def test_write_csv(self): ratios = dm.DataMatrix(2, 2, ['Gene 1', 'Gene 2'], ['Cond 1', 'Cond 2'], np.array([[1, 2], [3, 4]])) ratios.write_tsv_file('/tmp/simple_ratios.tsv', compressed=False) # check the written file ratios = dm.create_from_csv('/tmp/simple_ratios.tsv') self.assertEquals(ratios.row_names, ['Gene 1', 'Gene 2']) self.assertEquals(ratios.column_names, ['Cond 1', 'Cond 2']) self.assertAlmostEquals(ratios.values[0][0], 1.0)
def read_ratios(params, args_in): """reading ratios matrix""" if params['normalize_ratios']: if test_data_change(params, args_in) == True: #Turn off the nochange_filter if you're resuming a run an have changed the data matrix ratio_filters = [dm.center_scale_filter] else : ratio_filters = [dm.nochange_filter, dm.center_scale_filter] else: ratio_filters = [] matrix_filename = args_in.ratios case_sensitive = params['case_sensitive'] or args_in.case_sensitive return dm.create_from_csv(matrix_filename, filters=ratio_filters, case_sensitive=case_sensitive)
def setUp(self): # pylint; disable-msg=C0103 """test fixture""" self.search_distances = {'upstream': (-20, 150)} self.scan_distances = {'upstream': (-30, 250)} self.ratio_matrix = dm.create_from_csv('example_data/hal/halo_ratios5.tsv', filters=[dm.nochange_filter, dm.center_scale_filter]) self.organism = testutil.make_halo(self.search_distances, self.scan_distances, self.ratio_matrix) self.config_params = {'memb.min_cluster_rows_allowed': 3, 'memb.max_cluster_rows_allowed': 70, 'multiprocessing': False, 'memb.clusters_per_row': 2, 'memb.clusters_per_col': int(round(43 * 2.0 / 3.0)), 'num_clusters': 43, 'num_iterations': 2000} self.membership = self.__read_members() # relies on config_params self.iteration_result = { 'iteration': 51 }
def setUp(self): with open('testdata/hsa_mir_thesaurus.json') as infile: self.synonyms = json.load(infile) self.ratios = dm.create_from_csv('testdata/acc_rnaseq.tsv.gz', sep='\t') self.input_genes = self.ratios.row_names self.config_params = {'SetEnrichment': {'set_types': 'tfbs'}, 'SetEnrichment-tfbs': {'set_file': 'testdata/test_sets.json', 'weight': 1.0} } self.set_types = se.read_set_types(self.config_params, self.synonyms, self.input_genes) self.canonical_rownames = set(map(lambda n: self.synonyms[n] if n in self.synonyms else n, self.ratios.row_names)) self.canonical_row_indexes = {} for index, row in enumerate(self.ratios.row_names): if row in self.synonyms: self.canonical_row_indexes[self.synonyms[row]] = index else: self.canonical_row_indexes[row] = index
def setUp(self): # pylint; disable-msg=C0103 """test fixture""" self.search_distances = {'upstream': (-20, 150)} self.scan_distances = {'upstream': (-30, 250)} self.ratio_matrix = dm.create_from_csv('example_data/hal/halo_ratios5.tsv', filters=[dm.nochange_filter, dm.center_scale_filter]) self.ratios = self.ratio_matrix self.organism = testutil.make_halo(self.search_distances, self.scan_distances, self.ratio_matrix) self.config_params = {'memb.min_cluster_rows_allowed': 3, 'memb.max_cluster_rows_allowed': 70, 'multiprocessing': False, 'num_cores': None, 'memb.clusters_per_row': 2, 'memb.clusters_per_col': int(round(43 * 2.0 / 3.0)), 'num_clusters': 43, 'output_dir': 'out', 'remap_network_nodes': False, 'use_BSCM': False, 'num_iterations': 2000, 'debug': {}, 'search_distances': {'upstream': (-20, 150)}, 'Columns': {'schedule': lambda i: True }, 'Rows': {'schedule': lambda i: True, 'scaling': ('scaling_const', 6.0) }, 'Motifs': {'schedule': lambda i: True, 'scaling': ('scaling_rvec', 'seq(0, 1, length=num_iterations*3/4)')}, 'MEME': {'version': '4.3.0', 'global_background': False, 'schedule': lambda i: True, 'nmotifs_rvec': 'c(rep(1, num_iterations/3), rep(2, num_iterations/3))', 'max_width': 24, 'arg_mod': 'zoops', 'background_order': 3, 'use_revcomp': 'True'}, 'Networks': {'schedule': lambda i: True, 'scaling': ('scaling_rvec', 'seq(1e-5, 0.5, length=num_iterations*3/4)')}} self.membership = self.__read_members() # relies on config_params self.iteration_result = { 'iteration': 51, 'score_means': {} }
def read_matrix(filename): """reads a matrix file""" return dm.create_from_csv(filename, filters=[])
def __read_colscores_refresult(self): return dm.create_from_csv('testdata/column_scores_refresult.tsv', filters=[], case_sensitive=True)
def __read_ratios(self): return dm.create_from_csv('testdata/row_scores_testratios.tsv', filters=[], case_sensitive=True)
def test_read_csv_numeric_rownames(self): ratios = dm.create_from_csv('testdata/simple_ratios_numeric_rownames.tsv') self.assertEquals(['12231245', '12344542'], ratios.row_names) self.assertEquals(['Cond 1', 'Cond 2'], ratios.column_names) print(ratios.row_names) self.assertAlmostEquals(ratios.values[0][0], 54.1)
def test_read_csv(self): ratios = dm.create_from_csv('testdata/simple_ratios.tsv') self.assertEquals(ratios.row_names, ['Gene 1', 'Gene 2']) self.assertEquals(ratios.column_names, ['Cond 1', 'Cond 2']) self.assertAlmostEquals(ratios.values[0][0], 23.1)
def read_matrix(filename): """reads a matrix file""" return dm.create_from_csv(filename, filters=[]).sorted_by_row_name()