 3 # allow to choose lambda for different f in f_vec
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
elif choice == 403:
choose(402)
ymin = 0.3
ymax = 1.0
learning_method_vec.append('Holdout')
labels.append('Holdout')
elif choice == 404:
choose(401)
select_lambda_vec = [
True
] * 3 # allow to choose lambda for different f in f_vec
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
labels = ['GS', 'DCEr', 'Homophily']
facecolor_vec = ['black', "#C44E52", "#64B5CD"]
draw_std_vec = [False, True, False]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [4, 2, 2, 2, 2]
marker_vec = [None, '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8]
weight_vec = [None, 10, None]
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
randomize_vec = [False, True, False]
learning_method_vec = ['GT', 'DHE'] #TODO
elif choice == 405: # DCEr ONLY experiment
choose(605)
choose(401)
learning_method_vec += ['Holdout']
labels += ['Holdout']
elif choice == 406: # comparison with a static heuristic matrix
choose(402)
learning_method_vec += ['Heuristic']
labels += ['Heuristic']
H_heuristic = np.array([[.0476, .476, .476], [.476, .0476, .476],
[.476, .476, .0476]])
elif choice == 407:
choose(402)
ymin = 0.3
ymax = 1.0
lambda_vec = [1] * 21 # same length as f_vec
elif choice == 408:
choose(402)
ymin = 0.3
ymax = 1.0
lambda_vec = [10] * 21 # same length as f_vec
# DO NOT RUN WITH CREATE_DATA=True, if you do please restore the data from
# data/sigmod-movielens-fig.csv
elif choice == 409:
choose(402)
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#8172B2", "#C44E52",
"#C44E52", "#CCB974", "#64B5CD"
]
labels = [
'GS', 'LCE', 'MCE', 'DCE1', 'DCE10', 'DCEr1', 'DCEr10',
'Holdout'
]
draw_std_vec = [False] * 5 + [True] * 2 + [False]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [2, 2, 2, 2, 2, 2, 2, 2]
marker_vec = [None, 'o', 'x', 's', 'p', '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8, 8]
option_vec = [
'opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6', 'opt7', 'opt8'
]
legend_location = 'upper left'
ymin = 0.3
ymax = 1.0
lambda_vec = [10] * 21 # same length as f_vec
# -- Yelp dataset
elif choice == 501:
FILENAMEZ = 'yelp'
Macro_Accuracy = True
weight_vec = [None] * 3 + [10, 10]
gradient = True
ymin = 0.1
ymax = 0.75
fig_label = 'Yelp'
legend_location = 'upper left'
n = 4301900 # for figure
d = 6.56 # for figure
# -- Flickr dataset
elif choice == 601:
FILENAMEZ = 'flickr'
Macro_Accuracy = True
fig_label = 'Flickr'
legend_location = 'lower right'
ymin = 0.3
ymax = 0.7
n = 2007369
d = 18.1
elif choice == 602: ## with varying weights
choose(601)
select_lambda_vec = [False] * 4 + [
True
] * 2 # allow to choose lambda for different f in f_vec
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
elif choice == 603: ## with varying weights
choose(602)
select_lambda_vec = [False] * 3 + [
True
] * 2 # allow to choose lambda for different f in f_vec
# lambda_vec = [1] * 5 + [5] * 5 + [10] * 5 + [1] * 6 # same length as f_vec
elif choice == 604: ## with weight = 1
choose(603)
lambda_vec = [0.5] * 21 # same length as f_vec
elif choice == 605:
choose(601)
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974",
"#64B5CD", 'orange'
]
draw_std_vec = [False] + [True] * 10
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [3] * 10
marker_vec = [None, 'o', 'x', '^', 'v', '+', 'o', 'x']
markersize_vec = [0] + [8] * 10
randomize_vec = [True] * 8
option_vec = [
'opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6', 'opt7', 'opt8'
]
learning_method_vec = [
'GT', 'DHE', 'DHE', 'DHE', 'DHE', 'DHE', 'DHE'
]
select_lambda_vec = [False] * 8
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
weight_vec = [0, 0, 1, 2, 5, 10, 15]
labels = ['GT'] + [
i + ' {}'.format(weight_vec[ix])
for ix, i in enumerate(['DCEr'] * 6)
]
elif choice == 606: # heuristic experiment
choose(602)
labels.append('Heuristic')
learning_method_vec.append('Heuristic')
H_heuristic = np.array([[.0476, .476, .476], [.476, .0476, .476],
[.476, .476, .0476]])
# -- DBLP dataset
elif choice == 701:
FILENAMEZ = 'dblp'
Macro_Accuracy = True
ymin = 0.2
ymax = 0.5
fig_label = 'DBLP'
legend_location = 'lower right'
n = 2241258 # for figure
d = 26.11 # for figure
# -- ENRON dataset
elif choice == 801:
FILENAMEZ = 'enron'
Macro_Accuracy = True
ymin = 0.3
ymax = 0.75
fig_label = 'Enron'
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
legend_location = 'upper left'
n = 46463 # for figures
d = 23.4 # for figures
elif choice == 802: ### WITH ADAPTIVE WEIGHTS
choose(801)
select_lambda_vec = [False] * 4 + [
True
] * 2 # allow to choose lambda for different f in f_vec
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
elif choice == 803: ### WITH ADAPTIVE WEIGHTS
choose(802)
lambda_vec = [1] * 5 + [5] * 5 + [10] * 5 + [
1
] * 6 # same length as f_vec
elif choice == 804:
choose(803)
elif choice == 805:
choose(605)
choose(801)
#learning_method_vec += ['Holdout']
#labels += ['Holdout']
elif choice == 806: # Heuristic experiment
choose(802)
learning_method_vec += ['Heuristic']
labels += ['Heuristic']
H_heuristic = np.array([[0.76, 0.08, 0.08, 0.08],
[0.08, 0.08, 0.76, 0.08],
[0.08, 0.76, 0.08, 0.76],
[0.08, 0.08, 0.76, 0.08]])
# MASC Dataset
elif choice == 901:
FILENAMEZ = 'masc'
Macro_Accuracy = False
fig_label = 'MASC'
legend_location = 'lower right'
n = 0
d = 0
ymin = 0
num_restarts = 100
select_lambda_vec = [False] * 4 + [
True
] # allow to choose lambda for different f in f_vec
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
# MASC collapsed Dataset
elif choice == 1001:
FILENAMEZ = 'masc-collapsed'
fig_label = 'MASC Collapsed'
legend_location = 'lower right'
n = 43724
d = 7.2
ymin = 0
num_restarts = 20
select_lambda_vec = [False] * 4 + [
True
] # allow to choose lambda for different f in f_vec
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
elif choice == 1002:
choose(1001)
Macro_Accuracy = True
# MASC Reduced dataset
elif choice == 1101:
FILENAMEZ = 'masc-reduced'
fig_label = 'MASC Reduced'
legend_location = 'lower right'
n = 31000
d = 8.3
ymin = 0
select_lambda_vec = [False] * 4 + [
True
] # allow to choose lambda for different f in f_vec
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
elif choice == 1102:
choose(1101)
Macro_Accuracy = True
else:
raise Warning("Incorrect choice!")
def _f_worker_(X0, W, f, f_index):
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(
seed=RANDOMSEED
) # seeds the actually used numpy random generator; both are used and thus needed
X1, ind = replace_fraction_of_rows(X0,
1 - f,
avoidNeighbors=avoidNeighbors,
W=W,
stratified=stratified)
X2 = introduce_errors(X1, ind, err)
for option_index, (label, select_lambda, learning_method, alpha, beta, gamma, s, numMaxIt, weights, randomize) in \
enumerate(zip(labels, select_lambda_vec, learning_method_vec, alpha_vec, beta_vec, gamma_vec, s_vec, numMaxIt_vec, weight_vec, randomize_vec)):
learn_time = -1
# -- Learning
if learning_method == 'GT':
H2c = H0c
elif learning_method == 'Heuristic':
# print('Heuristic')
H2c = H_heuristic
elif learning_method == 'Holdout':
# print('Holdout')
H2 = estimateH_baseline_serial(
X2,
ind,
W,
numMax=numMaxIt,
# ignore_rows=ind,
numberOfSplits=numberOfSplits,
# method=learning_method, variant=1,
# distance=length,
EC=EC,
alpha=alpha,
beta=beta,
gamma=gamma,
doubly_stochastic=doubly_stochastic)
H2c = to_centering_beliefs(H2)
else:
if "DCEr" in learning_method:
learning_method = "DCEr"
elif "DCE" in learning_method:
learning_method = "DCE"
# -- choose optimal lambda: allows to specify different lambda for different f
# print("option: ", option_index)
if select_lambda == True:
weight = lambda_vec[f_index]
# print("weight : ", weight)
else:
weight = weights
# -- learn H
learn_start = time.time()
H2 = estimateH(X2,
W,
method=learning_method,
variant=1,
distance=length,
EC=EC,
weights=weight,
randomrestarts=num_restarts,
randomize=randomize,
constraints=constraints,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
learn_time = time.time() - learn_start
H2c = to_centering_beliefs(H2)
# if learning_method not in ['GT', 'GS']:
# print(FILENAMEZ, f, learning_method)
# print(H2c)
# -- Propagation
prop_start = time.time()
# X2c = to_centering_beliefs(X2, ignoreZeroRows=True) # try without
eps_max = eps_convergence_linbp_parameterized(H2c,
W,
method='noecho',
alpha=alpha,
beta=beta,
gamma=gamma,
X=X2)
eps = s * eps_max
# print("Max eps: {}, eps: {}".format(eps_max, eps))
# eps = 1
try:
F, actualIt, actualPercentageConverged = \
linBP_symmetric_parameterized(X2, W, H2c * eps,
method='noecho',
alpha=alpha, beta=beta, gamma=gamma,
numMaxIt=numMaxIt,
convergencePercentage=convergencePercentage_W,
debug=2)
prop_time = time.time() - prop_start
if Macro_Accuracy:
accuracy_X = matrix_difference_classwise(X0,
F,
ignore_rows=ind)
precision = matrix_difference_classwise(
X0, F, similarity='precision', ignore_rows=ind)
recall = matrix_difference_classwise(X0,
F,
similarity='recall',
ignore_rows=ind)
else:
accuracy_X = matrix_difference(X0, F, ignore_rows=ind)
precision = matrix_difference(X0,
F,
similarity='precision',
ignore_rows=ind)
recall = matrix_difference(X0,
F,
similarity='recall',
ignore_rows=ind)
result = [str(datetime.datetime.now())]
text = [
label, f, accuracy_X, precision, recall, learn_time,
prop_time
]
result.extend(text)
# print("method: {}, f: {}, actualIt: {}, accuracy: {}, precision:{}, recall: {}, learning time: {}, propagation time: {}".format(label, f, actualIt, accuracy_X, precision, recall, learn_time, prop_time))
save_csv_record(join(data_directory, csv_filename), result)
except ValueError as e:
print("ERROR: {} with {}: d={}, h={}".format(
e, learning_method, d, h))
raise e
return 'success'
def multi_run_wrapper(args):
"""Wrapper to unpack arguments passed to the pool worker.
NOTE: This method could be removed by upgrading to Python>=3.3, which
includes the multiprocessing.starmap_async() function, which allows
multiple arguments to be passed to the map function.
"""
return _f_worker_(*args)
for choice in experiments:
choose(choice)
filename = 'Fig_End-to-End_accuracy_realData_{}_{}'.format(
choice, FILENAMEZ)
csv_filename = '{}.csv'.format(filename)
header = [
'currenttime', 'method', 'f', 'accuracy', 'precision', 'recall',
'learntime', 'proptime'
]
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename),
header,
append=False)
# print("choice: {}".format(choice))
# --- print data statistics
if CALCULATE_DATA_STATISTICS:
Xd, W = load_Xd_W_from_csv(
join(realDataDir, FILENAMEZ) + '-classes.csv',
join(realDataDir, FILENAMEZ) + '-neighbors.csv')
X0 = from_dictionary_beliefs(Xd)
n = len(Xd.keys())
d = (len(W.nonzero()[0]) * 2) / n
k = len(X0[0])
print("FILENAMEZ:", FILENAMEZ)
print("k:", k)
print("n:", n)
print("d:", d)
# -- Graph statistics
n_vec = calculate_nVec_from_Xd(Xd)
print("n_vec:\n", n_vec)
d_vec = calculate_average_outdegree_from_graph(W, Xd=Xd)
print("d_vec:\n", d_vec)
P = calculate_Ptot_from_graph(W, Xd)
print("P:\n", P)
for i in range(k):
Phi = calculate_degree_correlation(W, X0, i, NB=True)
print("Degree Correlation, Class {}:\n{}".format(i, Phi))
# -- Various compatibilities
H0 = estimateH(X0,
W,
method='MHE',
variant=1,
distance=1,
EC=EC,
weights=1,
randomize=False,
constraints=True,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
print("H0 w/ constraints:\n", np.round(H0, 2))
#raw_input() # Why?
H2 = estimateH(X0,
W,
method='MHE',
variant=1,
distance=1,
EC=EC,
weights=1,
randomize=False,
constraints=True,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
H4 = estimateH(X0,
W,
method='DHE',
variant=1,
distance=1,
EC=EC,
weights=2,
randomize=False,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
H5 = estimateH(X0,
W,
method='DHE',
variant=1,
distance=1,
EC=EC,
weights=2,
randomize=False,
constraints=True,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
H6 = estimateH(X0,
W,
method='DHE',
variant=1,
distance=2,
EC=EC,
weights=10,
randomize=False,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
H7 = estimateH(X0,
W,
method='DHE',
variant=1,
distance=2,
EC=EC,
weights=10,
randomize=False,
constraints=True,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
print()
# print("H MCE w/o constraints:\n", np.round(H0, 3))
print("H MCE w/ constraints:\n", np.round(H2, 3))
# print("H DCE 2 w/o constraints:\n", np.round(H4, 3))
print("H DCE 2 w/ constraints:\n", np.round(H5, 3))
# print("H DCE 10 w/o constraints:\n", np.round(H6, 3))
print("H DCE 20 w/ constraints:\n", np.round(H7, 3))
print()
H_row_vec = H_observed(W, X0, 3, NB=True, variant=1)
print("H_est_1:\n", np.round(H_row_vec[0], 3))
print("H_est_2:\n", np.round(H_row_vec[1], 3))
print("H_est_3:\n", np.round(H_row_vec[2], 3))
# --- Create data
if CREATE_DATA or ADD_DATA:
Xd, W = load_Xd_W_from_csv(
join(realDataDir, FILENAMEZ) + '-classes.csv',
join(realDataDir, FILENAMEZ) + '-neighbors.csv')
X0 = from_dictionary_beliefs(Xd)
n = len(Xd.keys()) ## number of nodes in graph
k = len(X0[0])
d = (len(W.nonzero()[0]) * 2) / n
#print(n)
#print(d)
#print("contraint = {}".format(constraints))
#print('select lambda: {}'.format(len(select_lambda_vec)))
#print('learning method: {}'.format(len(learning_method_vec)))
#print('alpha: {}'.format(len(alpha_vec)))
#print('beta: {}'.format(len(beta_vec)))
#print('gamma: {}'.format(len(gamma_vec)))
#print('s: {}'.format(len(s_vec)))
#print('maxit: {}'.format(len(numMaxIt_vec)))
#print('weight: {}'.format(len(weight_vec)))
#print('randomize: {}'.format(len(randomize_vec)))
# --- Calculating True Compatibility matrix
H0 = estimateH(X0,
W,
method='MHE',
variant=1,
distance=1,
EC=EC,
weights=1,
randomize=False,
constraints=constraints,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
# print(H0)
H0c = to_centering_beliefs(H0)
num_results = len(f_vec) * len(learning_method_vec) * rep_SameGraph
# Starts a thread pool with 10 fewer than the max number your computer
# has available assuming one thread per cpu - this is meant for
# supercomputer.
#pool = multiprocessing.Pool(int(multiprocessing.cpu_count()-10))
# Use this for a reasonably powerful home computer
#pool = multiprocessing.Pool(int(multiprocessing.cpu_count()/2))
# Use this for anything else
pool = multiprocessing.Pool(2)
f_processes = f_vec * rep_SameGraph
workers = []
results = [(X0, W, f, ix)
for ix, f in enumerate(f_vec)] * rep_SameGraph
# print('Expected results: {}'.format(num_results))
try: # hacky fix due to a bug in 2.7 multiprocessing
# Distribute work for evaluating accuracy over the thread pool using
# a hacky method due to python 2.7 multiprocessing not being fully
# featured
pool.map_async(multi_run_wrapper, results).get(num_results * 2)
except multiprocessing.TimeoutError as e:
continue
finally:
pool.close()
pool.join()
# -- Read data for all options and plot
df1 = pd.read_csv(join(data_directory, csv_filename))
acc_filename = '{}_accuracy_plot.pdf'.format(filename)
pr_filename = '{}_PR_plot.pdf'.format(filename)
if TIMING:
print('=== {} Timing Results ==='.format(FILENAMEZ))
print('Prop Time:\navg: {}\nstddev: {}'.format(
np.average(df1['proptime'].values),
np.std(df1['proptime'].values)))
for learning_method in labels:
rs = df1.loc[df1["method"] == learning_method]
avg = np.average(rs['learntime'])
std = np.std(rs['learntime'])
print('{} Learn Time:\navg: {}\nstd: {}'.format(
learning_method, avg, std))
sslhv.plot(df1,
join(figure_directory, acc_filename),
n=n,
d=d,
k=k,
labels=labels,
dataset=FILENAMEZ,
line_styles=linestyle_vec,
xmin=xmin,
ymin=ymin,
xmax=xmax,
ymax=ymax,
marker_sizes=markersize_vec,
draw_stds=draw_std_vec,
markers=marker_vec,
line_colors=facecolor_vec,
line_widths=linewidth_vec,
legend_location=legend_location,
show=SHOW_PDF,
save=CREATE_PDF,
show_plot=SHOW_PLOT)
def run(choice, create_data=False, add_data=False, show_plot=False, create_pdf=False, show_pdf=False, shorten_length=False):
CHOICE = choice
CREATE_DATA = create_data
ADD_DATA = add_data
SHOW_PLOT = show_plot
SHOW_PDF = show_pdf
CREATE_PDF = create_pdf
STD_FILL = True
#
SHORTEN_LENGTH = False
fig_filename = 'Fig_homophily_{}.pdf'.format(CHOICE)
csv_filename = 'Fig_homophily_{}.csv'.format(CHOICE)
header = ['currenttime',
'option',
'f',
'accuracy']
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename), header, append=False)
# -- Default Graph parameters
k = 3
rep_DifferentGraphs = 1
rep_SameGraph = 2
initial_h0 = None
distribution = 'powerlaw'
exponent = -0.3
length = 5
constraint = True
variant = 1
EC = True # Non-backtracking for learning
global f_vec, labels, facecolor_vec
s = 0.5
err = 0
numMaxIt = 10
avoidNeighbors = False
convergencePercentage_W = None
stratified = True
clip_on_vec = [True] * 10
draw_std_vec = range(10)
ymin = 0.3
ymax = 1
xmin = 0.001
xmax = 1
xtick_lab = [0.00001, 0.0001, 0.001, 0.01, 0.1, 1]
xtick_labels = ['1e-5', '0.01\%', '0.1\%', '1\%', '10\%', '100\%']
ytick_lab = np.arange(0, 1.1, 0.1)
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [5, 2, 3, 3, 3, 3] + [3]*10
marker_vec = [None, '^', 'v', 'o', '^'] + [None]*10
markersize_vec = [0, 8, 8, 8, 6, 6] + [6]*10
facecolor_vec = ['black', "#C44E52", "#64B5CD"]
# -- Options with propagation variants
if CHOICE == 101:
n = 10000
h = 3
d = 15
f_vec = [0.9 * pow(0.1, 1 / 5) ** x for x in range(21)]
option_vec = ['opt1', 'opt2', 'opt3']
learning_method_vec = ['GT','DHE','Homophily']
weight_vec = [None] + [10] + [None]
randomize_vec = [None] + [True] + [None]
xmin = 0.001
ymin = 0.3
ymax = 1
labels = ['GS', 'DCEr', 'Homophily']
else:
raise Warning("Incorrect choice!")
