def get_doc_vector(self, doc_index=None, doc_name=None, n_dim=None):
if n_dim is None:
n_dim = self.dimension
if doc_name is None:
td_column = self._get_doc_column(doc_index)
elif doc_index is None:
td_column = self._get_doc_column(self.ldocs.index(doc_name))
if n_dim == self.dimension:
sigma_inverse = [1 / s for s in self.sigma]
ut = transpose(self.u)
else:
sigma_inverse = [1 / s for s in self.plot_sigma]
ut = transpose(self.plot_u)
ut_d = matmul(ut, td_column)
doc_vector = [sigma_inverse[i] * ut_d[i] for i in range(n_dim)]
return doc_vector
def ccprmod(supports, idx_correct_label, B=20):
"""Python implementation of the ccprmod.m (Classifier competence based on probabilistic modelling)
function. Matlab code is available at:
http://www.mathworks.com/matlabcentral/mlc-downloads/downloads/submissions/28391/versions/6/previews/ccprmod.m/index.html
Parameters
----------
supports: array of shape = [n_samples, n_classes]
containing the supports obtained by the base classifier for each class.
idx_correct_label: array of shape = [n_samples]
containing the index of the correct class.
B : int (Default = 20)
number of points used in the calculation of the competence, higher values result
in a more accurate estimation.
Returns
-------
C_src : array of shape = [n_samples]
representing the classifier competences at each data point
Examples
--------
>>> supports = [[0.3, 0.6, 0.1],[1.0/3, 1.0/3, 1.0/3]]
>>> idx_correct_label = [1,0]
>>> ccprmod(supports,idx_correct_label)
ans = [0.784953394056843, 0.332872292262951]
References
----------
T.Woloszynski, M. Kurzynski, A probabilistic model of classifier competence for dynamic ensemble selection,
Pattern Recognition 44 (2011) 2656–2668.
"""
if not isinstance(B, int):
raise TypeError(
'Parameter B should be an integer. Currently B is {0}'.format(
type(B)))
if B <= 0 or B is None:
raise ValueError(
'The parameter B should be higher than 0. Currently B is {0}'.
format(B))
supports = np.asarray(supports)
idx_correct_label = np.array(idx_correct_label)
supports[supports > 1] = 1
N, C = supports.shape
x = np.linspace(0, 1, B)
x = np.matlib.repmat(x, N, C)
a = npm.zeros(x.shape)
for c in range(C):
a[:, c * B:(c + 1) * B] = C * supports[:, c:c + 1]
b = C - a
# For extreme cases, with a or b equal to 0, add a small constant:
eps = 1e-20
a[a == 0] = eps
b[b == 0] = eps
betaincj = betainc(a, b, x)
C_src = np.zeros(N)
for n in range(N):
t = range((idx_correct_label[n]) * B, (idx_correct_label[n] + 1) * B)
bc = betaincj[n, t]
bi = betaincj[n, list(set(range(0, (C * B))) - set(t))]
bi = npm.transpose(npm.reshape(bi, (B, C - 1), order='F'))
C_src[n] = np.sum(
np.multiply((bc[0, 1:] - bc[0, 0:-1]),
np.prod((bi[:, 0:-1] + bi[:, 1:]) / 2, 0)))
return C_src
def _find(mat):
return [p[0] for p in nm.transpose(nm.nonzero(mat)).tolist()]
#_________Label Data normalization______# not useful______________________________________________________
maxx2 = np.max(output_mat[:,0])
output_mat[:,0] = output_mat[:,0]/maxx2
print("\n Labels Data normalization done")
#_________________________________________________________________________________________________________
"""
#_________Important Features Extraction___________________________________________________________________
ip_mean = npmat.mean(input_mat, 0) # column means found out
ip_mean_mat = npmat.repmat(ip_mean, new_row,
1) # use repmat for creating matrix
ip_mean_sub = input_mat - ip_mean_mat # subtract mean from columns
ip_mat_cvar = (npmat.transpose(ip_mean_sub) *
ip_mean_sub) / my_row # covariance matrix
dg = np.diagonal(ip_mat_cvar) # variance
dg = np.sqrt(dg) # std dev
dg = npmat.matrix(dg) # matrix form conversion
scaled_cov = np.transpose(
dg) * dg # scaling the covariance to get Coorelation matrix
ip_mat_corel = np.divide(ip_mat_cvar, scaled_cov) # corelation input matrix
#plt.matshow(ip_mat_corel)
#plt.show()
corel_thresh = 1.00 # set threshold of corelation
unimp_feat = npmat.zeros((new_row, 1))
# initialize unimportant features matrix
unimp_count = 0
def _find(mat): return [p[0] for p in
nm.transpose(nm.nonzero(mat)).tolist()]
open_positions = _find(self.board.state == BLANK)