def _assert_result(self, namefile: str, data: str, iterations: str, project_name: str,
result_means_filename: str) -> None:
means_test_filename = 'hi_{}_result__data-{}_it-{}.txt'.format(namefile, data, iterations)
original_means = pd.read_table(os.path.realpath('{}/{}'.format(data_test_dir, means_test_filename)))
result_means = pd.read_table('{}/{}/{}'.format(output_test_dir, project_name, result_means_filename))
self.assertTrue(dataframe_functions.dataframes_has_same_data(result_means, original_means))
self.remove_file('{}/{}/{}'.format(output_test_dir, project_name, result_means_filename))
def _assert_result(self, filename: str, data: str, iterations: int,
project_name: str, result_means_filename: str,
debug_seed: int, threshold: float,
result_precision: int) -> None:
str_threshold = ''.join(str(threshold).split('.'))
means_test_filename = \
'statistical_analysis__{}_result__' \
'data-{}_it-{}_seed-{}_threshold-{}_precision-{}.txt'.format(filename,
data,
iterations,
debug_seed,
str_threshold,
result_precision)
original_means = pd.read_table(
os.path.realpath('{}/{}'.format(data_test_dir,
means_test_filename)))
result_means = pd.read_table('{}/{}/{}'.format(output_test_dir,
project_name,
result_means_filename))
self.assertTrue(dataframe_functions.dataframes_has_same_data(
result_means, original_means),
msg='failed comparing {} with {}'.format(
means_test_filename, result_means_filename))
self.remove_file('{}/{}/{}'.format(output_test_dir, project_name,
result_means_filename))
def test_different_unsorted_columns(self):
dataframe1 = pd.DataFrame({'col2': [3, 4], 'col1': [1, 2]})
dataframe2 = pd.DataFrame({'col1': [1, 2], 'col2': [3, 5]})
self.assertFalse(
dataframe_functions.dataframes_has_same_data(
dataframe1, dataframe2))
def test_equal_unsorted_columns(self):
dataframe1 = pd.DataFrame({'col2': [3, 4], 'col1': [1, 2]})
dataframe2 = pd.DataFrame({'col1': [1, 2], 'col2': [3, 4]})
self.assertTrue(
dataframe_functions.dataframes_has_same_data(
dataframe1, dataframe2))
def test_apply_threshold(self):
cluster_counts = pd.read_csv('{}/cluster_counts_generic_cluster_counts.csv'.format(self.FIXTURES_SUBPATH))
expected_result = pd.read_csv('{}/cluster_counts_helper_threshold_results.csv'.format(self.FIXTURES_SUBPATH))
gene_column_name = 'gene'
cluster_names = list(cluster_counts.columns.values)
cluster_names.remove(gene_column_name)
result = cluster_counts_helper.apply_threshold(cluster_counts, cluster_names, threshold=0.2)
self.assertTrue(dataframe_functions.dataframes_has_same_data(result, expected_result))
def test_filter_by_multidatas(self):
multidatas = pd.read_csv(
'{}/filter_interaction/filter_interaction_multidatas_multidata.csv'
.format(data_test_dir))
interactions = pd.read_csv(
'{}/filter_interaction/filter_interaction_multidatas_interaction.csv'
.format(data_test_dir))
result = interaction_filter.filter_by_multidatas(
multidatas, interactions)
expected_result = interactions[interactions['test_both_enabled']]
self.assertTrue(
dataframe_functions.dataframes_has_same_data(
result, expected_result))
def test_get_involved_complex_from_protein_empty_result(self):
proteins = pd.read_csv('{}/helper_complex_protein.csv'.format(
self.FIXTURES_SUBPATH))
proteins.drop(proteins.index, inplace=True)
complexes = pd.read_csv('{}/helper_complex_complex.csv'.format(
self.FIXTURES_SUBPATH))
complex_composition = pd.read_csv(
'{}/helper_complex_complex_composition.csv'.format(
self.FIXTURES_SUBPATH))
result = complex_helper.get_involved_complex_from_protein(
proteins, complexes, complex_composition, drop_duplicates=False)
self.assertTrue(
dataframe_functions.dataframes_has_same_data(
result, pd.DataFrame()))
def _assert_result(self,
namefile: str,
data: str,
project_name: str,
result_means_filename: str,
threshold: float,
result_precision: int,
) -> None:
str_threshold = ''.join(str(threshold).split('.'))