a = 1
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(seed=RANDOMSEED) # seeds the actually used numpy random generator; both are used and thus needed
# print("CHOICE: {}".format(CHOICE))
# -- Create data
if CREATE_DATA or ADD_DATA:
for i in range(rep_DifferentGraphs): # create several graphs with same parameters
W, Xd = planted_distribution_model_H(n, alpha=alpha0, H=H0, d_out=d, distribution=distribution,
exponent=exponent, directed=False, debug=False)
X0 = from_dictionary_beliefs(Xd)
for j in range(rep_SameGraph): # repeat several times for same graph
# print("Graph:{} and j: {}".format(i,j))
ind = None
for f in f_vec:
X1, ind = replace_fraction_of_rows(X0, 1-f, avoidNeighbors=avoidNeighbors, W=W, ind_prior=ind, stratified=stratified)
X2 = introduce_errors(X1, ind, err)
for option_index, (option, learning_method, weights, randomize) in \
enumerate(zip(option_vec, learning_method_vec, weight_vec, randomize_vec)):
# -- Learning
if learning_method == 'GT':
H2 = H0
elif learning_method == 'Homophily':
H2 = np.identity(k)
elif learning_method == 'DHE':
H2 = estimateH(X2, W, method=learning_method, variant=1, distance=length, EC=EC, weights=weights, randomize=randomize, constraints=constraint)
# print("learning_method:", learning_method)
# print("H:\n{}".format(H2))
# -- Propagation
H2c = to_centering_beliefs(H2)
X2c = to_centering_beliefs(X2, ignoreZeroRows=True)
try:
eps_max = eps_convergence_linbp_parameterized(H2c, W,
method='noecho',
X=X2)
eps = s * eps_max
F, actualIt, actualPercentageConverged = \
linBP_symmetric_parameterized(X2, W, H2c * eps,
method='noecho',
numMaxIt=numMaxIt,
convergencePercentage=convergencePercentage_W,
debug=2)
except ValueError as e:
print (
"ERROR: {} with {}: d={}, h={}".format(e, learning_method, d, h))
else:
accuracy_X = matrix_difference_classwise(X0, F, ignore_rows=ind)
tuple = [str(datetime.datetime.now())]
text = [option_vec[option_index],
f,
accuracy_X]
tuple.extend(text)
# print("option: {}, f: {}, actualIt: {}, accuracy: {}".format(option_vec[option_index], f, actualIt, accuracy_X))
save_csv_record(join(data_directory, csv_filename), tuple)
# -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1: (length {}):\n{}".format(len(df1.index), df1.head(15)))
desred_decimals = 7
df1['f'] = df1['f'].apply(lambda x: round(x,desred_decimals)) # rounding due to different starting points
# print("\n-- df1: (length {}):\n{}".format(len(df1.index), df1.head(15)))
# Aggregate repetitions
df2 = df1.groupby(['option', 'f']).agg \
({'accuracy': [np.mean, np.std, np.size], # Multiple Aggregates
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'accuracy_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(10)))
# Pivot table
df3 = pd.pivot_table(df2, index=['f'], columns=['option'], values=['accuracy_mean', 'accuracy_std'] ) # Pivot
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
df3.columns = ['_'.join(col).strip() for col in df3.columns.values] # flatten the column hierarchy
df3.reset_index(inplace=True) # remove the index hierarchy
# df2.rename(columns={'time_size': 'count'}, inplace=True)
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(10)))
# Extract values
X_f = df3['f'].values # plot x values
Y=[]
Y_std=[]
for option in option_vec:
Y.append(df3['accuracy_mean_{}'.format(option)].values)
if STD_FILL:
Y_std.append(df3['accuracy_std_{}'.format(option)].values)
if SHORTEN_LENGTH:
SHORT_FACTOR = 2 ## KEEP EVERY Nth ELEMENT
X_f = np.copy(X_f[list(range(0, len(X_f), SHORT_FACTOR)), ])
for i in range(len(Y)):
Y[i] = np.copy(Y[i][list(range(0, len(Y[i]), SHORT_FACTOR)), ])
if STD_FILL:
Y_std[i] = np.copy(Y_std[i][list(range(0, len(Y_std[i]), SHORT_FACTOR)),])
if CREATE_PDF or SHOW_PLOT or SHOW_PDF:
# -- Setup figure
mpl.rc('font', **{'family': 'sans-serif', 'sans-serif': [u'Arial', u'Liberation Sans']})
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 14
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['xtick.major.pad'] = 2 # padding of tick labels: default = 4
mpl.rcParams['ytick.major.pad'] = 1 # padding of tick labels: default = 4
mpl.rcParams['xtick.direction'] = 'out' # default: 'in'
mpl.rcParams['ytick.direction'] = 'out' # default: 'in'
mpl.rcParams['font.size'] = 16
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['figure.figsize'] = [4, 4]
fig = figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
# -- Drawing
if STD_FILL:
for choice, (option, facecolor) in enumerate(zip(option_vec, facecolor_vec)):
ax.fill_between(X_f, Y[choice] + Y_std[choice], Y[choice] - Y_std[choice],
facecolor=facecolor, alpha=0.2, edgecolor=None, linewidth=0)
ax.plot(X_f, Y[choice] + Y_std[choice], linewidth=0.5, color='0.8', linestyle='solid')
ax.plot(X_f, Y[choice] - Y_std[choice], linewidth=0.5, color='0.8', linestyle='solid')
for choice, (option, label, color, linewidth, clip_on, linestyle, marker, markersize) in \
enumerate(zip(option_vec, labels, facecolor_vec, linewidth_vec, clip_on_vec, linestyle_vec, marker_vec, markersize_vec)):
P = ax.plot(X_f, Y[choice], linewidth=linewidth, color=color, linestyle=linestyle, label=label, zorder=4, marker=marker,
markersize=markersize, markeredgewidth=1, clip_on=clip_on, markeredgecolor='black')
plt.xscale('log')
# -- Title and legend
distribution_label = '$'
if distribution == 'uniform':
distribution_label = ',$uniform'
n_label = '{}k'.format(int(n / 1000))
if n < 1000:
n_label='{}'.format(n)
a_label = ''
if a != 1:
a_label = ', a\!=\!{}'.format(a)
titleString = r'$\!\!\!n\!=\!{}, d\!=\!{}, h\!=\!{}{}{}'.format(n_label, d, h, a_label, distribution_label)
plt.title(titleString)
handles, labels = ax.get_legend_handles_labels()
legend = plt.legend(handles, labels,
loc='upper left', # 'upper right'
handlelength=2,
labelspacing=0, # distance between label entries
handletextpad=0.3, # distance between label and the line representation
borderaxespad=0.2, # distance between legend and the outer axes
borderpad=0.3, # padding inside legend box
numpoints=1, # put the marker only once
)
# # legend.set_zorder(1)
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.9) # 0.8
plt.xticks(xtick_lab, xtick_labels)
plt.yticks(ytick_lab, ytick_lab)
ax.yaxis.set_ticks_position('left')
ax.xaxis.set_ticks_position('bottom')
ax.yaxis.set_major_formatter(mpl.ticker.FormatStrFormatter('%.1f'))
grid(b=True, which='major', axis='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
grid(b=True, which='minor', axis='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
xlabel(r'Label Sparsity $(f)$', labelpad=0) # labelpad=0
ylabel(r'Accuracy', labelpad=0)
xlim(xmin, xmax)
ylim(ymin, ymax)
if CREATE_PDF:
savefig(join(figure_directory, fig_filename), format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
frameon=None)
if SHOW_PLOT:
plt.show()
if SHOW_PDF:
showfig(join(figure_directory, fig_filename)) # shows actually created PDF
def run(choice,
create_data=False,
add_data=False,
show_plot=False,
create_pdf=False,
show_pdf=False):
global n
global d
global rep_SameGraph
global FILENAMEZ
global initial_h0
global H0c
global exponent
global length
global variant
global alpha_vec
global beta_vec
global gamma_vec
global s_vec
global clip_on_vec
global numMaxIt_vec
# Plotting Parameters
global xtick_lab
global xtick_labels
global ytick_lab
global xmax
global xmin
global ymin
global ymax
global labels
global facecolor_vec
global draw_std_vec
global linestyle_vec
global linewidth_vec
global marker_vec
global markersize_vec
global legend_location
global option_vec
global learning_method_vec
global Macro_Accuracy
global EC
global constraints
global weight_vec
global randomize_vec
global k
global fig_label
global err
global avoidNeighbors
global convergencePercentage_W
global stratified
global gradient
global doubly_stochastic
global numberOfSplits
global select_lambda_vec
global lambda_vec
global f_vec
# -- Setup
CHOICE = choice
#500 Yelp, 600 Flickr, 700 DBLP, 800 Enron
CREATE_DATA = create_data
ADD_DATA = add_data
SHOW_PDF = show_pdf
SHOW_PLOT = show_plot
CREATE_PDF = create_pdf
STD_FILL = True
CALCULATE_DATA_STATISTICS = False
# -- Default Graph parameters
rep_SameGraph = 3 # iterations on same graph
initial_h0 = None # initial vector to start finding optimal H
exponent = -0.3
length = 5
variant = 1
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
clip_on_vec = [True] * 10
numMaxIt_vec = [10] * 10
# Plotting Parameters
xtick_lab = [0.00001, 0.0001, 0.001, 0.01, 0.1, 1]
xtick_labels = ['0.001\%', '0.01\%', '0.1\%', '1\%', '10\%', '100\%']
ytick_lab = np.arange(0, 1.1, 0.1)
xmax = 1
xmin = 0.0001
ymin = 0.3
ymax = 0.7
labels = ['GT', 'LCE', 'MCE', 'DCE', 'DCE r']
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974",
"#64B5CD"
]
draw_std_vec = [0, 3, 4, 4, 4, 4]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [4, 4, 2, 1, 2]
marker_vec = [None, 'o', 'x', '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8]
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
Macro_Accuracy = False
EC = True # Non-backtracking for learning
constraints = True # True
weight_vec = [None] * 3 + [10, 10]
randomize_vec = [False] * 4 + [True]
k = 3
err = 0
avoidNeighbors = False
convergencePercentage_W = None
stratified = True
gradient = True
doubly_stochastic = True
draw_std_vec = range(10)
numberOfSplits = 1
select_lambda_vec = [False] * 20
lambda_vec = None
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
FILENAMEZ = ""
legend_location = ""
fig_label = ""
global exp_backoff
exp_backoff = [2**n for n in range(6, 12)]
def choose(choice):
# -- Default Graph parameters
global n
global d
global rep_SameGraph
global FILENAMEZ
global initial_h0
global exponent
global length
global variant
global alpha_vec
global beta_vec
global gamma_vec
global s_vec
global clip_on_vec
global numMaxIt_vec
# Plotting Parameters
global xtick_lab
global xtick_labels
global ytick_lab
global xmax
global xmin
global ymin
global ymax
global labels
global facecolor_vec
global draw_std_vec
global linestyle_vec
global linewidth_vec
global marker_vec
global markersize_vec
global legend_location
global option_vec
global learning_method_vec
global Macro_Accuracy
global EC
global constraints
global weight_vec
global randomize_vec
global k
global fig_label
global err
global avoidNeighbors
global convergencePercentage_W
global stratified
global gradient
global doubly_stochastic
global numberOfSplits
global select_lambda_vec
global lambda_vec
global f_vec
if choice == 0:
None
elif choice == 304: ## with varying weights
FILENAMEZ = 'prop37'
Macro_Accuracy = True
fig_label = 'Prop37'
legend_location = 'lower right'
n = 62000
d = 34.8
select_lambda_vec = [False] * 5
# select_lambda_vec = [False] * 3 + [True] * 2 # allow to choose lambda for different f in f_vec
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
# lambda_vec = [0.5] * 21 # same length as f_vec
elif choice == 305: # Test row stochastic cases
choose(304)
doubly_stochastic = False
# -- Yelp dataset
elif choice == 501:
FILENAMEZ = 'yelp'
Macro_Accuracy = True
weight_vec = [None] * 3 + [10, 10]
gradient = True
ymin = 0.1
ymax = 0.75
fig_label = 'Yelp'
legend_location = 'upper left'
n = 4301900 # for figure
d = 6.56 # for figure
# -- Flickr dataset
elif choice == 601:
FILENAMEZ = 'flickr'
Macro_Accuracy = True
fig_label = 'Flickr'
legend_location = 'lower right'
n = 2007369
d = 18.1
elif choice == 602: ## with varying weights
choose(601)
select_lambda_vec = [False] * 4 + [
True
] # allow to choose lambda for different f in f_vec
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
elif choice == 603: ## with varying weights
choose(602)
select_lambda_vec = [False] * 3 + [
True
] * 2 # allow to choose lambda for different f in f_vec
# lambda_vec = [1] * 5 + [5] * 5 + [10] * 5 + [1] * 6 # same length as f_vec
elif choice == 604: ## with weight = 1
draw_std_vec = [4]
choose(603)
lambda_vec = [0.5] * 21 # same length as f_vec
# -- DBLP dataset
elif choice == 701:
FILENAMEZ = 'dblp.txt'
Macro_Accuracy = True
ymin = 0.2
ymax = 0.5
fig_label = 'DBLP'
legend_location = 'lower right'
n = 2241258 # for figure
d = 26.11 # for figure
# -- ENRON dataset
elif choice == 801:
FILENAMEZ = 'enron'
Macro_Accuracy = True
ymin = 0.3
ymax = 0.75
fig_label = 'Enron'
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
legend_location = 'upper left'
n = 46463 # for figures
d = 23.4 # for figures
elif choice == 802: ### WITH ADAPTIVE WEIGHTS
choose(801)
select_lambda_vec = [False] * 4 + [
True
] # allow to choose lambda for different f in f_vec
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
elif choice == 803: ### WITH ADAPTIVE WEIGHTS
choose(802)
lambda_vec = [1] * 5 + [5] * 5 + [10] * 5 + [
1
] * 6 # same length as f_vec
elif choice == 804:
choose(803)
elif choice == 805:
choose(801)
doubly_stochastic = False
elif choice == 821:
FILENAMEZ = 'enron'
Macro_Accuracy = True
constraints = True # True
gradient = True
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
weight_vec = [None] * 3 + [0.2, 0.2]
randomize_vec = [False] * 4 + [True]
xmin = 0.0001
ymin = 0.0
ymax = 0.7
labels = ['GS', 'LCE', 'MCE', 'DCE', 'DCE r']
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974",
"#64B5CD"
]
draw_std_vec = [4]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [4, 4, 2, 1, 2]
marker_vec = [None, 'o', 'x', '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8]
fig_label = 'Enron'
legend_location = 'lower right'
n = 46463 # for figures
d = 23.4 # for figures
alpha = 0.0
beta = 0.0
gamma = 0.0
s = 0.5
numMaxIt = 10
select_lambda_vec = [False] * 3 + [True] * 2
lambda_vec = [0.2] * 13 + [10] * 8 # same length as f_vec
captionText = "DCE weight=[0.2*13] [10*8], s={}, numMaxIt={}".format(
s, numMaxIt)
# -- Cora dataset
elif choice == 901:
FILENAMEZ = 'cora'
Macro_Accuracy = True
constraints = True # True
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
weight_vec = [None] * 3 + [10, 10]
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True]
gradient = True
xmin = 0.001
ymin = 0.0
ymax = 0.9
labels = ['GT', 'LCE', 'MCE', 'DCE', 'DCE r']
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974",
"#64B5CD"
]
draw_std_vec = [4]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [4, 4, 2, 1, 2]
marker_vec = [None, 'o', 'x', '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8]
fig_label = 'Cora'
legend_location = 'lower right'
n = 2708
d = 7.8
# -- Citeseer dataset
elif CHOICE == 1001:
FILENAMEZ = 'citeseer'
Macro_Accuracy = True
constraints = True # True
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
weight_vec = [None] * 3 + [10, 10]
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True]
gradient = True
xmin = 0.001
ymin = 0.0
ymax = 0.75
labels = ['GT', 'LCE', 'MCE', 'DCE', 'DCE r']
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974",
"#64B5CD"
]
draw_std_vec = [4]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [4, 4, 2, 1, 2]
marker_vec = [None, 'o', 'x', '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8]
fig_label = 'Citeseer'
legend_location = 'lower right'
n = 3312
d = 5.6
elif CHOICE == 1101:
FILENAMEZ = 'hep-th'
Macro_Accuracy = True
constraints = True # True
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
weight_vec = [None] * 3 + [10, 10]
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True]
gradient = True
xmin = 0.0001
ymin = 0.0
ymax = 0.1
labels = ['GT', 'LCE', 'MCE', 'DCE', 'DCE r']
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974",
"#64B5CD"
]
draw_std_vec = [4]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [4, 4, 2, 1, 2]
marker_vec = [None, 'o', 'x', '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8]
fig_label = 'Hep-th'
legend_location = 'lower right'
n = 27770
d = 5.6
elif CHOICE == 1204:
FILENAMEZ = 'pokec-gender'
Macro_Accuracy = True
constraints = True # True
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
weight_vec = [None] * 3 + [10, 10]
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True]
gradient = True
xmin = 0.000015
ymin = 0.0
ymax = 0.75
labels = ['GT', 'LCE', 'MCE', 'DCE', 'DCE r']
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974",
"#64B5CD"
]
draw_std_vec = [0, 3, 4, 4, 4, 4]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [4, 4, 2, 1, 2]
marker_vec = [None, 'o', 'x', '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8]
fig_label = 'Pokec-Gender'
legend_location = 'lower right'
n = 1632803
d = 54.6
else:
raise Warning("Incorrect choice!")
choose(CHOICE)
csv_filename = 'Fig_End-to-End_accuracy_{}_{}.csv'.format(
CHOICE, FILENAMEZ)
header = ['currenttime', 'method', 'f', 'precision', 'recall', 'accuracy']
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename),
header,
append=False)
# print("choice: {}".format(CHOICE))
# --- print data statistics
if CALCULATE_DATA_STATISTICS:
Xd, W = load_Xd_W_from_csv(
join(realDataDir, FILENAMEZ) + '-classes.csv',
join(realDataDir, FILENAMEZ) + '-neighbors.csv')
X0 = from_dictionary_beliefs(Xd)
n = len(Xd.keys())
d = (len(W.nonzero()[0]) * 2) / n
print("FILENAMEZ:", FILENAMEZ)
print("n:", n)
print("d:", d)
# -- Graph statistics
n_vec = calculate_nVec_from_Xd(Xd)
print("n_vec:\n", n_vec)
d_vec = calculate_average_outdegree_from_graph(W, Xd=Xd)
print("d_vec:\n", d_vec)
P = calculate_Ptot_from_graph(W, Xd)
print("P:\n", P)
# -- Various compatibilities
H0 = estimateH(X0,
W,
method='MHE',
variant=1,
distance=1,
EC=EC,
weights=1,
randomize=False,
constraints=True,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
print("H0 w/ constraints:\n", np.round(H0, 2))
raw_input()
H2 = estimateH(X0,
W,
method='MHE',
variant=1,
distance=1,
EC=EC,
weights=1,
randomize=False,
constraints=True,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
H4 = estimateH(X0,
W,
method='DHE',
variant=1,
distance=1,
EC=EC,
weights=2,
randomize=False,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
H5 = estimateH(X0,
W,
method='DHE',
variant=1,
distance=1,
EC=EC,
weights=2,
randomize=False,
constraints=True,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
H6 = estimateH(X0,
W,
method='DHE',
variant=1,
distance=2,
EC=EC,
weights=10,
randomize=False,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
H7 = estimateH(X0,
W,
method='DHE',
variant=1,
distance=2,
EC=EC,
weights=10,
randomize=False,
constraints=True,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
# print("H MCE w/o constraints:\n", np.round(H0, 3))
print("H MCE w/ constraints:\n", np.round(H2, 3))
# print("H DCE 2 w/o constraints:\n", np.round(H4, 3))
print("H DCE 2 w/ constraints:\n", np.round(H5, 3))
# print("H DCE 10 w/o constraints:\n", np.round(H6, 3))
print("H DCE 20 w/ constraints:\n", np.round(H7, 3))
H_row_vec = H_observed(W, X0, 3, NB=True, variant=1)
print("H_est_1:\n", np.round(H_row_vec[0], 3))
print("H_est_2:\n", np.round(H_row_vec[1], 3))
print("H_est_3:\n", np.round(H_row_vec[2], 3))
# --- Create data
if CREATE_DATA or ADD_DATA:
Xd, W = load_Xd_W_from_csv(
join(realDataDir, FILENAMEZ) + '-classes.csv',
join(realDataDir, FILENAMEZ) + '-neighbors.csv')
X0 = from_dictionary_beliefs(Xd)
n = len(Xd.keys()) ## number of nodes in graph
d = (len(W.nonzero()[0]) * 2) / n
# print(n)
# print(d)
# print("contraint = {}".format(constraints))
# --- Calculating True Compatibility matrix
H0 = estimateH(X0,
W,
method='MHE',
variant=1,
distance=1,
EC=EC,
weights=1,
randomize=False,
constraints=constraints,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
# print(H0)
H0c = to_centering_beliefs(H0)
graph_workers = []
gq = multiprocessing.Queue()
for j in range(rep_SameGraph): # repeat several times for same graph
# print("Graph: {}".format(j))
graph_workers.append(
multiprocessing.Process(target=graph_worker, args=(X0, W, gq)))
for gw in graph_workers:
gw.start()
for gw in graph_workers:
for t in exp_backoff:
gw.join(t)
if gw.exitcode is None:
print(
"failed to join graph worker {} after {} seconds, retrying"
.format(gw, t))
else:
continue
print("Failed to join graph worker {}.".format(gw))
gq.put('STOP')
for i in iter(gq.get, 'STOP'):
save_csv_record(join(data_directory, csv_filename), i)
# -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
acc_filename = 'Fig_End-to-End_accuracy_realData{}_{}.pdf'.format(
CHOICE, FILENAMEZ)
pr_filename = 'Fig_End-to-End_PR_realData{}_{}.pdf'.format(
CHOICE, FILENAMEZ)
# generate_figure(data_directory, acc_filename, df1)
# generate_figure(data_directory, pr_filename, df1, metric='pr')
# print("\n-- df1: (length {}):\n{}".format(len(df1.index), df1.head(5)))
# Aggregate repetitions
if "option" in df1.columns.values:
pivot_col = "option"
pivot_vec = option_vec
else:
pivot_col = "method"
pivot_vec = learning_method_vec
df2 = df1.groupby([pivot_col, 'f']).agg \
({'accuracy': [np.mean, np.std, np.size], # Multiple Aggregates
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values
] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'accuracy_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(500)))
# Pivot table
df3 = pd.pivot_table(df2,
index='f',
columns=pivot_col,
values=['accuracy_mean', 'accuracy_std']) # Pivot
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
df3.columns = ['_'.join(col).strip() for col in df3.columns.values
] # flatten the column hierarchy
df3.reset_index(inplace=True) # remove the index hierarchy
# df2.rename(columns={'time_size': 'count'}, inplace=True)
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(5)))
# Extract values
X_f = df3['f'].values # plot x values
Y = []
Y_std = []
for val in pivot_vec:
Y.append(df3['accuracy_mean_{}'.format(val)].values)
if STD_FILL:
Y_std.append(df3['accuracy_std_{}'.format(val)].values)
if CREATE_PDF or SHOW_PDF or SHOW_PLOT:
print("Setting up figure...")
