def test_setdiff1d(self):
a = np.array([6, 5, 4, 7, 1, 2, 7, 4])
b = np.array([2, 4, 3, 3, 2, 1, 5])
ec = np.array([6, 7])
c = setdiff1d(a, b)
assert_array_equal(c, ec)
a = np.arange(21)
b = np.arange(19)
ec = np.array([19, 20])
c = setdiff1d(a, b)
assert_array_equal(c, ec)
assert_array_equal([], setdiff1d([], []))
def test_setdiff1d(self):
a = np.array([6, 5, 4, 7, 1, 2, 7, 4])
b = np.array([2, 4, 3, 3, 2, 1, 5])
ec = np.array([6, 7])
c = setdiff1d(a, b)
assert_array_equal(c, ec)
a = np.arange(21)
b = np.arange(19)
ec = np.array([19, 20])
c = setdiff1d(a, b)
assert_array_equal(c, ec)
assert_array_equal([], setdiff1d([], []))
def setdiff1d(a, b):
"""
setdiff1d(a, b) returns the elements of a that are not in b.
"""
from MDSplus import Data
from numpy.lib.arraysetops import setdiff1d
return Data(setdiff1d(a.data(),b.data()))
def filter(self, u_ind, job_inds, return_appd=False):
'''
Removes the jobs the user has already applied to.
Parameters
----------
u_ind: int
The index in the User-Job application co-occur matrix
job_inds: list of ints
This is a list of job indices
return_appd: boolean
if True, return the jobs applied to by u_ind as well
Returns
-------
A filted list of job indices excluding the indices to jobs the user
has already applied for.
Optionally, returns the jobs the user applied to as well.
'''
applied_inds = nonzero(self.UserJobOccurs[u_ind,:])[1]
filtered = setdiff1d(job_inds,applied_inds)
if return_appd:
return filtered, applied_inds
else:
return filtered
def test_manyways(self):
a = np.array([5, 7, 1, 2, 8])
b = np.array([9, 8, 2, 4, 3, 1, 5])
c1 = setxor1d(a, b)
aux1 = intersect1d(a, b)
aux2 = union1d(a, b)
c2 = setdiff1d(aux2, aux1)
assert_array_equal(c1, c2)
def test_manyways(self):
a = np.array([5, 7, 1, 2, 8])
b = np.array([9, 8, 2, 4, 3, 1, 5])
c1 = setxor1d(a, b)
aux1 = intersect1d(a, b)
aux2 = union1d(a, b)
c2 = setdiff1d(aux2, aux1)
assert_array_equal(c1, c2)
def test_naive_aggregation(self):
for A in self.cases:
S = symmetric_strength_of_connection(A)
(expected, expected_Cpts) = reference_naive_aggregation(S)
(result, Cpts) = naive_aggregation(S)
assert_equal((result - expected).nnz, 0)
assert_equal(Cpts.shape[0], expected_Cpts.shape[0])
assert_equal(setdiff1d(Cpts, expected_Cpts).shape[0], 0)
def test_naive_aggregation(self):
for A in self.cases:
S = symmetric_strength_of_connection(A)
(expected,expected_Cpts) = reference_naive_aggregation(S)
(result,Cpts) = naive_aggregation(S)
assert_equal( (result - expected).nnz, 0 )
assert_equal( Cpts.shape[0], expected_Cpts.shape[0])
assert_equal( setdiff1d(Cpts, expected_Cpts).shape[0], 0)
def test_naive_aggregation(self):
for A in self.cases:
S = symmetric_strength_of_connection(A)
(expected, expected_Cpts) = reference_naive_aggregation(S)
(result, Cpts) = naive_aggregation(S)
assert_equal((result - expected).nnz, 0)
assert_equal(Cpts.shape[0], expected_Cpts.shape[0])
assert_equal(setdiff1d(Cpts, expected_Cpts).shape[0], 0)
# S is diagonal - no dofs aggregated
S = spdiags([[1, 1, 1, 1]], [0], 4, 4, format='csr')
(result, Cpts) = naive_aggregation(S)
expected = numpy.eye(4)
assert_equal(result.todense(), expected)