test_filename = 'analysis__{}_result__data-{}_threshold-{}_precision-{}.txt'.format(namefile,
data,
str_threshold,
result_precision)
original_means = pd.read_table('{}/{}'.format(data_test_dir, test_filename))
result_means = pd.read_table('{}/{}/{}'.format(output_test_dir, project_name, result_means_filename))
self.assertTrue(dataframe_functions.dataframes_has_same_data(result_means, original_means))
self.remove_file('{}/{}/{}'.format(output_test_dir, project_name, result_means_filename))
def test_get_involved_complex_composition_from_protein(self):
proteins = pd.read_csv('{}/helper_complex_protein.csv'.format(
self.FIXTURES_SUBPATH),
index_col=0)
complex_composition = pd.read_csv(
'{}/helper_complex_complex_composition.csv'.format(
self.FIXTURES_SUBPATH))
result_expected = pd.read_csv(
'{}/helper_complex_result_drop_duplicates.csv'.format(
self.FIXTURES_SUBPATH))
result = complex_helper.get_involved_complex_composition_from_protein(
proteins, complex_composition)
self.assertTrue(
dataframe_functions.dataframes_has_same_data(
result, result_expected))
def test_filter_empty_cluster_counts(self):
cluster_counts = pd.read_csv(
'{}/cluster_counts_generic_cluster_counts.csv'.format(
self.FIXTURES_SUBPATH))
expected_result = pd.read_csv(
'{}/cluster_counts_filter_empty_cluster_results.csv'.format(
self.FIXTURES_SUBPATH))
gene_column_name = 'gene'
cluster_names = list(cluster_counts.columns.values)
cluster_names.remove(gene_column_name)
result = cluster_counts_filter.filter_empty_cluster_counts(
cluster_counts, cluster_names)
self.assertTrue(
dataframe_functions.dataframes_has_same_data(
result, expected_result))
def test_merge_complex_cluster_counts(self):
complex_counts_composition = pd.read_csv(
'{}/cluster_counts_helper_merge_complex_cluster_counts_complex_counts_composition.csv'.format(
self.FIXTURES_SUBPATH))
expected_result = pd.read_csv(
'{}/cluster_counts_helper_merge_complex_cluster_counts_result.csv'.format(
self.FIXTURES_SUBPATH))
cluster_names = ['cluster_1', 'cluster_2', 'cluster_3']
complex_column_names = ['complex_multidata_id']
result = cluster_counts_helper.merge_complex_counts(cluster_names, complex_counts_composition,
complex_column_names)
# Need to set equal 1 to 1.0000
result[complex_column_names] = result[complex_column_names].astype(dtype='int32')
expected_result[complex_column_names] = expected_result[complex_column_names].astype(dtype='int32')
self.assertTrue(dataframe_functions.dataframes_has_same_data(result, expected_result))
def test_get_involved_complex_from_protein_empty_result(self):
proteins = pd.read_csv('{}/helper_complex_protein.csv'.format(
self.FIXTURES_SUBPATH),
index_col=0)
proteins.drop(proteins.index, inplace=True)
complex_composition = pd.read_csv(
'{}/helper_complex_complex_composition.csv'.format(
self.FIXTURES_SUBPATH))
result = complex_helper.get_involved_complex_composition_from_protein(
proteins, complex_composition)
self.assertTrue(
dataframe_functions.dataframes_has_same_data(
result,
pd.DataFrame(columns=[
'complex_multidata_id', 'protein_multidata_id',
'total_protein'
])))
def test_get_complex_involved_in_counts(self):
multidatas_counts = pd.read_csv(
'{}/helper_cluster_counts.csv'.format(
self.FIXTURES_SUBPATH))
cluster_names = ['cluster_1', 'cluster_2', 'cluster_3']
complex_composition = pd.read_csv(
'{}/helper_cluster_counts_complex_composition.csv'.format(
self.FIXTURES_SUBPATH))
complex_expanded = pd.read_csv(
'{}/helper_cluster_counts_complex.csv'.format(
self.FIXTURES_SUBPATH))
result_expected = pd.read_csv(
'{}/cluster_counts_helper_get_complex_involved_in_counts_result.csv'.format(self.FIXTURES_SUBPATH))
result = cluster_counts_helper.get_complex_involved_in_counts(multidatas_counts, cluster_names,
complex_composition, complex_expanded)
self.assertTrue(dataframe_functions.dataframes_has_same_data(result, result_expected),
'get_complex_involved_in_counts result did not match with expected')
def test_compare_empty(self):
self.assertTrue(
dataframe_functions.dataframes_has_same_data(
pd.DataFrame(), pd.DataFrame()))