# -- Setup figure
# remove 4 last characters ".txt"
fig_filename = 'Fig_End-to-End_accuracy_realData{}_{}.pdf'.format(
CHOICE, FILENAMEZ)
mpl.rc(
'font', **{
'family': 'sans-serif',
'sans-serif': [u'Arial', u'Liberation Sans']
})
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 14 # 6
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams[
'xtick.major.pad'] = 2 # padding of tick labels: default = 4
mpl.rcParams[
'ytick.major.pad'] = 1 # padding of tick labels: default = 4
mpl.rcParams['xtick.direction'] = 'out' # default: 'in'
mpl.rcParams['ytick.direction'] = 'out' # default: 'in'
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['figure.figsize'] = [4, 4]
fig = figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
# -- Drawing
if STD_FILL:
for choice, (option,
facecolor) in enumerate(zip(option_vec,
facecolor_vec)):
if choice in draw_std_vec:
ax.fill_between(X_f,
Y[choice] + Y_std[choice],
Y[choice] - Y_std[choice],
facecolor=facecolor,
alpha=0.2,
edgecolor=None,
linewidth=0)
ax.plot(X_f,
Y[choice] + Y_std[choice],
linewidth=0.5,
color='0.8',
linestyle='solid')
ax.plot(X_f,
Y[choice] - Y_std[choice],
linewidth=0.5,
color='0.8',
linestyle='solid')
for choice, (option, label, color, linewidth, clip_on, linestyle, marker, markersize) in \
enumerate(zip(option_vec, labels, facecolor_vec, linewidth_vec, clip_on_vec, linestyle_vec, marker_vec, markersize_vec)):
ax.plot(X_f,
Y[choice],
linewidth=linewidth,
color=color,
linestyle=linestyle,
label=label,
zorder=4,
marker=marker,
markersize=markersize,
markeredgewidth=1,
clip_on=clip_on)
# -- Title and legend
if n < 1000:
n_label = '{}'.format(n)
else:
n_label = '{}k'.format(int(n / 1000))
title(r'$\!\!\!\!\!\!\!${}: $n={}, d={}$'.format(
fig_label, n_label, np.round(d, 1)))
handles, labels = ax.get_legend_handles_labels()
legend = plt.legend(
handles,
labels,
loc=legend_location, # 'upper right'
handlelength=2,
labelspacing=0, # distance between label entries
handletextpad=
0.3, # distance between label and the line representation
# title='Variants',
borderaxespad=0.2, # distance between legend and the outer axes
borderpad=0.3, # padding inside legend box
numpoints=1, # put the marker only once
)
# # legend.set_zorder(1)
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.9) # 0.8
plt.xscale('log')
# -- Figure settings and save
plt.xticks(xtick_lab, xtick_labels)
plt.yticks(ytick_lab, ytick_lab)
# Only show ticks on the left and bottom spines
ax.yaxis.set_ticks_position('left')
ax.xaxis.set_ticks_position('bottom')
ax.yaxis.set_major_formatter(mpl.ticker.FormatStrFormatter('%.1f'))
grid(b=True,
which='major',
axis='both',
alpha=0.2,
linestyle='solid',
linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
grid(b=True,
which='minor',
axis='both',
alpha=0.2,
linestyle='solid',
linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
xlabel(r'Label Sparsity $(f)$', labelpad=0) # labelpad=0
ylabel(r'Accuracy', labelpad=0)
xlim(xmin, xmax)
ylim(ymin, ymax)
if CREATE_PDF:
print("saving PDF of figure...")
savefig(join(figure_directory, fig_filename),
format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
frameon=None)
if SHOW_PLOT:
print("Showing plot...")
plt.show()
if SHOW_PDF:
print("Showing pdf...")
showfig(join(figure_directory,
fig_filename)) # shows actually created PDF
def run(choice, create_data=False, add_data=False, show_plot=False, create_pdf=False, show_pdf=False, show_fig=True):
# -- Setup
CHOICE = choice
CREATE_DATA = create_data
ADD_DATA = add_data
CREATE_PDF = create_pdf
SHOW_PDF=show_pdf
SHOW_FIG1 = show_fig # bar diagram
SHOW_FIG2 = False # curve
csv_filename = 'Fig_MHE_Variants_{}.csv'.format(CHOICE)
header = ['currenttime',
'option', # one option corresponds to one choice of weight vector. In practice, one choice of scaling factor (for weight vector)
'variant', # 1, 2, 3 (against GT), and 1-2, 1-3, 2-3 (against each other)
'length',
'diff',
'time'] # L2 norm between H and estimate
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename), header, append=False)
# Default Graph parameters and options
n = 10000
f = 0.1
h = 8
distribution = 'uniform'
randomize = False
initial_h0 = None # initial vector to start finding optimal H
initial_H0 = None
exponent = -0.3
length = 5
rep = 10 #
EC = [False] + [True] * 31
scaling_vec = [1, 0.1, 0.14, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1, 1.4, 2, 3, 4, 5, 6, 7, 8, 9, 10, 14, 20, 30, 40, 50, 60, 70, 80, 90, 100]
num_options = len(scaling_vec)
scaling_vec = np.array(scaling_vec)
weight = np.array([np.power(scaling_vec, i) for i in range(5)])
weight = weight.transpose()
ymin1 = None
ymax1 = None
xmin2 = None
xmax2 = None
ymin2 = None
ymax2 = None
# fig1_index = [0, 11, 16, 21, 23, 24, 25, 26] # which index of scaling options to display if CHOICE_FIG_BAR_VARIANT==True
fig1_index = [21]
smartInit = False
smartInitRandomize = False
delta = 0.1
variant_vec = [1,2, 3] # for figure 1
variant_vec = [1] # for figure 2, to speed up calculations
if CHOICE == 1: # ok
n = 1000
d = 10
ymax2 = 0.24
elif CHOICE == 2: # ok
n = 1000
d = 10
distribution = 'powerlaw'
ymax2 = 0.24
elif CHOICE == 3: # ok
n = 1000
d = 5
distribution = 'powerlaw'
ymax2 = 0.4
elif CHOICE == 4: # ok
n = 1000
d = 25
distribution = 'powerlaw'
ymax2 = 0.16
elif CHOICE == 10: # ok
d = 10
ymax2 = 0.1
elif CHOICE == 11: # (selection)
d = 10
distribution = 'powerlaw'
exponent = -0.5
ymax2 = 0.1
ymax1 = 0.14
elif CHOICE == 12:
d = 3
ymax2 = 0.19
ymax1 = 0.2
elif CHOICE == 13:
d = 25
ymax2 = 0.05
elif CHOICE == 14: # selection (for comparison)
d = 25
distribution = 'powerlaw'
ymax2 = 0.046
ymax1 = 0.08
elif CHOICE == 15: # selection
d = 25
f = 0.05
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 0.095
elif CHOICE == 16: # selection TODO !!!
d = 25
f = 0.01
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 0.4
ymin2 = 0
elif CHOICE == 17: # selection TODO !!!
d = 25
f = 0.003
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 1.
ymin2 = 0
elif CHOICE == 18: # selection TODO !!!
d = 25
f = 0.001
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 1.
ymin2 = 0
elif CHOICE == 20:
h = 3
d = 10
ymax1 = 0.12
elif CHOICE == 21: # selection (for comparison against f=0.05: 26)
h = 3
d = 10
distribution = 'powerlaw'
exponent = -0.5
ymax1 = 0.15
ymax2 = 0.099
elif CHOICE == 22: # selection (for comparison with start from GT: 44)
h = 3
d = 3
ymax1 = 0.25
ymax2 = 0.39
elif CHOICE == 23: # ok
h = 3
d = 25
ymax1 = 0.1
ymax2 = 0.12
elif CHOICE == 24:
h = 3
d = 25
distribution = 'powerlaw'
ymax1 = 0.08
elif CHOICE == 25: # main selection
h = 3
d = 25
f = 0.05
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 0.125
elif CHOICE == 26: # selection, #=200
h = 3
d = 10
f = 0.05
distribution = 'powerlaw'
ymax1 = 0.21
ymax2 = 0.26
elif CHOICE == 27: # selection, #=200
d = 10
f = 0.05
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 0.21
elif CHOICE == 60: # ??? #=50 !!!, 50 more
d = 25
f = 0.01
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 0.6
elif CHOICE == 61: # ??? #=50, 100 more
d = 25
f = 0.005
distribution = 'powerlaw'
ymax1 = 0.99
ymax2 = 0.99
elif CHOICE == 62: # ??? #=50, 150 more
h = 3
d = 25
f = 0.01
distribution = 'powerlaw'
ymax1 = 0.6
ymax2 = 0.6
elif CHOICE == 63: # ??? #=50, 150 more
h = 3
d = 25
f = 0.005
distribution = 'powerlaw'
ymax1 = 1.2
ymax2 = 1.0
# --- Randomization ---
# randomized 22
elif CHOICE == 32:
randomize = True
h = 3
d = 3
ymax1 = 0.25
ymax2 = 0.4
# --- GT ---
# version of 22 where GT is supplied to start optimiziation
# just to check if the global optimum of the energy function actually corresponds to the GT
elif CHOICE == 42: # selection, #=200 (for comparison with start from GT)
initial_h0 = [0.2, 0.6, 0.2] # start optimization at optimal point
h = 3
d = 3
ymax1 = 0.25
ymax2 = 0.39
# version of 15 where GT is supplied to start optimiziation
elif CHOICE == 43: # selection, #=200
initial_h0 = [0.1, 0.8, 0.1] # start optimization at optimal point
h = 8
d = 25
f = 0.05
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 0.095
# version of 12 where GT is supplied to start optimiziation
elif CHOICE == 44: # selection, #=200 (for comparison)
initial_h0 = [0.1, 0.8, 0.1] # start optimization at optimal point
h = 8
d = 3
ymax1 = 0.2
ymax2 = 0.19
# version of 25 where GT is supplied to start optimiziation
elif CHOICE == 45: # selection, #=200
h = 3
d = 25
f = 0.05
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 0.125
# version of 12 where GT is supplied to start optimiziation
elif CHOICE == 46: # selection TODO !!!
initial_h0 = [0.1, 0.8, 0.1] # start optimization at optimal point
d = 25
f = 0.01
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 0.4
ymin2 = 0.0
# version of 12 where GT is supplied to start optimiziation
elif CHOICE == 47: # selection TODO !!!
initial_h0 = [0.1, 0.8, 0.1] # start optimization at optimal point
d = 25
f = 0.003
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 1.
ymin2 = 0.0
# version of 12 with smart init
elif CHOICE == 48: # selection TODO !!!
d = 25
f = 0.003
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 1.
ymin2 = 0.0
smartInit = True
# version of 12 with smart init
elif CHOICE == 49: # selection TODO !!!
d = 25
f = 0.003
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 1.
ymin2 = 0.0
smartInit = True
smartInitRandomize = True # initialize optimization at several random points for smart init only
elif CHOICE == 50: # selection TODO !!!
initial_h0 = [0.1, 0.8, 0.1] # start optimization at optimal point
d = 25
f = 0.001
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 1.
ymin2 = 0.0
elif CHOICE == 51: # selection TODO !!!
d = 25
f = 0.001
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 1.
ymin2 = 0.0
randomize = True # start optimization at several random points
delta = 0.1
elif CHOICE == 52: # selection TODO !!!
d = 25
f = 0.001
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 1.
ymin2 = 0.0
randomize = True # start optimization at several random points
delta = 0.2
elif CHOICE == 53: # selection TODO !!!
d = 25
f = 0.001
distribution = 'powerlaw'
ymax1 = 0.15
ymax2 = 1.
ymin2 = 0.0
randomize = True # start optimization at several random points
delta = 0.3
else:
raise Warning("Incorrect choice!")
k = 3
a = 1
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(seed=RANDOMSEED) # seeds the actually used numpy random generator; both are used and thus needed
# print("CHOICE: {}".format(CHOICE))
# -- Create data
if CREATE_DATA or ADD_DATA:
for r in range(1, rep+1):
# print('Repetition {}'.format(r))
# -- Create graph
W, Xd = planted_distribution_model_H(n, alpha=alpha0, H=H0, d_out=d,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
X1, ind = replace_fraction_of_rows(X0, 1 - f)
# -- Create estimates and compare against GT, or against each other
H_est={}
for length in range(1, length + 1):
for option in range(num_options):
for variant in variant_vec:
start = time.time()
if smartInit:
startWeight = 0.2
initial_H0 = estimateH(X1, W, method='DHE', variant=variant,
distance=5,
EC=EC[option], weights=startWeight,
randomize=smartInitRandomize)
H_est[variant] = estimateH(X1, W, method='DHE', variant=variant,
distance=length, EC=EC[option], weights=weight[option],
randomize=randomize,
initial_h0=initial_h0,
initial_H0=initial_H0,
delta = delta
)
time_est = time.time() - start
diff = LA.norm(H_est[variant] - H0)
tuple = [str(datetime.datetime.now())]
text = [option, variant, length, diff, time_est]
# text = np.asarray(text) # (without np, entries get ugly format) not used here because it transforms integers to float !!
tuple.extend(text)
save_csv_record(join(data_directory, csv_filename), tuple)
# -- Compare against each other
for variant1 in variant_vec:
for variant2 in variant_vec:
if variant1 < variant2:
diff = LA.norm(H_est[variant1] - H_est[variant2])
tuple = [str(datetime.datetime.now())]
text = [option, "{}-{}".format(variant1, variant2), length, diff, time_est]
tuple.extend(text)
save_csv_record(join(data_directory, csv_filename), tuple)
if SHOW_FIG1:
# -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1 (length {}):\n{}".format(len(df1.index), df1.head(15)))
df2 = df1.groupby(['option', 'variant', 'length']).agg \
({'diff': [np.mean, np.std, np.size], # Multiple Aggregates
'time': [np.mean, np.std],
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'diff_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(90)))
# -- Create one separate figure for each option
for option in range(num_options):
if option not in fig1_index:
continue
scaling = scaling_vec[option]
fig_filename = 'Fig_MHE_Variants_{}_{}.pdf'.format(CHOICE, option)
df3 = df2.query('option==@option') # Query
df3 = pd.pivot_table(df3, index=['length'], columns=['variant'], values=['diff_mean', 'diff_std']) # Pivot
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
df3.columns = ['_'.join(col).strip() for col in df3.columns.values] # flatten the column hierarchy
df3.reset_index(level=0, inplace=True) # get length into columns
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
df3.drop(['diff_std_1-2', 'diff_std_1-3', 'diff_std_2-3', ], axis=1, inplace=True)
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
# -- Setup figure
mpl.rcParams['backend'] = 'pdf'
mpl.rcParams['lines.linewidth'] = 3
mpl.rcParams['font.size'] = 16
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 14
mpl.rcParams['axes.edgecolor'] = '111111' # axes edge color
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['figure.figsize'] = [4, 4]
mpl.rcParams['xtick.major.pad'] = 4 # padding of tick labels: default = 4
mpl.rcParams['ytick.major.pad'] = 4 # padding of tick labels: default = 4
fig = plt.figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
# -- Extract values into columns (plotting dataframew with bars plus error lines and lines gave troubles)
l_vec = df3['length'].values # .tolist() does not work with bar plot, requires np.array
diff_mean_1 = df3['diff_mean_1'].values
diff_mean_2 = df3['diff_mean_2'].values
diff_mean_3 = df3['diff_mean_3'].values
diff_std_1 = df3['diff_std_1'].values
diff_std_3 = df3['diff_std_2'].values
diff_std_2 = df3['diff_std_3'].values
# -- Draw the bar plots
width = 0.2 # the width of the bars
bar1 = ax.bar(l_vec-1.5*width, diff_mean_1, width, color='blue',
yerr=diff_std_1, error_kw={'ecolor':'black', 'linewidth':2}, # error-bars colour
label=r'1')
bar2 = ax.bar(l_vec-0.5*width, diff_mean_2, width, color='darkorange',
yerr=diff_std_2, error_kw={'ecolor':'black', 'linewidth':2}, # error-bars colour
label=r'2')
bar3 = ax.bar(l_vec+0.5*width, diff_mean_3, width, color='green',
yerr=diff_std_1, error_kw={'ecolor':'black', 'linewidth':2}, # error-bars colour
label=r'3')
if CHOICE == 15 and option == 0:
ax.annotate(np.round(diff_mean_1[1], 2), xy=(1.6, 0.15), xytext=(0.8, 0.122),
arrowprops=dict(facecolor='black', arrowstyle="->"), )
# -- Legend
handles, labels = ax.get_legend_handles_labels()
# print("labels: {}".format(labels))
legend = plt.legend(handles, labels,
loc='upper right',
handlelength=2,
labelspacing=0, # distance between label entries
handletextpad=0.3, # distance between label and the line representation
title='Variants',
borderaxespad=0.3, # distance between legend and the outer axes
borderpad=0.1, # padding inside legend box
)
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.8) # 0.8
# -- Title and figure settings
if distribution == 'uniform':
distribution_label = ',$uniform'
else:
distribution_label = '$'
plt.title(r'$\!\!\!\!n\!=\!{}\mathrm{{k}}, d\!=\!{}, h\!=\!{}, f\!=\!{}{}'.format(int(n / 1000), d, h, f, distribution_label))
# ax.set_xticks(range(10))
plt.grid(b=True, which='both', alpha=0.2, linestyle='solid', axis='y', linewidth=0.5) # linestyle='dashed', which='minor'
plt.xlabel(r'Max path length ($\ell_{{\mathrm{{max}}}})$', labelpad=0)
plt.ylabel(r'L2 norm', labelpad=0)
if ymin1 is None:
ymin1 = plt.ylim()[0]
ymin1 = max(ymin1, 0)
if ymax1 is None:
ymax1 = plt.ylim()[1]
plt.ylim(ymin1, ymax1)
plt.xlim(0.5,5.5)
plt.xticks([1, 2, 3, 4, 5])
plt.tick_params(
axis='x', # changes apply to the x-axis
which='both', # both major and minor ticks are affected
bottom='off', # ticks along the bottom edge are off
top='off', # ticks along the top edge are off
# labelbottom='off', # labels along the bottom edge are off
)
plt.annotate(r'$\lambda={:g}$'.format(float(scaling)), xycoords = 'axes fraction', xy=(0.5, 0.9), ha="center", va="center")
if CREATE_PDF:
plt.savefig(join(figure_directory, fig_filename), format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
frameon=None)
if SHOW_FIG1:
plt.show()
if SHOW_PDF:
os.system('{} "'.format(open_cmd[sys.platform]) + join(figure_directory, fig_filename) + '"') # shows actually created PDF
if SHOW_FIG2:
# -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1 (length {}):\n{}".format(len(df1.index), df1.head(15)))
df2 = df1.groupby(['option', 'variant', 'length']).agg \
({'diff': [np.mean, np.std, np.size], # Multiple Aggregates
'time': [np.mean, np.std],
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'diff_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(90)))
df2['length'] = df2['length'].astype(str) # transform numbers into string for later join: '.join(col).strip()'
df3 = df2.query('variant=="1"') # We only focus on variant 1 (as close to row stochastic matrix as possible)
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(n=20)))
df4 = pd.pivot_table(df3, index=['option'], columns=['length'], values=['diff_mean', 'diff_std']) # Pivot
# print("\n-- df4 (length {}):\n{}".format(len(df4.index), df4.head(30)))
df4.columns = ['_'.join(col).strip() for col in df4.columns.values] # flatten the column hierarchy, requires to have only strings
df4.reset_index(level=0, inplace=True) # get length into columns
# print("\n-- df4 (length {}):\n{}".format(len(df4.index), df4.head(30)))
# Add scaling factor for each row
option = df4['option'].values # extract the values from dataframe
scaling = scaling_vec[option] # look up the scaling factor in original list
scaling = pd.Series(scaling)
# print("scaling:\n{}".format(scaling))
df5 = df4.assign(scaling=scaling.values)
# print("\n-- df5 (length {}):\n{}".format(len(df5.index), df5.head(30)))
# Filter rows
select_rows = [i for i in range(num_options) if EC[i]] # only those values for EC being tru
df6 = df5[df5['option'].isin(select_rows)]
# print("\n-- df6 (length {}):\n{}".format(len(df6.index), df6.head(30)))
fig_filename = 'Fig_MHE_ScalingFactor_{}.pdf'.format(CHOICE)
# -- Setup figure
mpl.rcParams['backend'] = 'pdf'
mpl.rcParams['lines.linewidth'] = 3
mpl.rcParams['font.size'] = 14
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 14
mpl.rcParams['axes.edgecolor'] = '111111' # axes edge color
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['figure.figsize'] = [4, 4]
mpl.rcParams['xtick.major.pad'] = 4 # padding of tick labels: default = 4
mpl.rcParams['ytick.major.pad'] = 4 # padding of tick labels: default = 4
fig = plt.figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
# -- Extract values into columns (plotting dataframew with bars plus error lines and lines gave troubles)
scaling = df6['scaling'].values # .tolist() does not work with bar plot, requires np.array
diff_mean_1 = df6['diff_mean_1'].values
diff_mean_2 = df6['diff_mean_2'].values
diff_mean_3 = df6['diff_mean_3'].values
diff_mean_4 = df6['diff_mean_4'].values
diff_mean_5 = df6['diff_mean_5'].values
diff_std_5 = df6['diff_std_5'].values
# -- Draw the plots
p1 = ax.plot(scaling, diff_mean_1, color='black', linewidth=1, linestyle='--', label=r'$\ell_\mathrm{max} = 1$')
p2 = ax.plot(scaling, diff_mean_2, color='orange', label=r'$\ell_\mathrm{max} = 2$')
p3 = ax.plot(scaling, diff_mean_3, color='blue', label=r'$\ell_\mathrm{max} = 3$')
p4 = ax.plot(scaling, diff_mean_4, color='green', label=r'$\ell_\mathrm{max} = 4$')
p5 = ax.plot(scaling, diff_mean_5, color='red', marker='o', label=r'$\ell_\mathrm{max} = 5$')
plt.xscale('log')
upper = diff_mean_5 + diff_std_5
lower = diff_mean_5 - diff_std_5
ax.fill_between(scaling, upper, lower, facecolor='red', alpha=0.2, edgecolor='none')
# -- Title and legend
if distribution == 'uniform':
distribution_label = ',$uniform'
else:
distribution_label = '$'
plt.title(r'$\!\!\!\!n\!=\!{}\mathrm{{k}}, d\!=\!{}, h\!=\!{}, f\!=\!{}{}'.format(int(n / 1000), d, h, f, distribution_label))
handles, labels = ax.get_legend_handles_labels()
# print("labels: {}".format(labels))
legend = plt.legend(handles, labels,
loc='upper center', # 'upper right'
handlelength=2,
labelspacing=0, # distance between label entries
handletextpad=0.3, # distance between label and the line representation
# title='Variants',
borderaxespad=0.3, # distance between legend and the outer axes
borderpad=0.1, # padding inside legend box
)
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.9) # 0.8
# -- Figure settings
# ax.set_xticks(range(10))
plt.grid(b=True, which='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
plt.xlabel(r'$\lambda$', labelpad=0)
plt.ylabel(r'L$^2$ norm', labelpad=0)
if xmin2 is None:
xmin2 = plt.xlim()[0]
if xmax2 is None:
xmax2 = plt.xlim()[1]
if ymin2 is None:
ymin2 = plt.ylim()[0]
ymin2 = max(ymin2, 0)
if ymax2 is None:
ymax2 = plt.ylim()[1]
plt.xlim(xmin2, xmax2)
plt.ylim(ymin2, ymax2)
plt.tick_params(
axis='x', # changes apply to the x-axis
which='both', # both major and minor ticks are affected
# bottom='off', # ticks along the bottom edge are off
top='off', # ticks along the top edge are off
right='off', # ticks along the top edge are off
# labelbottom='off', # labels along the bottom edge are off
)
if CREATE_PDF:
plt.savefig(join(figure_directory, fig_filename), format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
frameon=None)
if SHOW_FIG2:
plt.show()
if SHOW_PDF:
os.system('{} "'.format(open_cmd[sys.platform]) + join(figure_directory, fig_filename) + '"') # shows actually created PDF
