def homo_mustach(self, frame):
""" Hmophily mustach
"""
if self.model is None: return
expe = self.expe
figs = []
Y = self._Y
N = Y[0].shape[0]
model = self.model
if not hasattr(self.gramexp, 'tables'):
corpuses = self.specname(self.gramexp.get_set('corpus'))
models = self.gramexp.get_set('model')
tables = {}
corpuses = self.specname(self.gramexp.get_set('corpus'))
for m in models:
sim = ['natural', 'latent']
Meas = ['links', 'non-links']
table = {
'natural': {
'links': [],
'non-links': []
},
'latent': {
'links': [],
'non-links': []
}
}
tables[m] = table
self.gramexp.Meas = Meas
self.gramexp.tables = tables
table = tables[expe.model]
else:
table = self.gramexp.tables[expe.model]
Meas = self.gramexp.Meas
### Global degree
d, dc, yerr = random_degree(Y)
sim_nat = model.similarity_matrix(sim='natural')
sim_lat = model.similarity_matrix(sim='latent')
step_tab = len(self.specname(self.gramexp.get_set('corpus')))
if not hasattr(self.gramexp._figs[expe.model], 'damax'):
damax = -np.inf
else:
damax = self.gramexp._figs[expe.model].damax
self.gramexp._figs[expe.model].damax = max(sim_nat.max(),
sim_lat.max(), damax)
for it_dat, data in enumerate(Y):
#homo_object = data
#homo_object = model.likelihood()
table['natural']['links'].extend(sim_nat[data == 1].tolist())
table['natural']['non-links'].extend(sim_nat[data == 0].tolist())
table['latent']['links'].extend(sim_lat[data == 1].tolist())
table['latent']['non-links'].extend(sim_lat[data == 0].tolist())
if self._it == self.expe_size - 1:
for _model, table in self.gramexp.tables.items():
ax = self.gramexp._figs[_model].fig.gca()
bp = ax.boxplot([table['natural']['links']],
widths=0.5,
positions=[1],
whis='range')
bp = ax.boxplot([table['natural']['non-links']],
widths=0.5,
positions=[2],
whis='range')
bp = ax.boxplot([table['latent']['links']],
widths=0.5,
positions=[4],
whis='range')
bp = ax.boxplot([table['latent']['non-links']],
widths=0.5,
positions=[5],
whis='range')
ax.set_ylabel('Similarity')
ax.set_xticks([1.5, 4.5])
ax.set_xticklabels(('natural', 'latent'), rotation=0)
ax.set_xlim(0, 6)
nbox = 4
top = self.gramexp._figs[_model].damax
pos = [1, 2, 4, 5]
upperLabels = ['linked', ' non-linked'] * 2
#weights = ['light', 'ultralight']
weights = ['normal', 'normal']
for tick in range(nbox):
ax.text(pos[tick],
top + top * 0.015,
upperLabels[tick],
horizontalalignment='center',
weight=weights[tick % 2])
print(_model)
t1 = sp.stats.ttest_ind(table['natural']['links'],
table['natural']['non-links'])
t2 = sp.stats.ttest_ind(table['latent']['links'],
table['latent']['non-links'])
print(t1)
print(t2)
def pvalue(self, _type='global'):
""" similar to zipf but compute pvalue and print table
Parameters
==========
_type: str in [global, local, feature]
"""
if self.model is None: return
expe = self.expe
figs = []
Y = self._Y
N = Y[0].shape[0]
model = self.model
Table, Meas = self.init_fit_tables(_type, Y)
self.log.info('using `%s\' burstiness' % _type)
if _type == 'global':
### Global degree
for it_dat, data in enumerate(Y):
d, dc = degree_hist(adj_to_degree(data), filter_zeros=True)
gof = gofit(d, dc)
if not gof:
continue
for i, v in enumerate(Meas):
Table[self.corpus_pos, i, it_dat] = gof[v]
elif _type == 'local':
### Z assignement method
a, b = model.get_params()
N, K = a.shape
print('theta shape: %s' % (str((N, K))))
now = Now()
if 'mmsb' in expe.model:
ZZ = []
for _i, _ in enumerate(Y):
#for _ in Y: # Do not reflect real local degree !