assert_equal(Cpts.shape[0], 4)
def test_naive_aggregation(self):
for A in self.cases:
S = symmetric_strength_of_connection(A)
(expected,expected_Cpts) = reference_naive_aggregation(S)
(result,Cpts) = naive_aggregation(S)
assert_equal( (result - expected).nnz, 0 )
assert_equal( Cpts.shape[0], expected_Cpts.shape[0])
assert_equal( setdiff1d(Cpts, expected_Cpts).shape[0], 0)
# S is diagonal - no dofs aggregated
S = spdiags([[1,1,1,1]],[0],4,4,format='csr')
(result, Cpts) = naive_aggregation(S)
expected = numpy.eye(4)
assert_equal(result.todense(),expected)
assert_equal(Cpts.shape[0], 4)
def test_setdiff1d_char_array(self):
a = np.array(['a', 'b', 'c'])
b = np.array(['a', 'b', 's'])
assert_array_equal(setdiff1d(a, b), np.array(['c']))
def test_setdiff1d_unique(self):
a = np.array([3, 2, 1])
b = np.array([7, 5, 2])
expected = np.array([3, 1])
actual = setdiff1d(a, b, assume_unique=True)
assert_equal(actual, expected)
def ghost_layer(submesh, mesh, p, tupper, tlower, parameters = None):
ncoord = mesh.number_of_nodes
ntriangles = mesh.number_of_triangles
if parameters is None:
layer_width = 2
else:
layer_width = parameters['ghost_layer_width']
full_ids = num.arange(tlower, tupper)
n0 = mesh.neighbours[full_ids, :]
n0 = num.unique(n0.flat)
n0 = num.extract(n0>=0,n0)
n0 = num.extract(num.logical_or(n0<tlower, tupper<= n0), n0)
layer_cells = {}
layer_cells[0] = n0
# Find the subsequent layers of ghost triangles
for i in range(layer_width-1):
# use previous layer as a start
n0 = mesh.neighbours[n0, :]
n0 = num.unique(n0.flat)
n0 = num.extract(n0>=0,n0)
n0 = num.extract(num.logical_or(n0<tlower, tupper<= n0), n0)
for j in xrange(i+1):
n0 = numset.setdiff1d(n0,layer_cells[j])
layer_cells[i+1] = n0
# Build the triangle list and make note of the vertices
new_trianglemap = layer_cells[0]
for i in range(layer_width-1):
new_trianglemap = numset.union1d(new_trianglemap,layer_cells[i+1])
new_subtriangles = num.concatenate((num.reshape(new_trianglemap, (-1,1)), mesh.triangles[new_trianglemap]), 1)
fullnodes = submesh["full_nodes"][p]
full_nodes_ids = num.array(fullnodes[:,0],num.int)
new_nodes = num.unique(mesh.triangles[new_trianglemap].flat)
new_nodes = numset.setdiff1d(new_nodes,full_nodes_ids)
new_subnodes = num.concatenate((num.reshape(new_nodes, (-1,1)), mesh.nodes[new_nodes]), 1)
# Clean up before exiting
del (new_nodes)
del (layer_cells)
del (n0)
del (new_trianglemap)
# Return the triangles and vertices sitting on the boundary layer
return new_subnodes, new_subtriangles, layer_width
def test_setdiff1d_char_array(self):
a = np.array(["a", "b", "c"])
b = np.array(["a", "b", "s"])
assert_array_equal(setdiff1d(a, b), np.array(["c"]))
def ghost_layer(submesh, mesh, p, tupper, tlower, parameters=None):
ncoord = mesh.number_of_nodes
ntriangles = mesh.number_of_triangles
if parameters is None:
layer_width = 2
else:
layer_width = parameters['ghost_layer_width']
full_ids = num.arange(tlower, tupper)
n0 = mesh.neighbours[full_ids, :]
n0 = num.unique(n0.flat)
n0 = num.extract(n0 >= 0, n0)
n0 = num.extract(num.logical_or(n0 < tlower, tupper <= n0), n0)
layer_cells = {}
layer_cells[0] = n0