def test_H_observed():
"""Illustrate H_observed"""
print(
"\n\n-- test_H_observed(): 'H_observed', uses: 'planted_distribution_model_H' --"
)
# --- Parameters for graph
n = 3000
a = 1
h = 8
d = 2
k = 3
distribution = 'uniform'
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
# --- Create graph
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(
seed=RANDOMSEED
) # seeds the actually used numpy random generator; both are used and thus needed
W, Xd = planted_distribution_model_H(n,
alpha=alpha0,
H=H0,
d_out=d,
distribution=distribution,
exponent=None,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
# --- Print first rows of matrices
distance = 8
print("First rows of powers of H0:")
for k in range(1, distance + 1):
print("{}: {}".format(k, np.linalg.matrix_power(H0, k)[0]))
H_vec = H_observed(W, X0, distance=distance, NB=False)
H_vec_EC = H_observed(W, X0, distance=distance, NB=True)
print("First rows of H_vec (without NB)")
for i, H in enumerate(H_vec): # skip the first entry in list
print("{}: {}".format(i + 1, H[0]))
print("First rows of H_vec (with NB)")
for i, H in enumerate(H_vec_EC):
print("{}: {}".format(i + 1, H[0]))
# --- Print just the top entry in first row (easier to compare)
h_vec = []
for k in range(1, distance + 1):
h_vec.append(np.max(np.linalg.matrix_power(H0, k)[0]))
hrow_vec = []
for H in H_vec:
hrow_vec.append(np.max(H[0]))
hrow_EC_vec = []
for H in H_vec_EC:
hrow_EC_vec.append(np.max(H[0]))
print("\nh_vec:\n{}".format(np.around(h_vec, 3)))
print("hrow_vec (estimated without NB):\n{}".format(np.around(hrow_vec,
3)))
print("hrow_EC_vec (estimated with NB):\n{}".format(
np.around(hrow_EC_vec, 3)))
def run(choice,
create_data=False,
add_data=False,
show_plot=False,
create_pdf=False,
show_pdf=False):
global n
global d
global rep_SameGraph
global FILENAMEZ
global csv_filename
global initial_h0
global exponent
global length
global variant
global alpha_vec
global beta_vec
global gamma_vec
global s_vec
global clip_on_vec
global numMaxIt_vec
# Plotting Parameters
global xtick_lab
global xtick_labels
global ytick_lab
global xmax
global xmin
global ymin
global ymax
global labels
global facecolor_vec
global draw_std_vec
global linestyle_vec
global linewidth_vec
global marker_vec
global markersize_vec
global legend_location
global option_vec
global learning_method_vec
global Macro_Accuracy
global EC
global constraints
global weight_vec
global randomize_vec
global k
global err
global avoidNeighbors
global convergencePercentage_W
global stratified
global gradient
global doubly_stochastic
global num_restarts
global numberOfSplits
global H_heuristic
global select_lambda_vec
global lambda_vec
global f_vec
global H0c
# -- Setup
CHOICE = choice
#300 Prop37, 400 MovieLens, 500 Yelp, 600 Flickr, 700 DBLP, 800 Enron
experiments = [CHOICE]
CREATE_DATA = create_data
ADD_DATA = add_data
SHOW_PDF = show_pdf
SHOW_PLOT = show_plot
CREATE_PDF = create_pdf
SHOW_FIG = SHOW_PLOT or SHOW_PDF or CREATE_PDF
STD_FILL = True
TIMING = False
CALCULATE_DATA_STATISTICS = False
# -- Default Graph parameters
rep_SameGraph = 10 # iterations on same graph
initial_h0 = None # initial vector to start finding optimal H
exponent = -0.3
length = 5
variant = 1
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
clip_on_vec = [True] * 10
numMaxIt_vec = [10] * 10
# Plotting Parameters
xtick_lab = [0.001, 0.01, 0.1, 1]
xtick_labels = ['0.1\%', '1\%', '10\%', '100\%']
ytick_lab = np.arange(0, 1.1, 0.1)
xmax = 1
xmin = 0.0001
ymin = 0.3
ymax = 0.7
labels = ['GS', 'LCE', 'MCE', 'DCE', 'DCEr']
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974",
"#64B5CD"
]
draw_std_vec = [False] * 4 + [True]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [4, 4, 2, 1, 2, 2]
marker_vec = [None, 'o', 'x', '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8]
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
Macro_Accuracy = False
EC = True # Non-backtracking for learning
constraints = True # True
weight_vec = [None] * 3 + [10, 10] * 2
randomize_vec = [False] * 4 + [True] * 2
k = 3
err = 0
avoidNeighbors = False
convergencePercentage_W = None
stratified = True
gradient = True
doubly_stochastic = True
num_restarts = None
raw_std_vec = range(10)
numberOfSplits = 1
select_lambda_vec = [False] * 20
lambda_vec = None
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
FILENAMEZ = ""
legend_location = ""
fig_label = ""
H_heuristic = ""
def choose(choice):
global n
global d
global rep_SameGraph
global FILENAMEZ
global initial_h0
global exponent
global length
global variant
global alpha_vec
global beta_vec
global gamma_vec
global s_vec
global clip_on_vec
global numMaxIt_vec
# Plotting Parameters
global xtick_lab
global xtick_labels
global ytick_lab
global xmax
global xmin
global ymin
global ymax
global labels
global facecolor_vec
global draw_std_vec
global linestyle_vec
global linewidth_vec
global marker_vec
global markersize_vec
global legend_location
global option_vec
global learning_method_vec
global Macro_Accuracy
global EC
global constraints
global weight_vec
global randomize_vec
global k
global err
global avoidNeighbors
global convergencePercentage_W
global stratified
global gradient
global doubly_stochastic
global num_restarts
global numberOfSplits
global H_heuristic
global select_lambda_vec
global lambda_vec
global f_vec
# -- Default Graph parameters
if choice == 0:
None
elif choice == 304: ## with varying weights
FILENAMEZ = 'prop37'
Macro_Accuracy = True
gradient = True
fig_label = 'Prop37'
legend_location = 'lower right'
n = 62000
d = 34.8
select_lambda_vec = [False] * 5
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
elif choice == 305: # DCEr Only experiment
choose(605)
choose(304)
select_lambda_vec = [False] * 6
elif choice == 306:
choose(304)
select_lambda_vec = [False] * 3 + [True] * 3
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
learning_method_vec.append('Holdout')
labels.append('Holdout')
elif choice == 307: # heuristic comparison
choose(304)
select_lambda_vec = [False] * 3 + [True] * 3
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
learning_method_vec.append('Heuristic')
labels.append('Heuristic')
H_heuristic = np.array([[.476, .0476, .476], [.476, .0476, .476],
[.476, .476, .0476]])
# -- MovieLens dataset
elif choice == 401:
FILENAMEZ = 'movielens'
Macro_Accuracy = True
gradient = True
fig_label = 'MovieLens'
legend_location = 'upper left'
n = 26850
d = 25.0832029795
elif choice == 402:
choose(401)
select_lambda_vec = [False] * 3 + [
True
] * 3 # allow to choose lambda for different f in f_vec
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
elif choice == 403:
choose(402)
ymin = 0.3
ymax = 1.0
learning_method_vec.append('Holdout')
labels.append('Holdout')
elif choice == 404:
choose(401)
select_lambda_vec = [
True
] * 3 # allow to choose lambda for different f in f_vec
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
labels = ['GS', 'DCEr', 'Homophily']
facecolor_vec = ['black', "#C44E52", "#64B5CD"]
draw_std_vec = [False, True, False]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [4, 2, 2, 2, 2]
marker_vec = [None, '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8]
weight_vec = [None, 10, None]
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
randomize_vec = [False, True, False]
learning_method_vec = ['GT', 'DHE'] #TODO
elif choice == 405: # DCEr ONLY experiment
choose(605)
choose(401)
learning_method_vec += ['Holdout']
labels += ['Holdout']
elif choice == 406: # comparison with a static heuristic matrix
choose(402)
learning_method_vec += ['Heuristic']
labels += ['Heuristic']
H_heuristic = np.array([[.0476, .476, .476], [.476, .0476, .476],
[.476, .476, .0476]])
elif choice == 407:
choose(402)
ymin = 0.3
ymax = 1.0
lambda_vec = [1] * 21 # same length as f_vec
elif choice == 408:
choose(402)
ymin = 0.3
ymax = 1.0
lambda_vec = [10] * 21 # same length as f_vec
# DO NOT RUN WITH CREATE_DATA=True, if you do please restore the data from
# data/sigmod-movielens-fig.csv
elif choice == 409:
choose(402)
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#8172B2", "#C44E52",
"#C44E52", "#CCB974", "#64B5CD"
]
labels = [
'GS', 'LCE', 'MCE', 'DCE1', 'DCE10', 'DCEr1', 'DCEr10',
'Holdout'
]
draw_std_vec = [False] * 5 + [True] * 2 + [False]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [2, 2, 2, 2, 2, 2, 2, 2]
marker_vec = [None, 'o', 'x', 's', 'p', '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8, 8]
option_vec = [
'opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6', 'opt7', 'opt8'
]
legend_location = 'upper left'
ymin = 0.3
ymax = 1.0
lambda_vec = [10] * 21 # same length as f_vec
# -- Yelp dataset
elif choice == 501:
FILENAMEZ = 'yelp'
Macro_Accuracy = True
weight_vec = [None] * 3 + [10, 10]
gradient = True
ymin = 0.1
ymax = 0.75
fig_label = 'Yelp'
legend_location = 'upper left'
n = 4301900 # for figure
d = 6.56 # for figure
# -- Flickr dataset
#elif choice == 601:
# FILENAMEZ = 'flickr'
# Macro_Accuracy = True
# fig_label = 'Flickr'
# legend_location = 'lower right'
# ymin = 0.3
# ymax = 0.7
# n = 2007369
# d = 18.1
#elif choice == 602: ## with varying weights
# choose(601)
# select_lambda_vec = [False] * 4 + [True]*2 # allow to choose lambda for different f in f_vec
# f_vec = [0.9 * pow(0.1, 1 / 5) ** x for x in range(21)]
# lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
#elif choice == 603: ## with varying weights
# choose(602)
# select_lambda_vec = [False] * 3 + [True] * 2 # allow to choose lambda for different f in f_vec
# # lambda_vec = [1] * 5 + [5] * 5 + [10] * 5 + [1] * 6 # same length as f_vec
#elif choice == 604: ## with weight = 1
# choose(603)
# lambda_vec = [0.5] * 21 # same length as f_vec
# -- Flickr dataset
elif choice == 601:
FILENAMEZ = 'flickr'
Macro_Accuracy = True
fig_label = 'Flickr'
legend_location = 'lower right'
n = 2007369
d = 18.1
elif choice == 602: ## with varying weights
choose(601)
select_lambda_vec = [False] * 4 + [
True
] # allow to choose lambda for different f in f_vec
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
elif choice == 603: ## with varying weights
choose(602)
select_lambda_vec = [False] * 3 + [
True
] * 2 # allow to choose lambda for different f in f_vec
# lambda_vec = [1] * 5 + [5] * 5 + [10] * 5 + [1] * 6 # same length as f_vec
elif choice == 604: ## with weight = 1
draw_std_vec = [4]
choose(603)
lambda_vec = [0.5] * 21 # same length as f_vec
elif choice == 605:
choose(601)
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974",
"#64B5CD", 'orange'
]
draw_std_vec = [False] + [True] * 10
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [3] * 10
marker_vec = [None, 'o', 'x', '^', 'v', '+', 'o', 'x']
markersize_vec = [0] + [8] * 10
randomize_vec = [True] * 8
option_vec = [
'opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6', 'opt7', 'opt8'
]
learning_method_vec = [
'GT', 'DHE', 'DHE', 'DHE', 'DHE', 'DHE', 'DHE'
]
select_lambda_vec = [False] * 8
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
weight_vec = [0, 0, 1, 2, 5, 10, 15]
labels = ['GT'] + [
i + ' {}'.format(weight_vec[ix])
for ix, i in enumerate(['DCEr'] * 6)
]
elif choice == 606: # heuristic experiment
choose(602)
labels.append('Heuristic')
learning_method_vec.append('Heuristic')
H_heuristic = np.array([[.0476, .476, .476], [.476, .0476, .476],
[.476, .476, .0476]])
# -- DBLP dataset
elif choice == 701:
FILENAMEZ = 'dblp'
Macro_Accuracy = True
ymin = 0.2
ymax = 0.5
fig_label = 'DBLP'
legend_location = 'lower right'
n = 2241258 # for figure
d = 26.11 # for figure
# -- ENRON dataset
elif choice == 801:
FILENAMEZ = 'enron'
Macro_Accuracy = True
ymin = 0.3
ymax = 0.75
fig_label = 'Enron'
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
legend_location = 'upper left'
n = 46463 # for figures
d = 23.4 # for figures
elif choice == 802: ### WITH ADAPTIVE WEIGHTS
choose(801)
select_lambda_vec = [False] * 4 + [
True
] * 2 # allow to choose lambda for different f in f_vec
f_vec = [0.9 * pow(0.1, 1 / 5)**x for x in range(21)]
lambda_vec = [1] * 11 + [10] * 10 # same length as f_vec
elif choice == 803: ### WITH ADAPTIVE WEIGHTS
choose(802)
lambda_vec = [1] * 5 + [5] * 5 + [10] * 5 + [
1
] * 6 # same length as f_vec
elif choice == 804:
choose(803)
elif choice == 805:
choose(605)
choose(801)
#learning_method_vec += ['Holdout']
#labels += ['Holdout']
elif choice == 806: # Heuristic experiment
choose(802)
learning_method_vec += ['Heuristic']
labels += ['Heuristic']
H_heuristic = np.array([[0.76, 0.08, 0.08, 0.08],
[0.08, 0.08, 0.76, 0.08],
[0.08, 0.76, 0.08, 0.76],
[0.08, 0.08, 0.76, 0.08]])
elif choice == 821:
FILENAMEZ = 'enron'
Macro_Accuracy = True
constraints = True # True
gradient = True
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
weight_vec = [None] * 3 + [0.2, 0.2]
randomize_vec = [False] * 4 + [True]
xmin = 0.0001
ymin = 0.0
ymax = 0.7
labels = ['GS', 'LCE', 'MCE', 'DCE', 'DCE r']
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974",
"#64B5CD"
]
draw_std_vec = [4]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [4, 4, 2, 1, 2]
marker_vec = [None, 'o', 'x', '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8]
fig_label = 'Enron'
legend_location = 'lower right'
n = 46463 # for figures
d = 23.4 # for figures
alpha = 0.0
beta = 0.0
gamma = 0.0
s = 0.5
numMaxIt = 10
select_lambda_vec = [False] * 3 + [True] * 2
lambda_vec = [0.2] * 13 + [10] * 8 # same length as f_vec
# -- Cora dataset
elif choice == 901:
FILENAMEZ = 'cora'
Macro_Accuracy = True
constraints = True # True
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
weight_vec = [None] * 3 + [10, 10]
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True]
gradient = True
xmin = 0.001
ymin = 0.0
ymax = 0.9
labels = ['GT', 'LCE', 'MCE', 'DCE', 'DCE r']
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974",
"#64B5CD"
]
draw_std_vec = [4]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [4, 4, 2, 1, 2]
marker_vec = [None, 'o', 'x', '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8]
fig_label = 'Cora'
legend_location = 'lower right'
n = 2708
d = 7.8
# -- Citeseer dataset
elif CHOICE == 1001:
FILENAMEZ = 'citeseer'
Macro_Accuracy = True
constraints = True # True
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
weight_vec = [None] * 3 + [10, 10]
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True]
gradient = True
xmin = 0.001
ymin = 0.0
ymax = 0.75
labels = ['GT', 'LCE', 'MCE', 'DCE', 'DCE r']
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974",
"#64B5CD"
]
draw_std_vec = [4]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [4, 4, 2, 1, 2]
marker_vec = [None, 'o', 'x', '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8]
fig_label = 'Citeseer'
legend_location = 'lower right'
n = 3312
d = 5.6
elif CHOICE == 1101:
FILENAMEZ = 'hep-th'
Macro_Accuracy = True
constraints = True # True
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
weight_vec = [None] * 3 + [10, 10]
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True]
gradient = True
xmin = 0.0001
ymin = 0.0
ymax = 0.1
labels = ['GT', 'LCE', 'MCE', 'DCE', 'DCE r']
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974",
"#64B5CD"
]
draw_std_vec = [4]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [4, 4, 2, 1, 2]
marker_vec = [None, 'o', 'x', '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8]
fig_label = 'Hep-th'
legend_location = 'lower right'
n = 27770
d = 5.6
elif choice == 1102:
choose(1101)
Macro_Accuracy = True
elif CHOICE == 1204:
FILENAMEZ = 'pokec-gender'
Macro_Accuracy = True
constraints = True # True
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
weight_vec = [None] * 3 + [10, 10]
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True]
gradient = True
xmin = 0.000015
ymin = 0.0
ymax = 0.75
labels = ['GT', 'LCE', 'MCE', 'DCE', 'DCE r']
facecolor_vec = [
'black', "#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974",
"#64B5CD"
]
draw_std_vec = [0, 3, 4, 4, 4, 4]
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [4, 4, 2, 1, 2]
marker_vec = [None, 'o', 'x', '^', 'v', '+']
markersize_vec = [0, 8, 8, 8, 8, 8, 8]
fig_label = 'Pokec-Gender'
legend_location = 'lower right'
n = 1632803
d = 54.6
else:
raise Warning("Incorrect choice!")
for choice in experiments:
choose(choice)
filename = 'Fig_End-to-End_accuracy_realData_{}_{}'.format(
choice, FILENAMEZ)
csv_filename = '{}.csv'.format(filename)
header = [
'currenttime', 'method', 'f', 'accuracy', 'precision', 'recall',
'learntime', 'proptime'
]
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename),
header,
append=False)
# print("choice: {}".format(choice))
# --- print data statistics
if CALCULATE_DATA_STATISTICS:
Xd, W = load_Xd_W_from_csv(
join(realDataDir, FILENAMEZ) + '-classes.csv',
join(realDataDir, FILENAMEZ) + '-neighbors.csv')
X0 = from_dictionary_beliefs(Xd)
n = len(Xd.keys())
d = (len(W.nonzero()[0]) * 2) / n
k = len(X0[0])
print("FILENAMEZ:", FILENAMEZ)
print("k:", k)
print("n:", n)
print("d:", d)
# -- Graph statistics
n_vec = calculate_nVec_from_Xd(Xd)
print("n_vec:\n", n_vec)
d_vec = calculate_average_outdegree_from_graph(W, Xd=Xd)
print("d_vec:\n", d_vec)
P = calculate_Ptot_from_graph(W, Xd)
print("P:\n", P)
for i in range(k):
Phi = calculate_degree_correlation(W, X0, i, NB=True)
print("Degree Correlation, Class {}:\n{}".format(i, Phi))
# -- Various compatibilities
H0 = estimateH(X0,
W,
method='MHE',
variant=1,
distance=1,
EC=EC,
weights=1,
randomize=False,
constraints=True,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
print("H0 w/ constraints:\n", np.round(H0, 2))
#raw_input() # Why?
H2 = estimateH(X0,
W,
method='MHE',
variant=1,
distance=1,
EC=EC,
weights=1,
randomize=False,
constraints=True,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
H4 = estimateH(X0,
W,
method='DHE',
variant=1,
distance=1,
EC=EC,
weights=2,
randomize=False,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
H5 = estimateH(X0,
W,
method='DHE',
variant=1,
distance=1,
EC=EC,
weights=2,
randomize=False,
constraints=True,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
H6 = estimateH(X0,
W,
method='DHE',
variant=1,
distance=2,
EC=EC,
weights=10,
randomize=False,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
H7 = estimateH(X0,
W,
method='DHE',
variant=1,
distance=2,
EC=EC,
weights=10,
randomize=False,
constraints=True,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
print()
# print("H MCE w/o constraints:\n", np.round(H0, 3))
print("H MCE w/ constraints:\n", np.round(H2, 3))
# print("H DCE 2 w/o constraints:\n", np.round(H4, 3))
print("H DCE 2 w/ constraints:\n", np.round(H5, 3))
# print("H DCE 10 w/o constraints:\n", np.round(H6, 3))
print("H DCE 20 w/ constraints:\n", np.round(H7, 3))
print()
H_row_vec = H_observed(W, X0, 3, NB=True, variant=1)
print("H_est_1:\n", np.round(H_row_vec[0], 3))
print("H_est_2:\n", np.round(H_row_vec[1], 3))
print("H_est_3:\n", np.round(H_row_vec[2], 3))
# --- Create data
if CREATE_DATA or ADD_DATA:
Xd, W = load_Xd_W_from_csv(
join(realDataDir, FILENAMEZ) + '-classes.csv',
join(realDataDir, FILENAMEZ) + '-neighbors.csv')
X0 = from_dictionary_beliefs(Xd)
n = len(Xd.keys()) ## number of nodes in graph
k = len(X0[0])
d = (len(W.nonzero()[0]) * 2) / n
#print(n)
#print(d)
#print("contraint = {}".format(constraints))
#print('select lambda: {}'.format(len(select_lambda_vec)))
#print('learning method: {}'.format(len(learning_method_vec)))
#print('alpha: {}'.format(len(alpha_vec)))
#print('beta: {}'.format(len(beta_vec)))
#print('gamma: {}'.format(len(gamma_vec)))
#print('s: {}'.format(len(s_vec)))
#print('maxit: {}'.format(len(numMaxIt_vec)))
#print('weight: {}'.format(len(weight_vec)))
#print('randomize: {}'.format(len(randomize_vec)))
# --- Calculating True Compatibility matrix
H0 = estimateH(X0,
W,
method='MHE',
variant=1,
distance=1,
EC=EC,
weights=1,
randomize=False,
constraints=constraints,
gradient=gradient,
doubly_stochastic=doubly_stochastic)
# print(H0)
H0c = to_centering_beliefs(H0)
num_results = len(f_vec) * len(learning_method_vec) * rep_SameGraph
# Starts a thread pool with at least 2 threads, and a lot more if you happen to be on a supercomputer
pool = multiprocessing.Pool(max(2,
multiprocessing.cpu_count() - 4))
f_processes = f_vec * rep_SameGraph
workers = []
results = [(X0, W, f, ix)
for ix, f in enumerate(f_vec)] * rep_SameGraph
# print('Expected results: {}'.format(num_results))
try: # hacky fix due to a bug in 2.7 multiprocessing
# Distribute work for evaluating accuracy over the thread pool using
# a hacky method due to python 2.7 multiprocessing not being fully
# featured
pool.map_async(multi_run_wrapper, results).get(num_results * 2)
except multiprocessing.TimeoutError as e:
continue
finally:
pool.close()
pool.join()
# -- Read data for all options and plot
df1 = pd.read_csv(join(data_directory, csv_filename))
acc_filename = '{}_accuracy_plot.pdf'.format(filename)
pr_filename = '{}_PR_plot.pdf'.format(filename)
if TIMING:
print('=== {} Timing Results ==='.format(FILENAMEZ))
print('Prop Time:\navg: {}\nstddev: {}'.format(
np.average(df1['proptime'].values),
np.std(df1['proptime'].values)))
for learning_method in labels:
rs = df1.loc[df1["method"] == learning_method]
avg = np.average(rs['learntime'])
std = np.std(rs['learntime'])
print('{} Learn Time:\navg: {}\nstd: {}'.format(
learning_method, avg, std))
sslhv.plot(df1,
join(figure_directory, acc_filename),
n=n,
d=d,
k=k,
labels=labels,
dataset=FILENAMEZ,
line_styles=linestyle_vec,
xmin=xmin,
ymin=ymin,
xmax=xmax,
ymax=ymax,
marker_sizes=markersize_vec,
draw_stds=draw_std_vec,
markers=marker_vec,
line_colors=facecolor_vec,
line_widths=linewidth_vec,
legend_location=legend_location,
show=SHOW_PDF,
save=CREATE_PDF,
show_plot=SHOW_PLOT)
def run(choice,
variant,
create_data=False,
show_plot=False,
create_pdf=False,
show_pdf=False):
"""main parameterized method to produce all figures.