theta = self._Theta[_i]
phi = self._Phi[_i]
Z = np.empty((2, N, N))
order = np.arange(N**2).reshape((N, N))
if expe.symmetric:
triu = np.triu_indices(N)
order = order[triu]
else:
order = order.flatten()
order = zip(*np.unravel_index(order, (N, N)))
for i, j in order:
Z[0, i, j] = categorical(theta[i])
Z[1, i, j] = categorical(theta[j])
Z[0] = np.triu(Z[0]) + np.triu(Z[0], 1).T
Z[1] = np.triu(Z[1]) + np.triu(Z[1], 1).T
ZZ.append(Z)
self.log.info('Z formation %s second', nowDiff(now))
clustering = 'modularity'
comm = model.communities_analysis(data=Y[0], clustering=clustering)
print('clustering method: %s, active clusters ratio: %f' %
(clustering, len(comm['block_hist'] > 0) / K))
local_degree_c = {}
### Iterate over all classes couple
if expe.symmetric:
#k_perm = np.unique( map(list, map(set, itertools.product(np.unique(clusters) , repeat=2))))
k_perm = np.unique(
list(
map(
list,
map(
list,
map(set, itertools.product(range(K),
repeat=2))))))
else:
#k_perm = itertools.product(np.unique(clusters) , repeat=2)
k_perm = itertools.product(range(K), repeat=2)
for it_k, c in enumerate(k_perm):
if isinstance(c, (np.int64, np.float64)):
k = l = c
elif len(c) == 2:
# Stochastic Equivalence (extra class bind
k, l = c
#continue
else:
# Comunnities (intra class bind)
k = l = c.pop()
#if i > expe.limit_class:
# break
if k != l:
continue
degree_c = []
YY = []
if 'mmsb' in expe.model:
for y, z in zip(Y, ZZ): # take the len of ZZ if < Y
y_c = y.copy()
phi_c = np.zeros(y.shape)
# UNDIRECTED !
phi_c[(z[0] == k) &
(z[1] == l
)] = 1 #; phi_c[(z[0] == l) & (z[1] == k)] = 1
y_c[phi_c != 1] = 0
#degree_c += adj_to_degree(y_c).values()
#yerr= None
YY.append(y_c)
elif 'ilfm' in expe.model:
for _i, y in enumerate(Y):
theta = self._Theta[_i]
YY.append(
(y *
np.outer(theta[:, k], theta[:, l])).astype(int))
d, dc, yerr = random_degree(YY)
if len(d) == 0: continue
gof = gofit(d, dc)
if not gof:
continue
for i, v in enumerate(Meas):
Table[self.corpus_pos, i, it_k] = gof[v]
elif _type == 'feature':
raise NotImplementedError
if self._it == self.expe_size - 1:
for _model, table in self.gramexp.tables.items():
# Mean and standard deviation
table_mean = np.char.array(np.around(
table.mean(2), decimals=3)).astype("|S20")
table_std = np.char.array(np.around(table.std(2),
decimals=3)).astype("|S20")
table = table_mean + b' $\pm$ ' + table_std
# Table formatting
corpuses = self.specname(self.gramexp.get_set('corpus'))
table = np.column_stack((self.specname(corpuses), table))
tablefmt = 'simple'
table = tabulate(table,
headers=['__' + _model.upper() + '__'] + Meas,
tablefmt=tablefmt,
floatfmt='.3f')
print()
print(table)
if expe._write:
if expe._mode == 'predictive':
base = '%s_%s_%s' % (self.specname(
expe.corpus), self.specname(_model), _type)
else:
base = '%s_%s_%s' % ('MG', self.specname(_model),
_type)
self.write_frames(table, base=base, ext='md')
def h**o(self, _type='pearson', _sim='latent'):
""" Hmophily test -- table output
Parameters
==========
_type: similarity type in (contengency, pearson)
_sim: similarity metric in (natural, latent)
"""
if self.model is None: return
expe = self.expe
figs = []
Y = self._Y
N = Y[0].shape[0]
model = self.model
self.log.info('using `%s\' type' % _type)
if not hasattr(self.gramexp, 'tables'):
corpuses = self.specname(self.gramexp.get_set('corpus'))
models = self.gramexp.get_set('model')
tables = {}
corpuses = self.specname(self.gramexp.get_set('corpus'))
for m in models:
if _type == 'pearson':
Meas = ['pearson coeff', '2-tailed pvalue']
table = np.empty((len(corpuses), len(Meas), len(Y)))
elif _type == 'contingency':
Meas = ['natural', 'latent', 'natural', 'latent']
table = np.empty((2 * len(corpuses), len(Meas), len(Y)))
tables[m] = table
self.gramexp.Meas = Meas
self.gramexp.tables = tables
table = tables[expe.model]
else:
table = self.gramexp.tables[expe.model]
Meas = self.gramexp.Meas
if _type == 'pearson':
self.log.info('using `%s\' similarity' % _sim)
