def save_corr_matrix(self, file_handle):
"""
saves the correlation matrix
"""
if self.column_order:
self.corr_matrix = self.corr_matrix[:, self.column_order][self.column_order]
self.labels = [self.labels[i] for i in self.column_order]
self.labels = [toString(x) for x in self.labels]
file_handle.write("\t'" + "'\t'".join(self.labels) + "'\n")
fmt = "\t".join(np.repeat('%.4f', self.corr_matrix.shape[1])) + "\n"
i = 0
for row in self.corr_matrix:
file_handle.write(
"'%s'\t" % self.labels[i] + fmt % tuple(row))
i += 1
def save_corr_matrix(self, file_handle):
"""
saves the correlation matrix
"""
if self.column_order:
self.corr_matrix = self.corr_matrix[:, self.column_order][self.column_order]
self.labels = [self.labels[i] for i in self.column_order]
self.labels = [toString(x) for x in self.labels]
file_handle.write("\t'" + "'\t'".join(self.labels) + "'\n")
fmt = "\t".join(np.repeat('%.4f', self.corr_matrix.shape[1])) + "\n"
i = 0
for row in self.corr_matrix:
file_handle.write(
"'%s'\t" % self.labels[i] + fmt % tuple(row))
i += 1
def __init__(self,
matrix_file,
corr_method=None,
labels=None,
remove_outliers=False,
skip_zeros=False,
log1p=False):
self.load_matrix(matrix_file)
self.skip_zeros = skip_zeros
self.corr_method = corr_method
self.corr_matrix = None # correlation matrix
self.column_order = None
self.rowCenter = False
if labels is not None:
# test that the length of labels
# corresponds to the length of
# samples
self.labels = labels
self.labels = [toString(x) for x in self.labels]
if self.matrix.shape[1] == 1:
# There's nothing that can be done with a single sample
sys.exit("\nPlease use a matrix with more than one sample\n")
if skip_zeros is True:
# remove rows containing only nans or zeros
# that could be unmappable regions.
self.remove_rows_of_zeros()
if remove_outliers is True:
# remove outliers, otherwise outliers will produce a very
# high pearson correlation. Unnecessary for spearman correlation
self.remove_outliers()
if log1p is True:
self.matrix = np.log1p(self.matrix)
if corr_method:
self.compute_correlation()
def __init__(self, matrix_file,
corr_method=None,
labels=None,
remove_outliers=False,
skip_zeros=False,
log1p=False):
self.load_matrix(matrix_file)
self.skip_zeros = skip_zeros
self.corr_method = corr_method
self.corr_matrix = None # correlation matrix
self.column_order = None
self.rowCenter = False
if labels is not None:
# test that the length of labels
# corresponds to the length of
# samples
self.labels = labels
self.labels = [toString(x) for x in self.labels]
if self.matrix.shape[1] == 1:
# There's nothing that can be done with a single sample
sys.exit("\nPlease use a matrix with more than one sample\n")
if skip_zeros is True:
# remove rows containing only nans or zeros
# that could be unmappable regions.
self.remove_rows_of_zeros()
if remove_outliers is True:
# remove outliers, otherwise outliers will produce a very
# high pearson correlation. Unnecessary for spearman correlation
self.remove_outliers()
if log1p is True:
self.matrix = np.log1p(self.matrix)
if corr_method:
self.compute_correlation()