Can be run from external jupyther notebook or method to produce all figures in PDF
"""
# %% -- Setup
CREATE_DATA = create_data
CHOICE = choice
VARIANT = variant
SHOW_PLOT = show_plot
CREATE_PDF = create_pdf
SHOW_PDF = show_pdf
SHOW_TITLE = True
LEGEND_MATCH_COLORS = False
SHOW_DISTRIBUTION_IN_TITLE = True
SHOW_BACKTRACK_ESTIMATE = True
SHOW_NONBACKTRACK_ESTIMATE = True
plot_colors = ['darkgreen', 'darkorange', 'blue']
label_vec = [
r'$\mathbf{H}^{\ell}\,\,\,\,$', r'$\mathbf{\hat P}^{(\ell)}$',
r'$\mathbf{\hat P}_{\mathrm{NB}}^{(\ell)}$'
]
csv_filename = 'Fig_Backtracking_Advantage_{}.csv'.format(CHOICE)
fig_filename = 'Fig_Backtracking_Advantage_{}-{}.pdf'.format(
CHOICE, VARIANT)
header = [
'currenttime',
'choice', # H, Hrow, HrowEC
'l',
'valueH', # maximal values in first row of H
'valueM'
] # average value across entries in M
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename),
header,
append=False)
# %% -- Default parameters
ymin = 0.3
ymax = 1
exponent = None
# %% -- CHOICES and VARIANTS
if CHOICE == 1: # n=1000, shows NB to be slight lower for l=2: probably due to sampling issues (d=3, thus very few points available)
n = 1000
h = 8
d = 3
f = 0.1
distribution = 'uniform'
rep = 10000
length = 8
elif CHOICE == 2:
n = 1000
h = 8
d = 10
f = 0.1
distribution = 'uniform'
rep = 10000
length = 8
elif CHOICE == 3: # nice: shows nicely that difference is even bigger for smaller h
n = 1000
h = 3
d = 10
f = 0.1
distribution = 'uniform'
rep = 10000
length = 8
ymax = 0.8
elif CHOICE == 4:
n = 10000
h = 3
d = 10
f = 0.1
distribution = 'uniform'
rep = 100
length = 8
ymin = 0.333
ymax = 0.65
elif CHOICE == 5:
n = 10000
h = 3
d = 3
f = 0.1
distribution = 'uniform'
rep = 1000
length = 8
elif CHOICE == 6: # n=1000, the powerlaw problem with small graphs and high exponent
n = 1000
h = 8
d = 3
f = 0.1
distribution = 'powerlaw'
exponent = -0.5
rep = 10000
length = 8
elif CHOICE == 7:
n = 10000
h = 8
d = 3
f = 0.1
distribution = 'uniform'
rep = 1000
length = 8
# ymin = 0.4
ymax = 1
elif CHOICE == 8:
n = 10000
h = 8
d = 10
f = 0.1
distribution = 'uniform'
rep = 1000
length = 8
# ymin = 0.4
ymax = 1
elif CHOICE == 9: # shows lower NB due to problem with sampling from high powerlaw -0.5
n = 10000
h = 8
d = 10
f = 0.1
distribution = 'powerlaw'
exponent = -0.5
rep = 1000
length = 8
elif CHOICE == 10:
n = 10000
h = 8
d = 3
f = 0.1
distribution = 'powerlaw'
exponent = -0.5
rep = 1000
length = 8
elif CHOICE == 11: # problem: shows that NB is too low (probably because of problem with sampling from -0.5 factor)
n = 1000
h = 8
d = 10
f = 0.1
distribution = 'powerlaw'
exponent = -0.5
rep = 1000
length = 8
elif CHOICE == 12: # problem: shows no problem with NB (probably because no problem with sampling from -0.2 factor)
n = 1000
h = 8
d = 10
f = 0.1
distribution = 'powerlaw'
exponent = -0.2
rep = 1000
length = 8
elif CHOICE == 20:
n = 10000
h = 3
d = 10
f = 0.1
distribution = 'powerlaw'
exponent = -0.3
rep = 1000
length = 8
ymin = 0.333
ymax = 0.65
elif CHOICE == 21: # originally used before color change
n = 10000
h = 3
d = 25
f = 0.1
distribution = 'powerlaw'
exponent = -0.3
rep = 1000
length = 8
ymin = 0.333
ymax = 0.65
if VARIANT == 1:
SHOW_TITLE = False
plot_colors = ['red', 'blue', 'darkorange']
label_vec = [r'$\mathbf{H}^{\ell}\quad\quad$', 'naive', 'better']
LEGEND_MATCH_COLORS = True
if VARIANT == 2:
SHOW_TITLE = False
plot_colors = ['red', 'blue', 'darkorange']
label_vec = [r'$\mathbf{H}^{\ell}\quad\quad$', 'naive', 'better']
SHOW_NONBACKTRACK_ESTIMATE = False
LEGEND_MATCH_COLORS = True
if VARIANT == 3:
SHOW_TITLE = False
plot_colors = ['red', 'blue', 'darkorange']
label_vec = [r'$\mathbf{H}^{\ell}\quad\quad$', 'naive', 'better']
SHOW_BACKTRACK_ESTIMATE = False
SHOW_NONBACKTRACK_ESTIMATE = False
LEGEND_MATCH_COLORS = True
if VARIANT == 4:
plot_colors = ['red', 'blue', 'darkorange']
LEGEND_MATCH_COLORS = True
elif CHOICE == 25:
n = 10000
h = 8
d = 5
f = 0.1
distribution = 'uniform'
rep = 1000
length = 8
elif CHOICE == 26:
n = 10000
h = 8
d = 25
f = 0.1
distribution = 'uniform'
rep = 1000
length = 8
ymax = 0.9
ymin = 0.4
elif CHOICE == 27:
n = 10000
h = 8
d = 10
f = 0.1
distribution = 'powerlaw'
exponent = -0.3
rep = 1000
length = 8
ymax = 0.9
ymin = 0.33
elif CHOICE == 31:
n = 10000
h = 3
d = 10
f = 0.1
distribution = 'uniform'
length = 8
ymin = 0.333
ymax = 0.65
SHOW_DISTRIBUTION_IN_TITLE = False
plot_colors = ['red', 'blue', 'darkorange']
LEGEND_MATCH_COLORS = True
if VARIANT == 0:
rep = 1000
if VARIANT == 1:
rep = 20
else:
raise Warning("Incorrect choice!")
k = 3
a = 1
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(
seed=RANDOMSEED
) # seeds the actually used numpy random generator; both are used and thus needed
# print("CHOICE: {}".format(CHOICE))
# %% -- Create data
if CREATE_DATA:
# Calculations H
print("Max entry of first rows of powers of H0:")
for l in range(1, length + 1):
valueH = np.max(np.linalg.matrix_power(H0, l)[0])
tuple = [str(datetime.datetime.now())]
text = ['H', l, valueH, '']
text = np.asarray(text) # without np, entries get ugly format
tuple.extend(text)
print("{}: {}".format(l, valueH))
save_csv_record(join(data_directory, csv_filename), tuple)
# Calculations Hrow and HrowEC
for r in range(rep):
print('Repetition {}'.format(r))
# Create graph
start = time.time()
W, Xd = planted_distribution_model_H(
n,
alpha=alpha0,
H=H0,
d_out=
d, # notice that for undirected graphs, actual degree = 2*d
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
X1, ind = replace_fraction_of_rows(X0, 1 - f)
time_calc = time.time() - start
# print("\nTime for graph:{}".format(time_calc))
print("Average outdegree: {}".format(
calculate_average_outdegree_from_graph(W)))
# Calculate H_vec and M_vec versions (M_vec to calculate the average number of entries in M)
H_vec = H_observed(W, X1, distance=length, NB=False, variant=1)
H_vec_EC = H_observed(W, X1, distance=length, NB=True, variant=1)
M_vec = M_observed(W, X1, distance=length, NB=False)
M_vec_EC = M_observed(W, X1, distance=length, NB=True)
# Calculation H_vec
# print("Max entry of first rows of H_vec")
for l, H in enumerate(H_vec):
valueH = H[0][
(l + 1) %
2] # better than 'value = np.max(H[0])', otherwise sometimes chooses another higher entry -> biased estimate
valueM = np.average(M_vec[l + 1])
# print(M_vec[l+1])
# print(valueM)
tuple = [str(datetime.datetime.now())]
text = ['Hrow', l + 1, valueH, valueM]
text = np.asarray(text) # without np, entries get ugly format
tuple.extend(text)
# print("{}: {}".format(l + 1, value))
save_csv_record(join(data_directory, csv_filename), tuple)
# Calculation H_vec_EC
# print("Max entry of first rows of H_vec_EC")
for l, H in enumerate(H_vec_EC):
valueH = H[0][(l + 1) % 2]
valueM = np.average(M_vec_EC[l + 1])
# print(M_vec_EC[l+1])
# print(valueM)
tuple = [str(datetime.datetime.now())]
text = ['HrowEC', l + 1, valueH, valueM]
text = np.asarray(text) # without np, entries get ugly format
tuple.extend(text)
# print("{}: {}".format(l + 1, value))
save_csv_record(join(data_directory, csv_filename), tuple)
#%% -- Read, aggregate, and pivot data
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1 (length {}):\n{}".format(len(df1.index), df1.head(15)))
df2 = df1.groupby(['choice', 'l']).agg \
({'valueH': [np.mean, np.std, np.size], # Multiple Aggregates
'valueM': [np.mean],
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values
] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'valueH_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(30)))
df3 = pd.pivot_table(df2,
index=['l'],
columns=['choice'],
values=['valueH_mean', 'valueH_std',
'valueM_mean']) # Pivot
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
df3.columns = ['_'.join(col).strip() for col in df3.columns.values
] # flatten the column hierarchy
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
# df3.drop(['valueM_mean_H', 'valueH_std_H'], axis=1, inplace=True)
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
df3.reset_index(level=0, inplace=True) # get l into columns
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
#%% -- Setup figure
mpl.rcParams['backend'] = 'pdf'
mpl.rcParams['lines.linewidth'] = 3
mpl.rcParams['font.size'] = 16
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 20
mpl.rcParams['axes.edgecolor'] = '111111' # axes edge color
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['figure.figsize'] = [4, 4]
mpl.rcParams['xtick.major.pad'] = 4 # padding of tick labels: default = 4
mpl.rcParams['ytick.major.pad'] = 4 # padding of tick labels: default = 4
fig = plt.figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
#%% -- Extract values into columns (plotting dataframew with bars plus error lines and lines gave troubles)
l_vec = df3['l'].values # .tolist() does not work with bar plot
mean_H_vec = df3['valueH_mean_H'].values
mean_Hrow_vec = df3['valueH_mean_Hrow'].values
mean_Hrow_vecEC = df3['valueH_mean_HrowEC'].values
std_Hrow_vec = df3['valueH_std_Hrow'].values
std_Hrow_vecEC = df3['valueH_std_HrowEC'].values
#%% -- Draw the plot and annotate
width = 0.3 # the width of the bars
if SHOW_BACKTRACK_ESTIMATE:
left_vec = l_vec
if SHOW_NONBACKTRACK_ESTIMATE:
left_vec = left_vec - width
bar1 = ax.bar(
left_vec,
mean_Hrow_vec,
width,
color=plot_colors[1],
yerr=std_Hrow_vec,
error_kw={
'ecolor': 'black',
'linewidth': 2
}, # error-bars colour
label=label_vec[1])
if SHOW_NONBACKTRACK_ESTIMATE:
bar2 = ax.bar(
l_vec,
mean_Hrow_vecEC,
width,
color=plot_colors[2],
yerr=std_Hrow_vecEC,
error_kw={
'ecolor': 'black',
'linewidth': 2
}, # error-bars colour
label=label_vec[2])
gt = ax.plot(l_vec,
mean_H_vec,
color=plot_colors[0],
linestyle='solid',
linewidth=2,
marker='o',
markersize=10,
markeredgewidth=2,
markerfacecolor='None',
markeredgecolor=plot_colors[0],
label=label_vec[0])
if CHOICE == 4 or CHOICE == 20:
ax.annotate(
np.round(mean_Hrow_vec[1], 2),
xy=(2.15, 0.65),
xytext=(2.1, 0.60),
arrowprops=dict(facecolor='black', arrowstyle="->"),
)
#%% -- Legend
if distribution == 'uniform' and SHOW_DISTRIBUTION_IN_TITLE:
distribution_label = ',$uniform'
else:
distribution_label = '$'
if SHOW_TITLE:
plt.title(
r'$\!\!\!\!n\!=\!{}\mathrm{{k}}, d\!=\!{}, h\!=\!{}, f\!=\!{}{}'.
format(int(n / 1000), 2 * d, h, f, distribution_label
)) # notice that actual d is double than in one direction
handles, labels = ax.get_legend_handles_labels()
legend = plt.legend(
handles,
labels,
loc='upper right',
handlelength=1.5,
labelspacing=0, # distance between label entries
handletextpad=0.3, # distance between label and the line representation
# title='Iterations'
borderaxespad=0.1, # distance between legend and the outer axes
borderpad=0.1, # padding inside legend box
numpoints=1, # put the marker only once
)
if LEGEND_MATCH_COLORS: # TODO: how to get back the nicer line spacing defined in legend above after changing the legend text colors
legend.get_texts()[0].set_color(plot_colors[0])
if SHOW_BACKTRACK_ESTIMATE:
legend.get_texts()[1].set_color(plot_colors[1])
if SHOW_NONBACKTRACK_ESTIMATE:
legend.get_texts()[2].set_color(plot_colors[2])
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.8) # 0.8
# %% -- Figure settings & plot
ax.set_xticks(range(10))
plt.grid(b=True,
which='both',
alpha=0.2,
linestyle='solid',
axis='y',
linewidth=0.5) # linestyle='dashed', which='minor'
plt.xlabel(r'Path length ($\ell$)', labelpad=0)
plt.ylim(ymin, ymax) # placed after yticks
plt.xlim(0.5, 5.5)
plt.tick_params(
axis='x', # changes apply to the x-axis
which='both', # both major and minor ticks are affected
bottom=
'off', # ticks along the bottom edge are off TODO: Paul, this does not work anymore :( 1/26/2020
top='off', # ticks along the top edge are off
# labelbottom='off', # labels along the bottom edge are off
)
if CREATE_PDF:
plt.savefig(
join(figure_directory, fig_filename),
format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
# frameon=None
)
if SHOW_PDF:
showfig(join(figure_directory, fig_filename))
if SHOW_PLOT:
plt.show()
def run(choice, create_data=False, add_data=False, show_plot=False, create_pdf=False, show_pdf=False, shorten_length=False):
verbose = False
repeat_diffGraph = 1000
SUBSET = True
NOGT = False ## Not draw Ground Truth Comparison
CHOICE = choice
CREATE_DATA = create_data
ADD_DATA = add_data
SHOW_PLOT = show_plot
SHOW_PDF = show_pdf
CREATE_PDF = create_pdf
STD_FILL = False
csv_filename = 'Fig_fast_optimal_restarts_Accv2_{}.csv'.format(CHOICE)
fig_filename = 'Fig_fast_optimal_restarts_Accv2_{}.pdf'.format(CHOICE)
header = ['currenttime',
'k',
'restarts',
'accuracy']
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename), header, append=False)
# -- Default Graph parameters
global f_vec, labels, facecolor_vec
global number_of_restarts
initial_h0 = None
distribution = 'powerlaw'
exponent = -0.3 # for powerlaw
length = 4 # path length
constraint = True
gradient = True
variant = 1
EC = True
delta = 0.001
numMaxIt = 10
avoidNeighbors = False
convergencePercentage_W = None
stratified = True
learning_method = 'DHE'
weights = 10
randomize = True
return_min_energy = True
number_of_restarts = [8, 6, 5, 4]
clip_on_vec = [True] * 20
draw_std_vec = range(10)
ymin = 0.3
ymax = 1
xmin = 0.001
xmax = 1
xtick_lab = []
xtick_labels = []
ytick_lab = np.arange(0, 1.1, 0.1)
linestyle_vec = ['solid','solid','solid'] * 20
linewidth_vec = [4,4,4,4]*10
marker_vec = ['x', 'v', '^', '+', '>', '<'] *10
markersize_vec = [10, 8, 8, 8 ,8 ,8 ,8 ]*10
facecolor_vec = ["#C44E52", "#4C72B0", "#8172B2", "#CCB974", "#55A868", "#64B5CD"]*5
# -- Options mainly change k
if CHOICE == 101:
n = 10000
h = 3
d = 15
k_vec = [3, 4, 5, 6, 7, 10, 13, 16, 18, 20]
# k_vec = [4, 5, 7, 10]
f = 0.09
distribution = 'uniform'
# Write in DESCENDING ORDER
number_of_restarts = [30, 20, 10, 7, 5, 4, 3, 2, 1, 50, 99, 100]
### 100:GT 99:GTr
### 50:min{30,GTr} 1:uninformative
labels = ['r' + str(a1) for a1 in number_of_restarts]
xtick_lab = k_vec
xtick_labels = [str(a1) for a1 in k_vec]
elif CHOICE == 102:
n = 10000
h = 3
d = 15
k_vec = [3, 4, 5, 6, 7, 8]
# k_vec = [4, 5, 7, 10]
f = 0.09
distribution = 'uniform'
# Write in DESCENDING ORDER
# number_of_restarts = [30, 20, 10, 7, 5, 4, 3, 2, 1, 50, 99, 100]
number_of_restarts = [20, 10, 5, 4, 3, 2]
### 100:GT 99:GTr
### 50:min{30,GTr} 1:uninformative
labels = ['r' + str(a1) for a1 in number_of_restarts]
xtick_lab = k_vec
xtick_labels = [str(a1) for a1 in k_vec]
elif CHOICE == 103:
n = 10000
h = 3
d = 15
k_vec = [3, 4, 5, 6, 7, 8]
# k_vec = [4, 5, 7, 10]
f = 0.09
distribution = 'uniform'
# Write in DESCENDING ORDER
number_of_restarts = [20, 10, 5, 4, 3, 2, 99]
### 100:GT 99:GTr
### 50:min{30,GTr} 1:uninformative
marker_vec = ['o', 'x', 'v', '^', '+', 's', None] * 10
markersize_vec = [6, 10, 6, 6, 10, 6] * 10
labels = ['r' + str(a1) for a1 in number_of_restarts]
xtick_lab = k_vec
xtick_labels = [str(a1) for a1 in k_vec]
elif CHOICE == 104:
n = 10000
h = 8
d = 15
k_vec = [3, 4, 5, 6, 7, 8]
# k_vec = [4, 5, 7, 10]
f = 0.09
distribution = 'uniform'
# Write in DESCENDING ORDER
number_of_restarts = [20, 10, 5, 4, 3, 2, 99]
### 100:GT 99:GTr
### 50:min{30,GTr} 1:uninformative
marker_vec = ['o', 'x', 'v', '^', '+', 's', None] * 10
markersize_vec = [6, 10, 6, 6, 10, 6] * 10
labels = ['r' + str(a1) for a1 in number_of_restarts]
xtick_lab = k_vec
xtick_labels = [str(a1) for a1 in k_vec]
elif CHOICE == 105:
n = 10000
h = 8
d = 15
k_vec = [3, 4, 5, 6, 7, 8]
# k_vec = [4, 5, 7, 10]
f = 0.09
distribution = 'uniform'
# Write in DESCENDING ORDER
number_of_restarts = [20, 10, 5, 4, 3, 2, 100]
### 100:GT 99:GTr
### 50:min{30,GTr} 1:uninformative
marker_vec = ['o', 'x', 'v', '^', '+', 's', None] * 10
markersize_vec = [6, 10, 6, 6, 10, 6] * 10
labels = ['r' + str(a1) for a1 in number_of_restarts]
xtick_lab = k_vec
xtick_labels = [str(a1) for a1 in k_vec]
elif CHOICE == 106:
n = 10000
h = 3
d = 15
k_vec = [3, 4, 5, 6, 7, 8]
# k_vec = [4, 5, 7, 10]
f = 0.09
distribution = 'uniform'
# Write in DESCENDING ORDER
number_of_restarts = [20, 10, 5, 4, 3, 2, 100]
### 100:GT 99:GTr
### 50:min{30,GTr} 1:uninformative
marker_vec = ['o', 'x', 'v', '^', '+', 's', None] * 10
markersize_vec = [6, 10, 6, 6, 10, 6] * 10
labels = ['r' + str(a1) for a1 in number_of_restarts]
xtick_lab = k_vec
xtick_labels = [str(a1) for a1 in k_vec]
elif CHOICE == 107:
n = 10000
h = 8
d = 15
k_vec = [2, 3, 4, 5, 6, 7, 8]
# k_vec = [4, 5, 7, 10]
f = 0.09
distribution = 'uniform'
# Write in DESCENDING ORDER
number_of_restarts = [10, 5, 4, 3, 2, 99]
# number_of_restarts = [20, 10, 5, 4, 3, 2, 100]
### 100:GT 99:GTr
### 50:min{30,GTr} 1:uninformative
marker_vec = ['x', 'v', '^', 's', 'o', 's', None] * 10
markersize_vec = [10, 6, 6, 6, 6, 6, 6] * 10
labels = [r'$r=$' + str(a1) for a1 in number_of_restarts]
xtick_lab = k_vec
xtick_labels = [str(a1) for a1 in k_vec]
elif CHOICE == 108:
n = 10000
h = 8
d = 15
k_vec = [2, 3, 4, 5, 6, 7, 8]
# k_vec = [4, 5, 7, 10]
f = 0.09
distribution = 'uniform'
# Write in DESCENDING ORDER
number_of_restarts = [10, 5, 4, 3, 2, 99]
# number_of_restarts = [20, 10, 5, 4, 3, 2, 100]
### 100:GT 99:GTr
### 50:min{30,GTr} 1:uninformative
marker_vec = ['x', 'v', '^', 's', 'o', 's', None] * 10
markersize_vec = [10, 6, 6, 6, 6, 6, 6] * 10
labels = [r'$r=$' + str(a1) for a1 in number_of_restarts]
xtick_lab = k_vec
xtick_labels = [str(a1) for a1 in k_vec]
repeat_diffGraph = 10
else:
raise Warning("Incorrect choice!")