# No variance for link expecation !!!
Y = [Y[0]]
### Global degree
d, dc, yerr = random_degree(Y)
sim = model.similarity_matrix(sim=_sim)
#plot(sim, title='Similarity', sort=True)
#plot_degree(sim)
for it_dat, data in enumerate(Y):
#homo_object = data
homo_object = model.likelihood()
table[self.corpus_pos, :,
it_dat] = sp.stats.pearsonr(homo_object.flatten(),
sim.flatten())
elif _type == 'contingency':
### Global degree
d, dc, yerr = random_degree(Y)
sim_nat = model.similarity_matrix(sim='natural')
sim_lat = model.similarity_matrix(sim='latent')
step_tab = len(self.specname(self.gramexp.get_set('corpus')))
for it_dat, data in enumerate(Y):
#homo_object = data
homo_object = model.likelihood()
table[self.corpus_pos, 0, it_dat] = sim_nat[data == 1].mean()
table[self.corpus_pos, 1, it_dat] = sim_lat[data == 1].mean()
table[self.corpus_pos, 2, it_dat] = sim_nat[data == 1].var()
table[self.corpus_pos, 3, it_dat] = sim_lat[data == 1].var()
table[self.corpus_pos + step_tab, 0,
it_dat] = sim_nat[data == 0].mean()
table[self.corpus_pos + step_tab, 1,
it_dat] = sim_lat[data == 0].mean()
table[self.corpus_pos + step_tab, 2,
it_dat] = sim_nat[data == 0].var()
table[self.corpus_pos + step_tab, 3,
it_dat] = sim_lat[data == 0].var()
if self._it == self.expe_size - 1:
for _model, table in self.gramexp.tables.items():
# Function in (utils. ?)
# Mean and standard deviation
table_mean = np.char.array(np.around(
table.mean(2), decimals=3)).astype("|S20")
table_std = np.char.array(np.around(table.std(2),
decimals=3)).astype("|S20")
table = table_mean + b' $\pm$ ' + table_std
# Table formatting
corpuses = self.specname(self.gramexp.get_set('corpus'))
try:
table = np.column_stack((corpuses, table))
except:
table = np.column_stack((corpuses * 2, table))
tablefmt = 'simple' # 'latex'
table = tabulate(table,
headers=['__' + _model.upper() + '__'] + Meas,
tablefmt=tablefmt,
floatfmt='.3f')
print()
print(table)
if expe._write:
base = '%s_homo_%s' % (self.specname(_model), _type)
self.write_frames(table, base=base, ext='md')
def burstiness(self, _type='all'):
'''Zipf Analysis
(global burstiness) + local burstiness + feature burstiness
Parameters
----------
_type : str
type of burstiness to compute in ('global', 'local', 'feature', 'all')
'''
if self.model is None: return
expe = self.expe
figs = []
Y = self._Y
N = Y[0].shape[0]
model = self.model
if _type in ('global', 'all'):
# Global burstiness
d, dc, yerr = random_degree(Y)
fig = plt.figure()
title = 'global | %s, %s' % (self.specname(
expe.get('corpus')), self.specname(expe.model))
plot_degree_2((d, dc, yerr), logscale=True, title=title)
figs.append(plt.gcf())
if _type in ('local', 'all'):
# Local burstiness
print('Computing Local Preferential attachment')
a, b = model.get_params()
N, K = a.shape
print('theta shape: %s' % (str((N, K))))
now = Now()
if 'mmsb' in expe.model:
### Z assignement method #
ZZ = []
for _i, _ in enumerate(Y):
#for _ in Y: # Do not reflect real local degree !
