del commongenes
# discard bad columns
tobediscarded = np.logical_or.reduce(
((gene_atb.matrix != 0).sum(axis=0) < 3,
(gene_atb.matrix == 0).sum(axis=0) < 3,
np.isnan(gene_atb.matrix).any(axis=0)))
gene_atb.discard(tobediscarded, axis=1)
tobediscarded = np.logical_or((gene_cst.matrix != 0).sum(axis=0) < 3,
np.isnan(gene_cst.matrix).any(axis=0))
gene_cst.discard(tobediscarded, axis=1)
if gene_atb.shape[0] == 0 or gene_atb.shape[1] == 0 or gene_cst.shape[
0] == 0 or gene_cst.shape[1] == 0:
continue
# arbitrary prioritization to break redundancyindex ties later
gene_atb.columnmeta[
'arbitrary_pvalues'] = featureselection.univariate_chisquare(
X=gene_atb.matrix, Y=gene_cst.matrix[:, 0] < 0.2)[1]
tobediscarded = np.isnan(gene_atb.columnmeta['arbitrary_pvalues'])
gene_atb.discard(tobediscarded, axis=1)
if gene_atb.shape[0] == 0 or gene_atb.shape[1] == 0:
continue
# discard redundant features
rowstatpreferredorder = np.array(['mean', 'stdv'], dtype='object')
atb_atb = atb_atb.tolabels(gene_atb.columnlabels, gene_atb.columnlabels)
atb_atb.rowmeta = copy.deepcopy(gene_atb.columnmeta)
atb_atb.columnmeta = copy.deepcopy(gene_atb.columnmeta)
redundancyindex = (np.abs(atb_atb.matrix) >
similarity_threshold).sum(1).astype('float64')
for i, rowstat in enumerate(rowstatpreferredorder):
if rowstat in atb_atb.rowlabels:
redundancyindex[atb_atb.rowlabels == rowstat] += 1 / (2 + i)
table = list(
tobediscarded = np.logical_or((gene_atb.matrix != 0).sum(axis=0) < 3,
np.isnan(gene_atb.matrix).any(axis=0))
gene_atb.discard(tobediscarded, axis=1)
tobediscarded = np.logical_or((gene_cst.matrix != 0).sum(axis=0) < 3,
np.isnan(gene_cst.matrix).any(axis=0))
gene_cst.discard(tobediscarded, axis=1)
if gene_atb.shape[0] == 0 or gene_atb.shape[1] == 0 or gene_cst.shape[
0] == 0 or gene_cst.shape[1] == 0:
continue
# arbitrary prioritization to break redundancyindex ties later
gene_atb.columnmeta['arbitrary_pvalues'] = np.zeros(gene_atb.shape[1],
dtype='float64')
gene_atb.columnmeta['arbitrary_pvalues'][
~gene_atb.
columnmeta['isrowstat']] = featureselection.univariate_chisquare(
X=gene_atb.matrix[:, ~gene_atb.columnmeta['isrowstat']],
Y=gene_cst.select([], '0'))[1]
gene_atb.columnmeta['arbitrary_pvalues'][
gene_atb.columnmeta['isrowstat']] = featureselection.univariate_utest(
X=gene_atb.matrix[:, gene_atb.columnmeta['isrowstat']],
Y=gene_cst.select([], '0'))[1]
tobediscarded = np.isnan(gene_atb.columnmeta['arbitrary_pvalues'])
gene_atb.discard(tobediscarded, axis=1)
if gene_atb.shape[0] == 0 or gene_atb.shape[1] == 0:
continue
# discard redundant features
rowstatpreferredorder = np.array(['mean', 'stdv'], dtype='object')
atb_atb = atb_atb.tolabels(gene_atb.columnlabels, gene_atb.columnlabels)
atb_atb.rowmeta = copy.deepcopy(gene_atb.columnmeta)
atb_atb.columnmeta = copy.deepcopy(gene_atb.columnmeta)
redundancyindex = (np.abs(atb_atb.matrix) >