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(seed=RANDOMSEED) # seeds the actually used numpy random generator; both are used and thus needed
# print("CHOICE: {}".format(CHOICE))
# -- Create data
if CREATE_DATA or ADD_DATA:
for _ in range(repeat_diffGraph):
for k in k_vec:
a = [1.] * k
k_star = int(k * (k - 1) / 2)
alpha0 = np.array(a)
alpha0 = alpha0 / np.sum(alpha0)
# Generate Graph
# print("Generating Graph: n={} h={} d={} k={}".format(n, h, d, k))
H0 = create_parameterized_H(k, h, symmetric=True)
W, Xd = planted_distribution_model_H(n, alpha=alpha0, H=H0, d_out=d, distribution=distribution, exponent=exponent, directed=False, debug=False)
H0_vec = transform_HToh(H0)
# print("\nGold standard {}".format(np.round(H0_vec, decimals=3)))
X0 = from_dictionary_beliefs(Xd)
X2, ind = replace_fraction_of_rows(X0, 1 - f, avoidNeighbors=avoidNeighbors, W=W, ind_prior=None, stratified=stratified)
h0 = [1.] * int(k_star)
h0 = np.array(h0)
h0 = h0 / k
delta = 1 / (3 * k)
# print("delta: ", delta)
perm = []
while len(perm) < number_of_restarts[0]:
temp = []
for _ in range(k_star):
temp.append(random.choice([-delta, delta]))
if temp not in perm:
perm.append(temp)
if len(perm) >= 2 ** (k_star):
break
E_list = [] ## format = [[energy, H_vec], []..]
for vec in perm:
H2_vec, energy = estimateH(X2, W, method=learning_method, variant=1, distance=length, EC=EC,
weights=weights, randomize=False, constraints=constraint,
gradient=gradient, return_min_energy=True, verbose=verbose,
initial_h0=h0 + np.array(vec))
E_list.append([energy, list(H2_vec)])
# print("All Optimizaed vector:")
# [print(i) for i in E_list ]
# print("Outside Energy:{} optimized vec:{} \n".format(min_energy_vec[0], optimized_Hvec))
# min_energy_vec = min(E_list)
# optimized_Hvec = min_energy_vec[1]
#
# print("\nEnergy:{} optimized vec:{} \n\n".format(min_energy_vec[0],optimized_Hvec))
#
#
GTr_optimized_Hvec, GTr_energy = estimateH(X2, W, method=learning_method, variant=1, distance=length, EC=EC,
weights=weights, randomize=False, constraints=constraint,
gradient=gradient, return_min_energy=True, verbose=verbose,
initial_h0=H0_vec)
uninformative_optimized_Hvec, uninformative_energy = estimateH(X2, W, method=learning_method, variant=1, distance=length, EC=EC,
weights=weights, randomize=False, constraints=constraint,
gradient=gradient, return_min_energy=True, verbose=verbose,
initial_h0=h0)
iterative_permutations = list(E_list)
for restartz in number_of_restarts:
if k==2 or k == 3 and restartz > 8 and restartz<99:
continue
if restartz <= number_of_restarts[0]:
iterative_permutations = random.sample(iterative_permutations, restartz)
# print("For restart:{}, we have vectors:\n".format(restartz))
# [print(i) for i in iterative_permutations]
if restartz == 100: ## for GT
H2c = to_centering_beliefs(H0)
# print("\nGT: ", transform_HToh(H0,k))
elif restartz == 99: ## for DCEr init with GT
H2c = to_centering_beliefs(transform_hToH(GTr_optimized_Hvec, k))
# print("\nGTr: ", GTr_optimized_Hvec)
elif restartz == 1: ## for DCEr with uninformative initial
H2c = to_centering_beliefs(transform_hToH(uninformative_optimized_Hvec, k))
# print("\nUninformative: ", uninformative_optimized_Hvec)
elif restartz == 50: ## for min{DCEr , GTr}
# print("Length:",len(E_list))
# [print(i) for i in E_list]
mod_E_list = list(E_list)+[[GTr_energy , list(GTr_optimized_Hvec)]] #Add GTr to list and take min
# print("Mod Length:", len(mod_E_list))
# [print(i) for i in mod_E_list]
min_energy_vec = min(mod_E_list)
# print("\nSelected for 50:",min_energy_vec)
optimized_Hvec = min_energy_vec[1]
H2c = to_centering_beliefs(transform_hToH(optimized_Hvec, k))
else:
min_energy_vec = min(iterative_permutations)
optimized_Hvec = min_energy_vec[1]
H2c = to_centering_beliefs(transform_hToH(optimized_Hvec, k))
# print("Inside Chosen Energy:{} optimized vec:{} \n".format(min_energy_vec[0], optimized_Hvec))
try:
eps_max = eps_convergence_linbp_parameterized(H2c, W, method='noecho', X=X2)
s = 0.5
eps = s * eps_max
F, actualIt, actualPercentageConverged = \
linBP_symmetric_parameterized(X2, W, H2c * eps,
method='noecho',
numMaxIt=numMaxIt,
convergencePercentage=convergencePercentage_W,
debug=2)
except ValueError as e:
print(
"ERROR: {} with {}: d={}, h={}".format(e, learning_method, d, h))
else:
acc = matrix_difference_classwise(X0, F, ignore_rows=ind)
tuple = [str(datetime.datetime.now())]
text = [k,
restartz,
acc]
tuple.extend(text)
if verbose:
print("\nGold standard {}".format(np.round(H0_vec, decimals=3)))
# print("k:{} Restart:{} OptimizedVec:{} Energy:{} Accuracy:{}".format(k, restartz, np.round(min_energy_vec[1], decimals=3), min_energy_vec[0], acc ))
# print("k:{} Restart:{} Accuracy:{}".format(k, 1, L2_dist))
save_csv_record(join(data_directory, csv_filename), tuple)
# -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1 (length {}):\n{}".format(len(df1.index), df1.head(20)))
# Aggregate repetitions
df2 = df1.groupby(['k', 'restarts']).agg \
({'accuracy': [np.mean, np.std, np.size], })
df2.columns = ['_'.join(col).strip() for col in df2.columns.values] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'accuracy_size': 'count'}, inplace=True)
df2['restarts'] = df2['restarts'].astype(str)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(20)))
# Pivot table
df3 = pd.pivot_table(df2, index=['k'], columns=['restarts'], values=['accuracy_mean', 'accuracy_std'] ) # Pivot
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
df3.columns = ['_'.join(col).strip() for col in df3.columns.values] # flatten the column hierarchy
df3.reset_index(inplace=True) # remove the index hierarchy
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(10)))
df4 = df3.drop('k', axis=1)
if NOGT:
df4 = df3.drop(['k', 'accuracy_mean_0', 'accuracy_mean_1', 'accuracy_std_0', 'accuracy_std_1'], axis=1)
# df4 = df3.drop(['k', 'accuracy_mean_100', 'accuracy_std_100'], axis=1)
df5 = df4.div(df4.max(axis=1), axis=0)
df5['k'] = df3['k']
# print("\n-- df5 (length {}):\n{}".format(len(df5.index), df5.head(100)))
# df5 = df3 ## for normalization
X_f = df5['k'].values # read k from values instead
Y=[]
Y_std=[]
for rez in number_of_restarts:
if NOGT:
if rez == 100 or rez==99:
continue
Y.append(df5['accuracy_mean_{}'.format(rez)].values)
if STD_FILL:
Y_std.append(df5['accuracy_std_{}'.format(rez)].values)
if CREATE_PDF or SHOW_PDF or SHOW_PLOT:
# -- Setup figure
mpl.rc('font', **{'family': 'sans-serif', 'sans-serif': [u'Arial', u'Liberation Sans']})
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 14
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['xtick.major.pad'] = 2 # padding of tick labels: default = 4
mpl.rcParams['ytick.major.pad'] = 1 # padding of tick labels: default = 4
mpl.rcParams['xtick.direction'] = 'out' # default: 'in'
mpl.rcParams['ytick.direction'] = 'out' # default: 'in'
mpl.rcParams['font.size'] = 16
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['figure.figsize'] = [4, 4]
fig = figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
# -- Drawing
if STD_FILL:
for choice, (option, facecolor) in enumerate(zip(number_of_restarts, facecolor_vec)):
if option == 100: ## GT
if NOGT:
continue
facecolor = 'black'
elif option == 99: ## GT-r
if NOGT:
continue
facecolor = 'black'
ax.fill_between(X_f, Y[choice] + Y_std[choice], Y[choice] - Y_std[choice],
facecolor=facecolor, alpha=0.2, edgecolor=None, linewidth=0)
ax.plot(X_f, Y[choice] + Y_std[choice], linewidth=0.5, color='0.8', linestyle='solid')
ax.plot(X_f, Y[choice] - Y_std[choice], linewidth=0.5, color='0.8', linestyle='solid')
for choice, (option, label, color, linewidth, clip_on, linestyle, marker, markersize) in \
enumerate(zip(number_of_restarts, labels, facecolor_vec, linewidth_vec, clip_on_vec, linestyle_vec, marker_vec, markersize_vec)):
if option == 100: ## GT
if NOGT:
continue
linestyle='dashed'
linewidth=3
color='black'
label='GS'
marker='x'
markersize=6
elif option == 99: ## GT-r
if NOGT:
continue
linestyle='dashed'
linewidth=2
color='black'
label='Global Minima'
marker = None
markersize = 6
elif option == 1: ## GT
color="#CCB974"
linewidth = 2
label='Uninfo'
elif option == 50: ## GT-r
label='min{30,GTr}'
P = ax.plot(X_f, Y[choice], linewidth=linewidth, color=color, linestyle=linestyle, label=label, zorder=4, marker=marker,
markersize=markersize, markeredgecolor='black', markeredgewidth=1, clip_on=clip_on)
# plt.xscale('log')
# -- Title and legend
distribution_label = '$'
if distribution == 'uniform':
distribution_label = ',$uniform'
n_label = '{}k'.format(int(n / 1000))
if n < 1000:
n_label='{}'.format(n)
titleString = r'$\!\!\!n\!=\!{}, d\!=\!{}, h\!=\!{}, f\!=\!{} $'.format(n_label, d, h, f)
title(titleString)
handles, labels = ax.get_legend_handles_labels()
legend = plt.legend(handles, labels,
loc='lower left', # 'upper right'
handlelength=2,
labelspacing=0, # distance between label entries
handletextpad=0.3, # distance between label and the line representation
borderaxespad=0.2, # distance between legend and the outer axes
borderpad=0.3, # padding inside legend box
numpoints=1, # put the marker only once
# bbox_to_anchor=(1.1, 0)
)
# # legend.set_zorder(1)
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.9) # 0.8
plt.xticks(xtick_lab, xtick_labels)
# plt.yticks(ytick_lab, ytick_lab)
ax.yaxis.set_ticks_position('left')
ax.xaxis.set_ticks_position('bottom')
ax.yaxis.set_major_formatter(mpl.ticker.FormatStrFormatter('%.2f'))
# ax.xaxis.set_major_formatter(mpl.ticker.FormatStrFormatter('%.0f'))
grid(b=True, which='major', axis='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
grid(b=True, which='minor', axis='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
xlabel(r'Number of Classes $(k)$', labelpad=0) # labelpad=0
ylabel(r'Relative Accuracy', labelpad=0)
xlim(2.9, 7.1)
#
ylim(0.65, 1.015)
if CREATE_PDF:
savefig(join(figure_directory, fig_filename), format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
frameon=None)
if SHOW_PLOT:
plt.show()
if SHOW_PDF:
showfig(join(figure_directory, fig_filename)) # shows actually created PDF
def run(choice, create_data=False, add_data=False, show_plot=False, create_pdf=False, show_pdf=False, shorten_length=False):
# -- Setup
CHOICE = choice
CREATE_DATA = create_data
ADD_DATA = add_data
SHOW_PDF = show_pdf
SHOW_PLOT = show_plot
CREATE_PDF = create_pdf
STD_FILL = True
csv_filename = 'Fig_End-to-End_accuracy_VaryK_{}.csv'.format(CHOICE)
header = ['currenttime',
'option',
'k',
'f',
'accuracy']
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename), header, append=False)
# -- Default Graph parameters
rep_SameGraph = 10 # iterations on same graph
initial_h0 = None # initial vector to start finding optimal H
distribution = 'powerlaw'
exponent = -0.3
length = 5
variant = 1
EC = True # Non-backtracking for learning
ymin = 0.3
ymax = 1
xmax = 8
xtick_lab = [2,3,4,5,6,7, 8]
xtick_labels = ['2', '3', '4', '5', '6', '7', '8']
ytick_lab = np.arange(0, 1.1, 0.1)
f_vec = [0.9 * pow(0.1, 1 / 5) ** x for x in range(21)]
k_vec = [3, 4, 5 ]
rep_DifferentGraphs = 10 # iterations on different graphs
err = 0
avoidNeighbors = False
gradient = False
pruneRandom = False
convergencePercentage_W = None
stratified = True
label_vec = ['*'] * 10
clip_on_vec = [False] * 10
draw_std_vec = range(10)
numberOfSplits = 1
linestyle_vec = ['dashed'] + ['solid'] * 10
linewidth_vec = [5, 4, 3, 3] + [3] * 10
marker_vec = [None, None, 'o', 'x', 'o', '^', 'o', 'x', 'o', '^', 'o', 'x', 'o', '^']
markersize_vec = [0, 0, 4, 8] + [6] * 10
facecolor_vec = ["#4C72B0", "#55A868", "#C44E52", "#8172B2", "#CCB974", "#64B5CD"]
# -- Options with propagation variants
if CHOICE == 500: ## 1k nodes
n = 1000
h = 8
d = 25
option_vec = ['opt1', 'opt2', 'opt3']
learning_method_vec = ['GS', 'MHE', 'DHE']
weight_vec = [10] * 3
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 2 + [True]
xmin = 3.
ymin = 0.
ymax = 1.
label_vec = ['GS', 'MCE', 'DCEr']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.03, 0.01, 0.001]
k_vec = [3, 4, 5, 6]
elif CHOICE == 501: ## 10k nodes
n = 10000
h = 8
d = 25
option_vec = ['opt1', 'opt2', 'opt3']
learning_method_vec = ['GT', 'MHE', 'DHE']
weight_vec = [10] * 3
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 2 + [True]
xmin = 2.
ymin = 0.
ymax = 1.
label_vec = ['GT', 'MCE', 'DCEr']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.03, 0.01, 0.001]
k_vec = [2, 3, 4, 5]
elif CHOICE == 502: ## 10k nodes
n = 10000
h = 8
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE', 'Holdout']
weight_vec = [10] * 10
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True] + [False]
xmin = 2
ymin = 0.6
ymax = 1.
label_vec = ['GT', 'LCE', 'MCE', 'DCE', 'DCEr', 'Holdout']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.01]
k_vec = [2, 3, 4, 5, 6, 7, 8]
# option_vec = ['opt1', 'opt2', 'opt3', 'opt4']
# learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE']
# k_vec = [2, 3, 4, 5]
elif CHOICE == 503: ## 10k nodes
n = 10000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE', 'Holdout']
weight_vec = [10] * 10
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True] + [False]
xmin = 2
ymin = 0.3
ymax = 0.9
label_vec = ['GT', 'LCE', 'MCE', 'DCE', 'DCEr', 'Holdout']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.01]
k_vec = [2, 3, 4, 5, 6, 7, 8]
# k_vec = [6, 7, 8]
clip_on_vec = [True] * 10
# option_vec = ['opt1', 'opt2', 'opt3', 'opt4']
# learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE']
# k_vec = [2, 3, 4, 5]
elif CHOICE == 504: ## 10k nodes
n = 10000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE', 'Holdout']
weight_vec = [10] * 10
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True] + [False]
xmin = 2
xmax = 7
ymin = 0.2
ymax = 0.9
label_vec = ['GT', 'LCE', 'MCE', 'DCE', 'DCEr', 'Holdout']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.01]
# k_vec = [2, 3, 4, 5, 6, 7, 8]
k_vec = [7]
clip_on_vec = [True] * 10
elif CHOICE == 505: ## 10k nodes with f = 0.005
n = 10000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE', 'Holdout']
weight_vec = [10] * 10
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True] + [False]
xmin = 2
xmax = 7
ymin = 0.2
ymax = 0.9
label_vec = ['GT', 'LCE', 'MCE', 'DCE', 'DCEr', 'Holdout']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.005]
k_vec = [2, 3, 4, 5, 6, 7]
# k_vec = [7]
clip_on_vec = [True] * 10
# elif CHOICE == 506: ## 10k nodes with f = 0.005
# n = 10000
# h = 3
# d = 25
# option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
# learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
# weight_vec = [10] * 10
# alpha_vec = [0] * 10
# beta_vec = [0] * 10
# gamma_vec = [0] * 10
# s_vec = [0.5] * 10
# numMaxIt_vec = [10] * 10
# randomize_vec = [False] * 4 + [True] + [False]
# xmin = 2
# xmax = 7
# ymin = 0.2
# ymax = 0.9
# label_vec = ['GT', 'LCE', 'MCE', 'DCE', 'DCEr']
# facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
# f_vec = [0.005]
# k_vec = [2,3,4,5,6,7]
# # k_vec = [7]
# clip_on_vec = [True] * 10
elif CHOICE == 506: ## 10k nodes
n = 10000
h = 8
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE', 'Holdout']
learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE', 'DHE']
weight_vec = [10] * 10
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True] + [False]
xmin = 2
xmax = 7
ymin = 0.2
ymax = 0.9
label_vec = ['GT', 'LCE', 'MCE', 'DCE', 'DCEr', 'Holdout']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.005]
k_vec = [2, 3, 4, 5, 6, 7, 8]
# k_vec = [5]
clip_on_vec = [True] * 10
rep_SameGraph = 1 # iterations on same graph
rep_DifferentGraphs = 1 # iterations on same graph
elif CHOICE == 507: ## 10k nodes with gradient and PruneRandom
n = 10000
h = 3
d = 25
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['GS', 'LHE', 'MHE', 'DHE', 'DHE', 'Holdout']
weight_vec = [10] * 10
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True] + [False]
xmin = 2
ymin = 0.1
ymax = 0.9
label_vec = ['GS', 'LCE', 'MCE', 'DCE', 'DCEr', 'Holdout']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.01]
k_vec = [2, 3, 4, 5, 6, 7, 8]
# k_vec = [6, 7, 8]
clip_on_vec = [True] * 10
# option_vec = ['opt1', 'opt2', 'opt3', 'opt4']
# learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE']
# k_vec = [2, 3, 4, 5]
gradient = True
pruneRandom = True
elif CHOICE == 508: ## 10k nodes with gradient and PruneRandom
n = 1000
h = 3
d = 10
option_vec = ['opt1', 'opt2', 'opt3', 'opt4', 'opt5', 'opt6']
learning_method_vec = ['GS', 'LHE', 'MHE', 'DHE', 'DHE', 'Holdout']
weight_vec = [10] * 10
alpha_vec = [0] * 10
beta_vec = [0] * 10
gamma_vec = [0] * 10
s_vec = [0.5] * 10
numMaxIt_vec = [10] * 10
randomize_vec = [False] * 4 + [True] + [False]
xmin = 2
ymin = 0.1
ymax = 0.9
label_vec = ['GS', 'LCE', 'MCE', 'DCE', 'DCEr', 'Holdout']
facecolor_vec = ['black'] + ["#55A868", "#4C72B0", "#8172B2", "#C44E52", "#CCB974"] * 3
f_vec = [0.01]
k_vec = [2, 3, 4, 5, 6, 7, 8]
# k_vec = [6, 7, 8]
clip_on_vec = [True] * 10
# option_vec = ['opt1', 'opt2', 'opt3', 'opt4']
# learning_method_vec = ['GT', 'LHE', 'MHE', 'DHE']
# k_vec = [2, 3, 4, 5]
gradient = True
pruneRandom = True
rep_DifferentGraphs = 1
rep_SameGraph = 1
else:
raise Warning("Incorrect choice!")
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(seed=RANDOMSEED) # seeds the actually used numpy random generator; both are used and thus needed
# print("CHOICE: {}".format(CHOICE))
# -- Create data
if CREATE_DATA or ADD_DATA:
for i in range(rep_DifferentGraphs): # create several graphs with same parameters
# print("\ni: {}".format(i))
for k in k_vec:
# print("\nk: {}".format(k))
H0 = create_parameterized_H(k, h, symmetric=True)
H0c = to_centering_beliefs(H0)
a = [1.] * k
alpha0 = np.array(a)
alpha0 = alpha0 / np.sum(alpha0)
W, Xd = planted_distribution_model_H(n, alpha=alpha0, H=H0, d_out=d,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
for j in range(rep_SameGraph): # repeat several times for same graph
# print("j: {}".format(j))
ind = None
for f in f_vec: # Remove fraction (1-f) of rows from X0 (notice that different from first implementation)
X1, ind = replace_fraction_of_rows(X0, 1-f, avoidNeighbors=avoidNeighbors, W=W, ind_prior=ind, stratified=stratified)
X2 = introduce_errors(X1, ind, err)
for option_index, (learning_method, alpha, beta, gamma, s, numMaxIt, weights, randomize) in \
enumerate(zip(learning_method_vec, alpha_vec, beta_vec, gamma_vec, s_vec, numMaxIt_vec, weight_vec, randomize_vec)):
# -- Learning
if learning_method == 'GT':
H2c = H0c
elif learning_method == 'Holdout':
H2 = estimateH_baseline_serial(X2, ind, W, numMax=numMaxIt,
# ignore_rows=ind,
numberOfSplits=numberOfSplits,
# method=learning_method, variant=1, distance=length,
EC=EC,
alpha=alpha, beta=beta, gamma=gamma)
H2c = to_centering_beliefs(H2)
elif learning_method != 'DHE':
H2 = estimateH(X2, W, method=learning_method, variant=1, distance=length, EC=EC, weights=weights, randomize=randomize)
H2c = to_centering_beliefs(H2)
else:
H2 = estimateH(X2, W, method=learning_method, variant=1, distance=length, EC=EC, weights=weights, randomize=randomize, gradient=gradient, randomrestarts=pruneRandom)
H2c = to_centering_beliefs(H2)
# -- Propagation
X2c = to_centering_beliefs(X2, ignoreZeroRows=True) # try without
eps_max = eps_convergence_linbp_parameterized(H2c, W,
method='noecho',
alpha=alpha, beta=beta, gamma=gamma,
X=X2)
eps = s * eps_max
try:
F, actualIt, actualPercentageConverged = \
linBP_symmetric_parameterized(X2, W, H2c * eps,
method='noecho',
alpha=alpha, beta=beta, gamma=gamma,
numMaxIt=numMaxIt,
convergencePercentage=convergencePercentage_W,
debug=2)
except ValueError as e:
print (
"ERROR: {} with {}: d={}, h={}".format(e, learning_method, d, h))
else:
accuracy_X = matrix_difference(X0, F, ignore_rows=ind)
tuple = [str(datetime.datetime.now())]
text = [option_vec[option_index],
k,
f,
accuracy_X]
# text = ['' if v is None else v for v in text] # TODO: test with vocabularies
# text = np.asarray(text) # without np, entries get ugly format
tuple.extend(text)
# print("option: {}, f: {}, actualIt: {}, accuracy: {}".format(option_vec[option_index], f, actualIt, accuracy_X))
save_csv_record(join(data_directory, csv_filename), tuple)
# -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1: (length {}):\n{}".format(len(df1.index), df1.head(15)))
# -- Aggregate repetitions
df2 = df1.groupby(['option', 'k', 'f']).agg \
({'accuracy': [np.mean, np.std, np.size, np.median], # Multiple Aggregates
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'accuracy_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(15)))
# -- Pivot table
df3 = pd.pivot_table(df2, index=['f', 'k'], columns=['option'], values=[ 'accuracy_mean', 'accuracy_std'] ) # Pivot
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
df3.columns = ['_'.join(col).strip() for col in df3.columns.values] # flatten the column hierarchy
df3.reset_index(inplace=True) # remove the index hierarchy
# df2.rename(columns={'time_size': 'count'}, inplace=True)
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(100)))
# X_f = k_vec
X_f = df3['k'].values # read k from values instead
Y_hash = defaultdict(dict)
Y_hash_std = defaultdict(dict)
for f in f_vec:
for option in option_vec:
Y_hash[f][option] = list()
Y_hash_std[f][option] = list()
for f in f_vec:
for option in option_vec:
Y_hash[f][option] = df3.loc[df3['f'] == f]['accuracy_mean_{}'.format(option)].values
Y_hash_std[f][option] = df3.loc[df3['f'] == f]['accuracy_std_{}'.format(option)].values
if CREATE_PDF or SHOW_PLOT or SHOW_PDF:
# -- Setup figure
fig_filename = 'Fig_End-to-End_accuracy_varyK_{}.pdf'.format(CHOICE)
mpl.rc('font', **{'family': 'sans-serif', 'sans-serif': [u'Arial', u'Liberation Sans']})
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 14
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['xtick.major.pad'] = 2 # padding of tick labels: default = 4
mpl.rcParams['ytick.major.pad'] = 1 # padding of tick labels: default = 4
mpl.rcParams['xtick.direction'] = 'out' # default: 'in'
mpl.rcParams['ytick.direction'] = 'out' # default: 'in'
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['figure.figsize'] = [4, 4]
fig = figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
opt_f_vecs = [(option, f) for option in option_vec for f in f_vec]
for ((option, f), color, linewidth, clip_on, linestyle, marker, markersize) in \
zip(opt_f_vecs, facecolor_vec, linewidth_vec, clip_on_vec, linestyle_vec, marker_vec, markersize_vec):
# label = learning_method_vec[option_vec.index(option)]
label = label_vec[option_vec.index(option)]
# label = label + " " + str(f)
if STD_FILL:
# print((X_f))
# print(Y_hash[f][option])
ax.fill_between(X_f, Y_hash[f][option] + Y_hash_std[f][option], Y_hash[f][option] - Y_hash_std[f][option],
facecolor=color, alpha=0.2, edgecolor=None, linewidth=0)
ax.plot(X_f, Y_hash[f][option] + Y_hash_std[f][option], linewidth=0.5, color='0.8', linestyle='solid')
ax.plot(X_f, Y_hash[f][option] - Y_hash_std[f][option], linewidth=0.5, color='0.8', linestyle='solid')
ax.plot(X_f, Y_hash[f][option], linewidth=linewidth, color=color, linestyle=linestyle, label=label, zorder=4, marker=marker,
markersize=markersize, markeredgewidth=1, markeredgecolor='black', clip_on=clip_on)
if CHOICE==507:
Y_f = [1/float(i) for i in X_f]
ax.plot(X_f, Y_f, linewidth=2, color='black', linestyle='dashed',
label='Random', zorder=4, marker='x',
markersize=8, markeredgewidth=1, markeredgecolor='black', clip_on=clip_on)
# -- Title and legend
if distribution == 'uniform':
distribution_label = ',$uniform'
else:
distribution_label = '$'
if n < 1000:
n_label='{}'.format(n)
else:
n_label = '{}k'.format(int(n / 1000))
title(r'$\!\!\!n\!=\!{}, d\!=\!{}, h\!=\!{}, f\!=\!{}{}'.format(n_label, d, h, f, distribution_label))
handles, label_vec = ax.get_legend_handles_labels()
legend = plt.legend(handles, label_vec,
loc='upper right', # 'upper right'
handlelength=2,
labelspacing=0, # distance between label entries
handletextpad=0.3, # distance between label and the line representation
borderaxespad=0.2, # distance between legend and the outer axes
borderpad=0.3, # padding inside legend box
numpoints=1, # put the marker only once
)
# # legend.set_zorder(1)
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.9) # 0.8
# -- Figure settings and save
plt.xticks(xtick_lab, xtick_labels)
plt.yticks(ytick_lab, ytick_lab)
ax.yaxis.set_major_formatter(mpl.ticker.FormatStrFormatter('%.1f'))
# Only show ticks on the left and bottom spines
ax.yaxis.set_ticks_position('left')
ax.xaxis.set_ticks_position('bottom')
grid(b=True, which='major', axis='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
grid(b=True, which='minor', axis='both', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
xlabel(r'Number of Classes $(k)$', labelpad=0) # labelpad=0
ylabel(r'Accuracy', labelpad=0)
xlim(xmin, xmax)
ylim(ymin, ymax)
if CREATE_PDF:
savefig(join(figure_directory, fig_filename), format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
frameon=None)
if SHOW_PLOT:
plt.show()
if SHOW_PDF:
showfig(join(figure_directory, fig_filename))
def run(choice, variant, create_data=False, show_plot=False, create_pdf=False, show_pdf=False, append_data=False):
"""main parameterized method to produce all figures.