theta = self._Theta[_i]
phi = self._Phi[_i]
Z = np.empty((2, N, N))
order = np.arange(N**2).reshape((N, N))
if expe.symmetric:
triu = np.triu_indices(N)
order = order[triu]
else:
order = order.flatten()
order = zip(*np.unravel_index(order, (N, N)))
for i, j in order:
Z[0, i, j] = categorical(theta[i])
Z[1, i, j] = categorical(theta[j])
Z[0] = np.triu(Z[0]) + np.triu(Z[0], 1).T
Z[1] = np.triu(Z[1]) + np.triu(Z[1], 1).T
ZZ.append(Z)
self.log.info('Z formation %s second' % nowDiff(now))
clustering = 'modularity'
comm = model.communities_analysis(data=Y[0], clustering=clustering)
print('clustering method: %s, active clusters ratio: %f' %
(clustering, len(comm['block_hist'] > 0) / K))
local_degree_c = {}
### Iterate over all classes couple
if expe.symmetric:
#k_perm = np.unique( map(list, map(set, itertools.product(np.unique(clusters) , repeat=2))))
k_perm = np.unique(
list(
map(
list,
map(
list,
map(set, itertools.product(range(K),
repeat=2))))))
else:
#k_perm = itertools.product(np.unique(clusters) , repeat=2)
k_perm = itertools.product(range(K), repeat=2)
fig = plt.figure()
for i, c in enumerate(k_perm):
if isinstance(c, (np.int64, np.float64)):
k = l = c
elif len(c) == 2:
# Stochastic Equivalence (outer class)
k, l = c
else:
# Comunnities (inner class)
k = l = c.pop()
#if i > expe.limit_class:
# break
if k != l:
continue
degree_c = []
YY = []
if 'mmsb' in expe.model:
for y, z in zip(Y, ZZ): # take the len of ZZ if < Y
y_c = np.zeros(y.shape)
phi_c = np.zeros(y.shape)
# UNDIRECTED !
phi_c[(z[0] == k) & (z[1] == l)] = 1
y_c = y * phi_c
#degree_c += adj_to_degree(y_c).values()
#yerr= None
YY.append(y_c)
elif 'ilfm' in expe.model: # or Corpus !
for _i, y in enumerate(Y):
theta = self._Theta[_i]
if theta.shape[1] <= max(k, l):
print('warning: not all block converted.')
continue
YY.append(
(y *
np.outer(theta[:, k], theta[:, l])).astype(int))
d, dc, yerr = random_degree(YY)
if len(d) == 0: continue
title = 'local | %s, %s' % (self.specname(
expe.get('corpus')), self.specname(expe.model))
plot_degree_2((d, dc, yerr),
logscale=True,
colors=True,
line=True,
title=title)
figs.append(plt.gcf())
# Blockmodel Analysis
#if _type in ('feature', 'all'):
# plt.figure()
# if 'mmsb' in expe.model:
# # Feature burstiness
# hist, label = clusters_hist(comm['clusters'])
# bins = len(hist)
# plt.bar(range(bins), hist)
# plt.xticks(np.arange(bins)+0.5, label)
# plt.xlabel('Class labels')
# plt.title('Blocks Size (max assignement)')
# elif 'ilfm' in expe.model:
# # Feature burstiness
# hist, label = sorted_perm(comm['block_hist'], reverse=True)
# bins = len(hist)
# plt.bar(range(bins), hist)
# plt.xticks(np.arange(bins)+0.5, label)
# plt.xlabel('Class labels')
# plt.title('Blocks Size (max assignement)')
# figs.append(plt.gcf())
if expe._write:
if expe._mode == 'predictive':
base = '%s_%s' % (self.specname(
expe.corpus), self.specname(expe.model))
else:
base = '%s_%s' % ('MG', self.specname(expe.model))
self.write_frames(figs, base=base)
return