# Find the subsequent layers of ghost triangles
for i in range(layer_width - 1):
# use previous layer as a start
n0 = mesh.neighbours[n0, :]
n0 = num.unique(n0.flat)
n0 = num.extract(n0 >= 0, n0)
n0 = num.extract(num.logical_or(n0 < tlower, tupper <= n0), n0)
for j in range(i + 1):
n0 = numset.setdiff1d(n0, layer_cells[j])
layer_cells[i + 1] = n0
# Build the triangle list and make note of the vertices
new_trianglemap = layer_cells[0]
for i in range(layer_width - 1):
new_trianglemap = numset.union1d(new_trianglemap, layer_cells[i + 1])
new_subtriangles = num.concatenate(
(num.reshape(new_trianglemap,
(-1, 1)), mesh.triangles[new_trianglemap]), 1)
fullnodes = submesh["full_nodes"][p]
full_nodes_ids = num.array(fullnodes[:, 0], num.int)
new_nodes = num.unique(mesh.triangles[new_trianglemap].flat)
new_nodes = numset.setdiff1d(new_nodes, full_nodes_ids)
new_subnodes = num.concatenate(
(num.reshape(new_nodes, (-1, 1)), mesh.nodes[new_nodes]), 1)
# Clean up before exiting
del (new_nodes)
del (layer_cells)
del (n0)
del (new_trianglemap)
# Return the triangles and vertices sitting on the boundary layer
return new_subnodes, new_subtriangles, layer_width
def test_setdiff1d_char_array(self):
a = np.array(['a', 'b', 'c'])
b = np.array(['a', 'b', 's'])
assert_array_equal(setdiff1d(a, b), np.array(['c']))
import matplotlib.pyplot as plt
import numpy.lib.arraysetops as aso
lr = linear_model.LinearRegression()
rcv = linear_model.RidgeCV()
boston = datasets.load_boston()
y = boston.target
# cross_val_predict returns an array of the same size as `y` where each entry
# is a prediction obtained by cross validation:
predicted = cross_val_predict(lr, boston.data, y, cv=10)
predicted2 = cross_val_predict(rcv, boston.data, y, cv=10)
print aso.setdiff1d(predicted, predicted2)
# which one is better?
print type(predicted2)
print rcv
fig, ax = plt.subplots()
ax.scatter(y, predicted)
ax.plot([y.min(), y.max()], [y.min(), y.max()], 'k--', lw=4)
ax.set_xlabel('Measured')
ax.set_ylabel('Predicted')
plt.show()
fig, ax = plt.subplots()
ax.scatter(y, predicted2)
def test_setdiff1d_unique(self):
a = np.array([3, 2, 1])
b = np.array([7, 5, 2])
expected = np.array([3, 1])
actual = setdiff1d(a, b, assume_unique=True)
assert_equal(actual, expected)
sys.exit(1)
file1, file2 = sys.argv[1:]
if os.path.isfile(file1) != True:
sys.stderr.write('\nERROR: file ' + file1 + ' not found\n')
sys.exit(1)
elif os.path.isfile(file2) != True:
sys.stderr.write('\nERROR: file ' + file2 + ' not found\n')
sys.exit(1)
#open the 2 files
var_file = pd.read_csv(file1, sep='\t', usecols=[0], chunksize=1000000)
annotation = pd.read_csv(file2, sep='\t', usecols=[0])
print 'Chunking the var matrix...'
for c in var_file:
#check if all the var in the var_file are in the geno_annotation file
diff = aso.setdiff1d(c.values, annotation.values)
print 'Check consistency between the var_file colnames chunk and the annotation file colnames'
#check consistency between var_file and geno_annotation file
if diff.shape[0] != 0:
for var in diff:
sys.stderr.write('\nERROR: variant ' + var +
' not found in the annotation file\n')
sys.exit(1)
else:
print 'OK!'
sys.exit(0)