Can be run from external jupyther notebook or method to produce all figures, optionally as PDF
CHOICE uses a different saved experimental run
VARIANT uses a different wayt o plot
"""
# %% -- Setup
CREATE_DATA = create_data
APPEND_DATA = append_data # allows to add more data, requires CREATE_DATA to be true
CHOICE = choice
VARIANT = variant
SHOW_PLOT = show_plot
CREATE_PDF = create_pdf
SHOW_PDF = show_pdf
BOTH = True # show both figures for W and H
SHOW_TITLE = True # show parameters in title of plot
f = 1 # fraction of labeled nodes for H estimation
csv_filename = 'Fig_Scaling_Hrow_{}.csv'.format(CHOICE)
fig_filename = 'Fig_Scaling_Hrow_{}-{}.pdf'.format(CHOICE, VARIANT)
plot_colors = ['darkorange', 'blue']
header = ['currenttime',
'choice', # W, or H
'l',
'time']
if CREATE_DATA and not APPEND_DATA:
save_csv_record(join(data_directory, csv_filename), header, append=APPEND_DATA)
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(seed=RANDOMSEED) # seeds the actually used numpy random generator; both are used and thus needed
# %% -- Default parameters
n = 10000
ymax = 10
h = 3
d = 10 # actual degree is double
distribution = 'uniform'
exponent = None
# %% -- CHOICES and VARIANTS
if CHOICE == 1:
W_repeat = [0, 0, 30, 5, 3, 1] # index starts with 0. useful only for W^2 and later
H_repeat = [0, 50, 50, 50, 50, 50, 50, 50, 50]
W_annotate_x = 4.3
W_annotate_y = 1
H_annotate_x = 6
H_annotate_y = 0.005
elif CHOICE == 2: # small exponent 3, does not show the advantage well
d = 3
W_repeat = [0, 0, 10, 5, 5, 5, 5, 5, 5] # index starts with 0. useful only for W^2 and later
H_repeat = [0, 50, 50, 50, 50, 50, 50, 50, 50]
W_annotate_x = 5
W_annotate_y = 0.08
H_annotate_x = 6.5
H_annotate_y = 0.004
elif CHOICE == 3: # small exponent 2, does not show the advantage well
d = 2
W_repeat = [0, 0, 50, 50, 50, 50, 50, 50, 50] # index starts with 0. useful only for W^2 and later
H_repeat = [0, 50, 50, 50, 50, 50, 50, 50, 50]
W_annotate_x = 6.5
W_annotate_y = 0.02
H_annotate_x = 6.5
H_annotate_y = 0.004
elif CHOICE == 4:
distribution = 'powerlaw'
exponent = -0.5
W_repeat = [0, 0, 50, 9, 5, 3] # index starts with 0. useful only for W^2 and later
H_repeat = [0, 50, 50, 50, 50, 50, 50, 50, 50]
W_annotate_x = 4
W_annotate_y = 1
H_annotate_x = 6.5
H_annotate_y = 0.006
if VARIANT == 1:
plot_colors = ['blue', 'darkorange']
SHOW_TITLE = False
if VARIANT == 2:
plot_colors = ['blue', 'darkorange']
BOTH = False
SHOW_TITLE = False
elif CHOICE == 5:
distribution = 'powerlaw'
exponent = -0.5
W_repeat = [0, 0, 1, 1] # index starts with 0. useful only for W^2 and later
H_repeat = [0] + [1] * 8
W_annotate_x = 4
W_annotate_y = 1
H_annotate_x = 6.5
H_annotate_y = 0.006
elif CHOICE == 11:
W_repeat = [0, 0, 1, 1, 0, 0] # index starts with 0. useful only for W^2 and later
H_repeat = [0, 50, 50, 50, 50, 50, 50, 50, 50]
W_annotate_x = 4.3
W_annotate_y = 1
H_annotate_x = 6
H_annotate_y = 0.005
elif CHOICE == 12:
W_repeat = [0, 0, 31, 11, 5, 3, 3, 3, 3] # index starts with 0. useful only for W^2 and later
H_repeat = [0, 50, 50, 50, 50, 50, 50, 50, 50]
W_annotate_x = 4.3
W_annotate_y = 2.5
H_annotate_x = 5.5
H_annotate_y = 0.004
f = 0.1
plot_colors = ['blue', 'darkorange']
ymax = 100
if VARIANT == 1: # TODO: when trying to add additional data, then it creates 7 instead of 4 rows,
# but the same code idea of CREATE vs ADD data appears to work in Fig_MHE_Optimal_Lambda, for that to replicate run below
# run(12, 1, create_pdf=True, show_pdf=True, create_data=False, append_data=True)
W_repeat = [0, 0, 0, 0, 0, 0, 0, 0, 0] # index starts with 0. useful only for W^2 and later
H_repeat = [0, 50, 50, 50, 50, 50, 50, 50, 50]
else:
raise Warning("Incorrect choice!")
# %% -- Create data
if CREATE_DATA or APPEND_DATA:
# Create graph
k = 3
a = 1
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
start = time.time()
W, Xd = planted_distribution_model_H(n, alpha=alpha0, H=H0, d_out=d,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
time_calc = time.time() - start
# print("\nTime for graph:{}".format(time_calc))
# print("Average outdegree: {}".format(calculate_average_outdegree_from_graph(W)))
# Calculations W
for length, rep in enumerate(W_repeat):
for _ in range(rep):
start = time.time()
if length == 2:
result = W.dot(W)
elif length == 3:
result = W.dot(W.dot(W)) # naive enumeration used as nothing can be faster
elif length == 4:
result = W.dot(W.dot(W.dot(W)))
elif length == 5:
result = W.dot(W.dot(W.dot(W.dot(W))))
elif length == 6:
result = W.dot(W.dot(W.dot(W.dot(W.dot(W)))))
elif length == 7:
result = W.dot(W.dot(W.dot(W.dot(W.dot(W.dot(W))))))
elif length == 8:
result = W.dot(W.dot(W.dot(W.dot(W.dot(W.dot(W.dot(W)))))))
elif length == 9:
result = W.dot(W.dot(W.dot(W.dot(W.dot(W.dot(W.dot(W.dot(W))))))))
time_calc = time.time() - start
tuple = [str(datetime.datetime.now())]
text = ['W',
length,
time_calc]
text = np.asarray(text) # without np, entries get ugly format
tuple.extend(text)
# print("W, d: {}, time: {}".format(length, time_calc))
save_csv_record(join(data_directory, csv_filename), tuple)
# Calculations H_NB
for length, rep in enumerate(H_repeat):
for _ in range(rep):
X0 = from_dictionary_beliefs(Xd)
X1, ind = replace_fraction_of_rows(X0, 1 - f)
start = time.time()
result = H_observed(W, X=X1, distance=length, NB=True, variant=1)
time_calc = time.time() - start
tuple = [str(datetime.datetime.now())]
text = ['H',
length,
time_calc]
text = np.asarray(text) # without np, entries get ugly format
tuple.extend(text)
# print("H, d: {}, time: {}".format(length, time_calc))
save_csv_record(join(data_directory, csv_filename), tuple)
# Calculate and display M statistics
for length, _ in enumerate(H_repeat):
M = M_observed(W, X=X0, distance=length, NB=True)
M = M[-1]
s = np.sum(M)
# print("l: {}, sum: {:e}, M:\n{}".format(length, s, M))
# %% -- Read, aggregate, and pivot data
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1 (length {}):\n{}".format(len(df1.index), df1.head(15)))
df2 = df1.groupby(['choice', 'l']).agg \
({'time': [np.max, np.mean, np.median, np.min, np.size], # Multiple Aggregates
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'time_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(30)))
df3 = pd.pivot_table(df2, index=['l'], columns=['choice'], values='time_median', ) # Pivot
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
#%% -- Setup figure
mpl.rcParams['backend'] = 'pdf'
mpl.rcParams['lines.linewidth'] = 3
mpl.rcParams['font.size'] = 20
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['axes.edgecolor'] = '111111' # axes edge color
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['figure.figsize'] = [4, 4]
mpl.rcParams['xtick.major.pad'] = 6 # padding of tick labels: default = 4
mpl.rcParams['ytick.major.pad'] = 4 # padding of tick labels: default = 4
fig = plt.figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
#%% -- Draw the plot and annotate
df4 = df3['H']
# print("\n-- df4 (length {}):\n{}".format(len(df4.index), df4.head(30)))
Y1 = df3['W'].plot(logy=True, color=plot_colors[0], marker='o', legend=None,
clip_on=False, # cut off data points outside of plot area
# zorder=3
) # style='o', kind='bar', style='o-',
plt.annotate(r'$\mathbf{W}^\ell$',
xy=(W_annotate_x, W_annotate_y),
color=plot_colors[0],
)
if BOTH:
Y2 = df3['H'].plot(logy=True, color=plot_colors[1], marker='o', legend=None,
clip_on=False, # cut off data points outside of plot area
zorder=3
) # style='o', kind='bar', style='o-',
plt.annotate(r'$\mathbf{\hat P}_{\mathrm{NB}}^{(\ell)}$',
xy=(H_annotate_x, H_annotate_y),
color=plot_colors[1],
)
if SHOW_TITLE:
plt.title(r'$\!\!\!\!n\!=\!{}\mathrm{{k}}, d\!=\!{}, h\!=\!{}, f\!=\!{}$'.format(int(n / 1000), 2 * d, h, f))
# %% -- Figure settings & plot
plt.grid(b=True, which='both', alpha=0.2, linestyle='solid', axis='y', linewidth=0.5) # linestyle='dashed', which='minor'
plt.xlabel(r'Path length ($\ell$)', labelpad=0)
plt.ylabel(r'$\!$Time [sec]', labelpad=1)
plt.ylim(0.001, ymax) # placed after yticks
plt.xticks(range(1, 9))
if SHOW_PLOT:
plt.show()
if CREATE_PDF:
plt.savefig(join(figure_directory, fig_filename), format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
# frameon=None
)
if SHOW_PDF:
# os.system('{} "'.format(open_cmd[sys.platform]) + join(figure_directory, fig_filename) + '"') # shows actually created PDF
showfig(join(figure_directory, fig_filename)) # shows actually created PDF # TODO replace with this method
def test_estimate_synthetic():
print(
"\n\n-- test_estimate_synthetic(): 'estimateH', uses: 'M_observed', 'planted_distribution_model_H', --"
)
# --- Parameters for graph
n = 1000
a = 1
h = 8
d = 25
k = 3
distribution = 'powerlaw'
exponent = -0.3
f = 0.05
print("n={}, a={},d={}, f={}".format(n, a, d, f))
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
print("H0:\n{}".format(H0))
# --- Create graph
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(
seed=RANDOMSEED
) # seeds the actually used numpy random generator; both are used and thus needed
W, Xd = planted_distribution_model_H(n,
alpha=alpha0,
H=H0,
d_out=d,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
X1, ind = replace_fraction_of_rows(X0, 1 - f)
# --- Print some neighbor statistics
M_vec = M_observed(W, X0, distance=3, NB=True)
print("\nNeighbor statistics in fully labeled graph:")
print("M^(1): direct neighbors:\n{}".format(M_vec[1]))
print("M^(2): distance-2 neighbors:\n{}".format(M_vec[2]))
print("M^(3): distance-3 neighbors:\n{}".format(M_vec[3]))
# --- MHE ---
print("\nMHE: Estimate H based on X0 (fully labeled graph):")
start = time.time()
H1 = estimateH(X0, W, method='MHE', variant=1)
H2 = estimateH(X0, W, method='MHE', variant=2)
H3 = estimateH(X0, W, method='MHE', variant=3)
time_est = time.time() - start
print("Estimated H based on X0 (MHE), variant 1:\n{}".format(H1))
print("Estimated H based on X0 (MHE), variant 2:\n{}".format(H2))
print("Estimated H based on X0 (MHE), variant 3:\n{}".format(H3))
print("Time for all three variants:{}".format(time_est))
print("\nMHE: Estimate H based on X1 with f={}:".format(f))
start = time.time()
H1 = estimateH(X1, W, method='MHE', variant=1)
H2 = estimateH(X1, W, method='MHE', variant=2)
H3 = estimateH(X1, W, method='MHE', variant=3)
time_est = time.time() - start
print("Estimated H based on X1 (MHE), variant 1:\n{}".format(H1))
print("Estimated H based on X1 (MHE), variant 2:\n{}".format(H2))
print("Estimated H based on X1 (MHE), variant 3:\n{}".format(H3))
print("Time for all three variants:{}".format(time_est))
print(
"\nMHE, variant=1: Estimate H based on X1 with f={}, but with initial correct vector:"
)
weight = [0, 0, 0, 0, 0] # ignored for MHE
initial_h0 = [0.1, 0.8, 0.1]
H5 = estimateH(X1, W, method='MHE', weights=weight)
H5_r = estimateH(X1, W, method='MHE', weights=weight, randomize=True)
H5_i = estimateH(X1,
W,
method='MHE',
weights=weight,
initial_H0=transform_hToH(initial_h0, 3))
print("Estimated H based on X5 only (MHE): \n{}".format(H5))
print("Estimated H based on X5 only (MHE), randomize:\n{}".format(H5_r))
print("Estimated H based on X5 only (MHE), initial=GT:\n{}".format(H5_i))
# --- DHE ---
print("\nDHE: Estimate H based on X1 with f={}:".format(f))
start = time.time()
H1 = estimateH(X1, W, method='DHE', variant=1, distance=1)
H2 = estimateH(X1, W, method='DHE', variant=2, distance=1)
H3 = estimateH(X1, W, method='DHE', variant=3, distance=1)
time_est = time.time() - start
print(
"Estimated H based on X1 (DHE, distance=1), variant 1:\n{}".format(H1))
print(
"Estimated H based on X1 (DHE, distance=1), variant 2:\n{}".format(H2))
print(
"Estimated H based on X1 (DHE, distance=1), variant 3:\n{}".format(H3))
print("Time for all three variants:{}".format(time_est))
# --- LHE ---
print("\nLHE: Estimate H based on X1 with f={}:".format(f))
start = time.time()
H1 = estimateH(X1, W, method='LHE')
time_est = time.time() - start
print("Estimated H based on X1 (LHE):\n{}".format(H1))
print("Time for LHE:{}".format(time_est))
# --- Baseline holdout method ---
f2 = 0.5
X2, ind2 = replace_fraction_of_rows(X0, 1 - f2)
print("\nHoldout method: Estimate H based on X2 with f={}):".format(f2))
start = time.time()
H2 = estimateH_baseline_serial(X2=X2,
ind=ind2,
W=W,
numberOfSplits=1,
numMax=10)
time_est = time.time() - start
print("Estimated H based on X2 (Holdout method) with f={}:\n{}".format(
f2, H2))
print("Time for Holdout method:{}".format(
time_est)) # TODO: result suggests this method does not work?
def run(choice,
variant,
create_data=False,
add_data=False,
create_graph=False,
create_fig=True,
show_plot=False,
create_pdf=False,
show_pdf=False,
shorten_length=False,
show_arrows=True):
"""main parameterized method to produce all figures.
Can be run from external jupyther notebook or method to produce all figures in PDF
"""
# -- Setup
CHOICE = choice # determines the CSV data file to use
VARIANT = variant # determines the variant of how the figures are plotted
CREATE_DATA = create_data # starts new CSV file and stores experimental timing results
ADD_DATA = add_data # adds data to existing file
CREATE_GRAPH = create_graph # creates the actual graph for experiments (stores W and X in CSV files)
SHOW_PDF = show_pdf
SHOW_PLOT = show_plot
CREATE_FIG = create_fig
CREATE_PDF = create_pdf
SHORTEN_LENGTH = shorten_length # to prune certain fraction of data to plot
SHOW_SCALING_LABELS = True # first entry in the legend is for the dashed line of scalability
SHOW_TITLE = True # show parameters in title of plot
SHOW_DCER_WITH_BOX = True # show DCER value in a extra box
LABEL_FONTSIZE = 16 # size of number labels in figure
SHOW_LINEAR = True # show dashed line for linear scaling
SHOW_ARROWS = show_arrows # show extra visual comparison of speed-up
csv_filename = 'Fig_Timing_{}.csv'.format(
CHOICE) # CSV filename includes CHOICE
filename = 'Fig_Timing_{}-{}'.format(
CHOICE, VARIANT) # PDF filename includes CHOICE and VARIANT
header = ['n', 'type', 'time']
if CREATE_DATA:
save_csv_record(join(data_directory, csv_filename),
header,
append=False)
# -- Default Graph parameters
distribution = 'powerlaw'
exponent = -0.3
k = 3
a = 1 # this value was erroneously set to 5 previously!!! TODO: fix everywhere else
# err = 0
avoidNeighbors = False
f = 0.1
est_EC = True # !!! TODO: for graph estimation
weights = 10
pyamg = False
convergencePercentage_W = None
alpha = 0
beta = 0
gamma = 0
s = 0.5
numMaxIt = 10
xtick_lab = [0.001, 0.01, 0.1, 1]
ytick_lab = np.arange(0, 1, 0.1)
xmin = 1e2
xmax = 1e8
# xmax = 1e6
ymin = 1e-3
ymax = 5e3
color_vec = [
"#4C72B0", "#55A868", "#8172B2", "#C44E52", "#CCB974", 'black',
'black', "#64B5CD", "black"
]
marker_vec = ['s', '^', 'x', 'o', 'None', 'None', 'None', 'None']
linestyle_vec = ['solid'] * 6 + ['dashed']
linewidth_vec = [3] * 3 + [4, 3, 4] + [3] * 7
SHOWMAXNUMBER = True
show_num_vec = ['MHE', 'LHE', 'DHE', 'DHEr', 'Holdout', 'prop', 'eps_max']
# %% -- Main Options
if CHOICE == 3:
n_vec = [
100, 200, 400, 800, 1600, 3200, 6400, 12800, 25600, 51200, 102400,
204800, 409600, 819200, 1638400, 3276800, 6553600
]
# # n_vec = [1638400] # graph: 12021 sec = 3.4h, 18600 sec = 5h, 21824 sec (34000 sec old laptop)
# # n_vec = [3276800] # graph: 49481 sec = 13.8h, 68145 sec (125233 sec old laptop)
# # n_vec = [6553600] # graph: 145020 sec = 40h
h = 8
d = 5
repeat_vec_vec = [[
50, 50, 50, 50, 50, 50, 50, 20, 10, 10, 5, 5, 5, 3, 3, 3, 3
], [5, 5, 5, 5, 3, 3, 3, 3, 3, 1,
1], [20, 20, 20, 10, 10, 10, 10, 10, 5, 5, 5, 3, 3, 1, 1, 1, 1]]
method_vec_vec = [['MHE', 'DHE', 'DHEr', 'LHE'], ['Holdout'], ['prop']]
if VARIANT == 1:
method_vec_fig = ['MHE', 'LHE', 'DHE', 'DHEr', 'Holdout', 'prop']
label_vec = ['MCE', 'LCE', 'DCE', 'DCEr', 'Holdout', 'prop']
show_num_vec = ['MHE', 'LHE', 'DHE', 'DHEr', 'Holdout', 'prop']
if VARIANT == 2: # version used for main paper figure
method_vec_fig = ['MHE', 'LHE', 'DHE', 'DHEr', 'Holdout', 'prop']
label_vec = ['MCE', 'LCE', 'DCE', 'DCEr', 'Holdout', 'prop']
linestyle_vec = ['solid'] * 5 + ['dashed']
SHOW_ARROWS = False
if VARIANT == 3: # version used for main paper figure
method_vec_fig = ['DHEr', 'Holdout', 'prop']
label_vec = [
'DCEr', 'Holdout', 'Propagation', '$\epsilon_{\mathrm{max}}$'
]
linestyle_vec = ['solid'] * 2 + ['dashed']
color_vec = [
"#C44E52", "#CCB974", 'black', 'black', "#64B5CD", "black"
]
marker_vec = ['o', 'x', 'None', 'None', 'None']
linestyle_vec = ['solid'] * 3 + ['dashed']
linewidth_vec = [4, 3, 4] + [3] * 7
ymin = 1e-2
SHOW_ARROWS = True
if VARIANT == 4: # figure used in slides
method_vec_fig = ['prop']
label_vec = ['Propagation']
color_vec = ['black']
marker_vec = ['None']
linestyle_vec = ['solid'] * 1
linewidth_vec = [2]
ymin = 1e-2
SHOW_ARROWS = False
SHOW_SCALING_LABELS = False
SHOW_TITLE = False
SHOW_DCER_WITH_BOX = False
LABEL_FONTSIZE = 20
SHOW_LINEAR = False
if VARIANT == 5: # figure used in slides
method_vec_fig = ['prop', 'Holdout']
label_vec = ['Propagation', 'Baseline']
color_vec = ['black', "#CCB974"]
marker_vec = ['None', '^']
linestyle_vec = ['solid'] * 2
linewidth_vec = [2, 4]
ymin = 1e-2
SHOW_ARROWS = True
SHOW_SCALING_LABELS = False
SHOW_TITLE = False
SHOW_DCER_WITH_BOX = False
LABEL_FONTSIZE = 20
SHOW_LINEAR = False
if VARIANT == 6: # figure used in slides
method_vec_fig = ['prop', 'Holdout', 'DHEr']
label_vec = ['Propagation', 'Baseline', 'Our method']
color_vec = ['black', "#CCB974", "#C44E52"]
marker_vec = ['None', '^', 'o', 'None', 'None']
linestyle_vec = ['solid'] + ['solid'] * 2
linewidth_vec = [2, 4, 4]
ymin = 1e-2
SHOW_ARROWS = True
SHOW_SCALING_LABELS = False
SHOW_TITLE = True
SHOW_DCER_WITH_BOX = False
LABEL_FONTSIZE = 20
SHOW_LINEAR = False
graph_cvs = 'Fig_Timing_SSLH_1' # re-use existing large graphs
elif CHOICE == 4:
n_vec = [
200,
400,
800,
1600,
3200,
6400,
12800,
25600,
51200,
102400,
204800,
409600,
819200,
]
# n_vec = [819200] # graph: 47905 sec = 13.3h. 90562 sec = 25h (180527 sec old laptop)
h = 3
d = 25
repeat_vec_vec = [[
50,
50,
50,
50,
50,
50,
20,
10,
10,
5,
3,
3,
3,
], [5, 5, 5, 3, 1, 1, 1, 1, 1],
[
20,
20,
10,
10,
10,
10,
10,
5,
5,
5,
1,
1,
1,
]]
method_vec_vec = [['MHE', 'DHE', 'DHEr', 'LHE'], ['Holdout'], ['prop']]
VARIANT = 2
if VARIANT == 1:
method_vec_fig = [
'MHE', 'LHE', 'DHE', 'DHEr', 'Holdout', 'prop', 'eps_max'
]
label_vec = [
'MCE', 'LCE', 'DCE', 'DCEr', 'Holdout', 'prop',
'$\epsilon_{\mathrm{max}}$'
]
show_num_vec = [
'MHE', 'LHE', 'DHE', 'DHEr', 'Holdout', 'prop', 'eps_max'
]
if VARIANT == 2:
method_vec_fig = ['MHE', 'LHE', 'DHE', 'DHEr', 'Holdout', 'prop']
label_vec = ['MCE', 'LCE', 'DCE', 'DCEr', 'Holdout', 'prop']
linestyle_vec = ['solid'] * 5 + ['dashed']
if VARIANT == 3:
method_vec_fig = ['DHEr', 'Holdout', 'prop']
label_vec = [
'DCEr', 'Holdout', 'Propagation', '$\epsilon_{\mathrm{max}}$'
]
linestyle_vec = ['solid'] * 2 + ['dashed']
color_vec = [
"#C44E52", "#CCB974", 'black', 'black', "#64B5CD", "black"
]
marker_vec = ['o', 'x', 'None', 'None', 'None']
linestyle_vec = ['solid'] * 3 + ['dashed']
linewidth_vec = [4, 3, 4] + [3] * 7
ymin = 1e-2
graph_cvs = 'Fig_Timing_SSLH_2' # re-use existing large graphs
xmin = 1e3
xmax = 5e7
ymax = 1e3
elif CHOICE == 2:
# rep_Estimation = 10
# n_vec = [200, 400, 800, 1600, 3200, 6400, 12800,
# 25600, 51200, 102400, 204800, 409600, 819200]
# repeat_vec = [20, 20, 20, 20, 20, 10, 10,
# 10, 10, 10, 5, 5, 1]
# n_vec = [819200] # graph: 47905 sec = 13.3h. 90562 sec = 25h (180527 sec old laptop)
n_vec = [1638400] # !!! not done yet
repeat_vec = [1]
h = 3
d = 25
xmax = 5e7
graph_cvs = 'Fig_Timing_SSLH_2'
elif CHOICE == 10: # same as 3 but with difference bars
n_vec = [
100, 200, 400, 800, 1600, 3200, 6400, 12800, 25600, 51200, 102400,
204800, 409600, 819200, 1638400, 3276800, 6553600
]
# # n_vec = [1638400] # graph: 12021 sec = 3.4h, 18600 sec = 5h, 21824 sec (34000 sec old laptop)
# # n_vec = [3276800] # graph: 49481 sec = 13.8h, 68145 sec (125233 sec old laptop)
# # n_vec = [6553600] # graph: 145020 sec = 40h
h = 8
d = 5
repeat_vec_vec = [[
50, 50, 50, 50, 50, 50, 50, 20, 10, 10, 5, 5, 5, 3, 3, 3, 3
], [5, 5, 5, 5, 3, 3, 3, 3, 3, 1,
1], [20, 20, 20, 10, 10, 10, 10, 10, 5, 5, 5, 3, 3, 1, 1, 1, 1]]
method_vec_vec = [['MHE', 'DHE', 'DHEr', 'LHE'], ['Holdout'], ['prop']]
method_vec_fig = ['DHEr', 'Holdout', 'prop']
label_vec = [
'DCEr', 'Holdout', 'Propagation', '$\epsilon_{\mathrm{max}}$'
]
linestyle_vec = ['solid'] * 2 + ['dashed']
color_vec = [
"#C44E52", "#CCB974", 'black', 'black', "#64B5CD", "black"
]
marker_vec = ['o', 'x', 'None', 'None', 'None']
linestyle_vec = ['solid'] * 3 + ['dashed']
linewidth_vec = [4, 3, 4] + [3] * 7
ymin = 1e-2
graph_cvs = 'Fig_Timing_SSLH_1' # re-use existing large graphs
else:
raise Warning("Incorrect choice!")
# %% -- Common options
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
H0c = to_centering_beliefs(H0)
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(
seed=RANDOMSEED
) # seeds the actually used numpy random generator; both are used and thus needed
# print("CHOICE: {}".format(CHOICE))
def save_tuple(n, label, time):
tuple = [str(datetime.datetime.now())]
text = [n, label, time]
tuple.extend(text)
print("time potential {}: {}".format(label, time))
save_csv_record(join(data_directory, csv_filename), tuple)
# %% -- Create data
if CREATE_DATA or ADD_DATA:
for repeat_vec, method_vec in zip(repeat_vec_vec, method_vec_vec):
for n, repeat in zip(n_vec, repeat_vec):
print("\nn: {}".format(n))
# repeat = repeat_vec[j]
# -- Graph
if CREATE_GRAPH:
start = time.time()
W, Xd = planted_distribution_model(
n,
alpha=alpha0,
P=H0,
m=d * n,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
time_graph = time.time() - start
save_W(join(data_directory,
'{}_{}_W.csv'.format(graph_cvs, n)),
W,
saveWeights=False)
save_X(
join(data_directory,
'{}_{}_X.csv'.format(graph_cvs, n)), X0)
save_tuple(n, 'graph', time_graph)
else:
W, _ = load_W(join(data_directory,
'{}_{}_W.csv'.format(graph_cvs, n)),
skiprows=1,
zeroindexing=True,
n=None,
doubleUndirected=False)
X0, _, _ = load_X(join(data_directory,
'{}_{}_X.csv'.format(graph_cvs, n)),
n=None,
k=None,
skiprows=1,
zeroindexing=True)
# -- Repeat loop
for i in range(repeat):
print("\n repeat: {}".format(i))
X2, ind = replace_fraction_of_rows(
X0, 1 - f, avoidNeighbors=avoidNeighbors, W=W)
for method in method_vec:
if method == 'DHE':
start = time.time()
H2 = estimateH(X2,
W,
method='DHE',
variant=1,
distance=5,
EC=est_EC,
weights=weights)
time_est = time.time() - start
save_tuple(n, 'DHE', time_est)
elif method == 'DHEr':
start = time.time()
H2 = estimateH(X2,
W,
method='DHE',
variant=1,
distance=5,
EC=est_EC,
weights=weights,
randomize=True)
time_est = time.time() - start
save_tuple(n, 'DHEr', time_est)
elif method == 'MHE':
start = time.time()
H2 = estimateH(X2,
W,
method='MHE',
variant=1,
distance=1,
EC=est_EC,
weights=None)
time_est = time.time() - start
save_tuple(n, 'MHE', time_est)
elif method == 'LHE':
start = time.time()
H2 = estimateH(X2,
W,
method='LHE',
variant=1,
distance=1,
EC=est_EC,
weights=None)
time_est = time.time() - start
save_tuple(n, 'LHE', time_est)
elif method == 'Holdout':
start = time.time()
H2 = estimateH_baseline_serial(
X2,
ind,
W,
numMax=numMaxIt,
numberOfSplits=1,
# EC=EC,
# weights=weight,
alpha=alpha,
beta=beta,
gamma=gamma)
time_est = time.time() - start
save_tuple(n, 'Holdout', time_est)
elif method == 'prop':
H2c = to_centering_beliefs(H0)
X2c = to_centering_beliefs(
X2, ignoreZeroRows=True) # try without
start = time.time()
eps_max = eps_convergence_linbp_parameterized(
H2c,
W,
method='noecho',
alpha=alpha,
beta=beta,
gamma=gamma,
X=X2,
pyamg=pyamg)
time_eps_max = time.time() - start
save_tuple(n, 'eps_max', time_eps_max)
# -- Propagate
eps = s * eps_max
try:
start = time.time()
F, actualIt, actualPercentageConverged = \
linBP_symmetric_parameterized(X2, W, H2c * eps,
method='noecho',
alpha=alpha, beta=beta, gamma=gamma,
numMaxIt=numMaxIt,
convergencePercentage=convergencePercentage_W,
debug=2)
time_prop = time.time() - start
except ValueError as e:
print("ERROR: {}: d={}, h={}".format(e, d, h))
else:
save_tuple(n, 'prop', time_prop)
else:
raise Warning("Incorrect choice!")
# %% -- Read, aggregate, and pivot data for all options
df1 = pd.read_csv(join(data_directory, csv_filename))
# print("\n-- df1: (length {}):\n{}".format(len(df1.index), df1.head(50)))
# Aggregate repetitions
df2 = df1.groupby(['n', 'type']).agg \
({'time': [np.mean, np.median, np.std, np.size], # Multiple Aggregates
})
df2.columns = ['_'.join(col).strip() for col in df2.columns.values
] # flatten the column hierarchy
df2.reset_index(inplace=True) # remove the index hierarchy
df2.rename(columns={'time_size': 'count'}, inplace=True)
# print("\n-- df2 (length {}):\n{}".format(len(df2.index), df2.head(15)))
# Pivot table
df3 = pd.pivot_table(df2,
index=['n'],
columns=['type'],
values=['time_mean', 'time_median']) # Pivot
# df3 = pd.pivot_table(df2, index=['n'], columns=['type'], values=['time_mean', 'time_median', 'time_std'] ) # Pivot
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
df3.columns = ['_'.join(col).strip() for col in df3.columns.values
] # flatten the column hierarchy
df3.reset_index(inplace=True) # remove the index hierarchy
# df2.rename(columns={'time_size': 'count'}, inplace=True)
# print("\n-- df3 (length {}):\n{}".format(len(df3.index), df3.head(30)))
# Extract values
X = df3['n'].values # plot x values
X = X * d / 2 # calculate edges (!!! notice dividing by 2 as one edge appears twice in symmetric adjacency matrix)
Y = {}
for method in method_vec_fig:
# Y[method] = df3['time_mean_{}'.format(method)].values
Y[method] = df3['time_median_{}'.format(method)].values
if SHORTEN_LENGTH:
SHORT_FACTOR = 4 ## KEEP EVERY Nth ELEMENT
X = np.copy(X[list(range(0, len(X), SHORT_FACTOR)), ])
for method in method_vec_fig:
Y[method] = np.copy(
Y[method][list(range(0, len(Y[method]), SHORT_FACTOR)), ])
# %% -- Figure
if CREATE_FIG:
fig_filename = '{}.pdf'.format(
filename) # TODO: repeat pattern in other files
mpl.rcParams['backend'] = 'agg'
mpl.rcParams['lines.linewidth'] = 3
mpl.rcParams['font.size'] = LABEL_FONTSIZE
mpl.rcParams['axes.labelsize'] = 20
mpl.rcParams['axes.titlesize'] = 16
mpl.rcParams['xtick.labelsize'] = 16
mpl.rcParams['ytick.labelsize'] = 16
mpl.rcParams['legend.fontsize'] = 12
mpl.rcParams['axes.edgecolor'] = '111111' # axes edge color
mpl.rcParams['grid.color'] = '777777' # grid color
mpl.rcParams['figure.figsize'] = [4, 4]
mpl.rcParams[
'xtick.major.pad'] = 4 # padding of tick labels: default = 4
mpl.rcParams[
'ytick.major.pad'] = 4 # padding of tick labels: default = 4
fig = plt.figure()
ax = fig.add_axes([0.13, 0.17, 0.8, 0.8])
# -- Draw the plots
if SHOW_LINEAR:
ax.plot([1, 1e8], [1e-5, 1e3],
linewidth=1,
color='gray',
linestyle='dashed',
label='1sec/100k edges',
clip_on=True,
zorder=3)
for i, (method, color, marker, linewidth, linestyle) in enumerate(
zip(method_vec_fig, color_vec, marker_vec, linewidth_vec,
linestyle_vec)):
ax.plot(X,
Y[method],
linewidth=linewidth,
color=color,
linestyle=linestyle,
label=label_vec[i],
clip_on=True,
marker=marker,
markersize=6,
markeredgewidth=1,
markeredgecolor='black',
zorder=4)
# for choice, (option, label, color, linewidth, clip_on, linestyle, marker, markersize) in \
# enumerate(zip(option_vec, labels, facecolor_vec, linewidth_vec, clip_on_vec, linestyle_vec, marker_vec, markersize_vec)):
# P = ax.plot(X_f, Y[choice], linewidth=linewidth, color=color, linestyle=linestyle, label=label, zorder=4, marker=marker,
# markersize=markersize, markeredgewidth=1, markeredgecolor='black', clip_on=clip_on)
if SHOWMAXNUMBER and method in show_num_vec:
if method == 'DHEr' and SHOW_DCER_WITH_BOX:
j = np.argmax(np.ma.masked_invalid(
Y[method])) # mask nan, then get index of max element
ax.annotate(int(np.round(Y[method][j])),
xy=(X[j] * 1.5, Y[method][j]),
color=color,
va='center',
bbox=dict(boxstyle="round,pad=0.3", fc="w"),
annotation_clip=False,
zorder=5)
else:
j = np.argmax(np.ma.masked_invalid(
Y[method])) # mask nan, then get index of max element
ax.annotate(int(np.round(Y[method][j])),
xy=(X[j] * 1.5, Y[method][j]),
color=color,
va='center',
annotation_clip=False,
zorder=5)
if SHOW_ARROWS:
dce_opt = 'DHEr'
holdout_opt = 'Holdout'
prop_opt = 'prop'
j_holdout = np.argmax(np.ma.masked_invalid(Y[holdout_opt]))
if dce_opt in Y:
j_dce = np.argmax(np.ma.masked_invalid(Y[dce_opt]))
ax.annotate(s='',
xy=(X[j_dce], Y[prop_opt][j_dce]),
xytext=(X[j_dce], Y[dce_opt][j_dce]),
arrowprops=dict(arrowstyle='<->'))
ax.annotate(
str(int(np.round(Y[prop_opt][j_dce] / Y[dce_opt][j_dce])))
+ 'x',
xy=(X[j_dce],
int(Y[prop_opt][j_dce] + Y[dce_opt][j_dce]) / 6),
color='black',
va='center',
fontsize=14,
# bbox = dict(boxstyle="round,pad=0.3", fc="w"),
annotation_clip=False,
zorder=5)
ax.annotate(s='',
xy=(X[j_holdout], Y[holdout_opt][j_holdout]),
xytext=(X[j_holdout], Y[dce_opt][j_holdout]),
arrowprops=dict(arrowstyle='<->'))
ax.annotate(
str(
int(
np.round(Y[holdout_opt][j_holdout] /
Y[dce_opt][j_holdout]))) + 'x',
xy=(X[j_holdout],
int(Y[holdout_opt][j_holdout] + Y[dce_opt][j_holdout])
/ 8),
color='black',
va='center',
fontsize=14,
# bbox = dict(boxstyle="round,pad=0.3", fc="w"),
annotation_clip=False,
zorder=5)
else: # in case dce_opt not shown, then show arrow as compared to prop method
ax.annotate(s='',
xy=(X[j_holdout], Y[holdout_opt][j_holdout]),
xytext=(X[j_holdout], Y[prop_opt][j_holdout]),
arrowprops=dict(arrowstyle='<->'))
ax.annotate(
str(
int(
np.round(Y[holdout_opt][j_holdout] /
Y[prop_opt][j_holdout]))) + 'x',
xy=(X[j_holdout],
int(Y[holdout_opt][j_holdout] + Y[prop_opt][j_holdout])
/ 8),
color='black',
va='center',
fontsize=14,
# bbox = dict(boxstyle="round,pad=0.3", fc="w"),
annotation_clip=False,
zorder=5)
if SHOW_TITLE:
plt.title(r'$\!\!\!d\!=\!{}, h\!=\!{}$'.format(d, h))
handles, labels = ax.get_legend_handles_labels()
if not SHOW_SCALING_LABELS and SHOW_LINEAR:
handles = handles[1:]
labels = labels[1:]
legend = plt.legend(
handles,
labels,
loc='upper left', # 'upper right'
handlelength=2,
labelspacing=0, # distance between label entries
handletextpad=
0.3, # distance between label and the line representation
borderaxespad=0.2, # distance between legend and the outer axes
borderpad=0.3, # padding inside legend box
numpoints=1, # put the marker only once
)
legend.set_zorder(3)
frame = legend.get_frame()
frame.set_linewidth(0.0)
frame.set_alpha(0.2) # 0.8
# -- Figure settings and save
plt.minorticks_on()
plt.xscale('log')
plt.yscale('log')
minorLocator = LogLocator(
base=10, subs=[0.1 * n for n in range(1, 10)], numticks=40
) # TODO: discuss with Paul trick that helped with grid lines last time; necessary in order to create the log locators (otherwise does now show the wanted ticks
# ax.xaxis.set_minor_locator(minorLocator)
plt.xticks([1e2, 1e3, 1e4, 1e5, 1e6, 1e7, 1e8, 1e9])
plt.grid(True,
which='both',
axis='both',
alpha=0.2,
linestyle='-',
linewidth=1,
zorder=1) # linestyle='dashed', which='minor', axis='y',
# grid(b=True, which='minor', axis='x', alpha=0.2, linestyle='solid', linewidth=0.5) # linestyle='dashed', which='minor', axis='y',
plt.xlabel(r'Number of edges ($m$)', labelpad=0) # labelpad=0
plt.ylabel(r'Time [sec]', labelpad=0)
plt.xlim(xmin, xmax)
plt.ylim(ymin, ymax)
# print(ax.get_xaxis().get_minor_locator())
if CREATE_PDF:
plt.savefig(
join(figure_directory, fig_filename),
format='pdf',
dpi=None,
edgecolor='w',
orientation='portrait',
transparent=False,
bbox_inches='tight',
pad_inches=0.05,
# frameon=None
)
if SHOW_PDF:
showfig(join(figure_directory,
fig_filename)) # shows actually created PDF
if SHOW_PLOT:
plt.show()
def test_gradient():
print(
"\n-- 'define_gradient_energy_H, define_energy_H, uses: planted_distribution_model_H, H_observed, M_observed, --"
)
# --- Parameters for graph
n = 1000
a = 1
h = 8
d = 25
k = 3
distribution = 'powerlaw'
exponent = -0.3
alpha0 = np.array([a, 1., 1.])
alpha0 = alpha0 / np.sum(alpha0)
H0 = create_parameterized_H(k, h, symmetric=True)
f = 0.5
print("Graph n={}, d={}, f={}".format(n, d, f))
print("H0:\n{}\n".format(H0))
# --- Create graph
RANDOMSEED = None # For repeatability
random.seed(RANDOMSEED) # seeds some other python random generator
np.random.seed(
seed=RANDOMSEED
) # seeds the actually used numpy random generator; both are used and thus needed
W, Xd = planted_distribution_model_H(n,
alpha=alpha0,
H=H0,
d_out=d,
distribution=distribution,
exponent=exponent,
directed=False,
debug=False)
X0 = from_dictionary_beliefs(Xd)
X1, ind = replace_fraction_of_rows(X0, 1 - f)
# --- M_vec, H_vec statistics
distance = 5
print("M_vec:")
M_vec = M_observed(W, X1, distance=distance)
for i, M in enumerate(M_vec):
print("{}:\n{}".format(i, M))
print("H_vec:")
H_vec = H_observed(W, X1, distance=distance)
for i, H in enumerate(H_vec):
print("{}:\n{}".format(i, H))
# --- Gradient at multiple points for distance 1
print("\n=Defining the gradient function with distance 1")
distance = 1
weights = [1, 0, 0, 0, 0]
gradient_energy_H = define_gradient_energy_H(H_vec_observed=H_vec,
weights=weights,
distance=distance)
energy_H = define_energy_H(weights=weights,
distance=1,
H_vec_observed=H_vec)
H_actual = H_vec[0]
print(
"1st example point: H_actual (row-stochastic frequencies of neighbors):\n{}"
.format(H_actual))
e = energy_H(H_actual)
g = gradient_energy_H(H_actual)
h = derivative_H_to_h(g)
print("energy: ", e)
print("gradient:\n{}".format(g))
print("projected gradient: ", h)
H_point = transform_hToH(np.array([0.2, 0.6, 0.2]), 3)
print("\n2nd example point: H_point:\n{}".format(H_point))
e = energy_H(H_point)
g = gradient_energy_H(H_point)
h = derivative_H_to_h(g)
print("energy: ", e)
print("gradient:\n{}".format(g))
print("projected gradient: ", h)
H_point2 = H_point - 0.45 * g
print(
"\n3rd example point in opposite direction of gradient: H_point2=H_point-0.45*gradient:\n{}"
.format(H_point2))
e = energy_H(H_point2)
g = gradient_energy_H(H_point2)
h = derivative_H_to_h(g)
print("energy: ", e)
print("gradient:\n{}".format(g))
print("projected gradient: ", h)
# --- Gradient at multiple points for distance 5
distance = 5
weights = [0, 0, 0, 0, 1]
print("\n= Defining the gradient function with distance={} and weights={}".
format(distance, weights))
gradient_energy_H = define_gradient_energy_H(H_vec_observed=H_vec,
weights=weights,
distance=distance)
energy_H = define_energy_H(weights=weights,
distance=1,
H_vec_observed=H_vec)
H_actual = H_vec[0]
print("1st point: H_actual:\n{}".format(H_actual))
e = energy_H(H_actual)
g = gradient_energy_H(H_actual)
h = derivative_H_to_h(g)
print("energy: ", e)
print("gradient:\n{}".format(g))
print("projected gradient: ", h)
H_point = transform_hToH(np.array([0.2, 0.6, 0.2]), 3)
print("\n2nd point: H_point:\n{}".format(H_point))
e = energy_H(H_point)
g = gradient_energy_H(H_point)
h = derivative_H_to_h(g)
print("energy: ", e)
print("gradient:\n{}".format(g))
print("projected gradient: ", h)
H_point2 = H_point - 1.5 * g
print(
"\n3rd point in opposite direction of gradient: H_point2:\n{}".format(
H_point2))
e = energy_H(H_point2)
g = gradient_energy_H(H_point2)
h = derivative_H_to_h(g)
print("energy: ", e)
print("gradient:\n{}".format(g))
print("projected gradient: ", h)
