def setUp(self):
logger.init()
self.run_parameters = {
"spreadsheet_name_full_path": "../../data/spreadsheets/TEST_1_gene_expression_positive_real_number.tsv",
"gg_network_name_full_path": "../../data/networks/TEST_1_gene_gene.edge",
"results_directory": "./",
"redis_credential": {
"host": "knowredis.knoweng.org",
"port": 6379,
"password": "******"
},
"source_hint": "",
"taxonid": '9606',
"pipeline_type": "samples_clustering_pipeline"
}
self.run_parameters_empty_phenotype = {
"spreadsheet_name_full_path": "../../data/spreadsheets/TEST_1_gene_expression_positive_real_number.tsv",
"gg_network_name_full_path": "../../data/networks/TEST_1_gene_gene.edge",
"phenotype_name_full_path": "",
"results_directory": "./",
"redis_credential": {
"host": "knowredis.knoweng.org",
"port": 6379,
"password": "******"
},
"source_hint": "",
"taxonid": '9606',
"pipeline_type": "samples_clustering_pipeline"
}
self.file_ETL = "TEST_1_gene_expression_positive_real_number_ETL.tsv"
self.file_MAP = "TEST_1_gene_expression_positive_real_number_MAP.tsv"
self.file_UNMAPPED = "TEST_1_gene_expression_positive_real_number_User_To_Ensembl.tsv"
def data_cleanup():
try:
logger.init()
run_directory, run_file = get_run_directory_and_file(sys.argv)
run_parameters = get_run_parameters(run_directory, run_file)
run_pipelines(run_parameters, SELECT[run_parameters['pipeline_type']])
except Exception as err:
logger.logging.append("ERROR: {}".format(str(err)))
raise RuntimeError(str(err))
def checker():
try:
logger.init()
run_directory, run_file = get_run_directory_and_file(sys.argv)
run_parameters = get_run_parameters(run_directory, run_file)
obj = Checker(run_parameters)
obj.condition_check()
except Exception as err:
logger.logging.append("ERROR: {}".format(str(err)))
raise RuntimeError(str(err))
def network_prepper():
try:
logger.init()
run_directory, run_file = get_run_directory_and_file(sys.argv)
run_parameters = get_run_parameters(run_directory, run_file)
run_pipelines(run_parameters, "network_prepper_pipeline")
except Exception as err:
logger.logging.append("ERROR: {}".format(str(err)))
# try to write the log
logger.generate_logging(
False, logger.logging, run_parameters["results_directory"] +
"/log_" + "network_prepper_pipeline" + ".yml")
raise RuntimeError(str(err))
def setUp(self):
logger.init()
self.run_dir = "./run_file"
self.user_spreadsheet = "user_spreadsheet.tsv"
self.spreadsheet_path = self.run_dir + "/" + self.user_spreadsheet
self.f_context = "\ta\tb\tc\n" + \
"ENSG00000000003\t1\t0\t1\n" + \
"ENSG00001000205\t0\t0\t1\n" + \
"ENSG00000700034\t1\t1\t1\n"
self.golden_output = pd.DataFrame(
[[1, 0, 1], [0, 0, 1], [1, 1, 1]],
index=['ENSG00000000003', "ENSG00001000205", 'ENSG00000700034'],
columns=['a', 'b', 'c'])
def setUp(self):
logger.init()
self.input_df = pd.DataFrame([[1, 1, None], [2, 0, 0], [4, 1, 1]],
index=['aa', "bb", 'cc'],
columns=['a', 'b', 'c'])
self.golden_output_remove = pd.DataFrame([[2, 0, 0], [4, 1, 1]],
index=["bb", 'cc'],
columns=['a', 'b', 'c'])
self.golden_output_average = pd.DataFrame(
[[1, 1, 0.5], [2, 0, 0], [4, 1, 1]],
index=['aa', "bb", 'cc'],
columns=['a', 'b', 'c'])
def setUp(self):
logger.init()
self.input_df = pd.DataFrame(
[[1, 2], [0, 10], [1, 9]],
index=['ENSG00001027003', "ENSG00001027003", 'ENSG00008000303'],
columns=['a', 'b'])
self.input_df_nan = pd.DataFrame(
[[1, 0], [0, 10], [1, 1]],
index=['ENSG00001027003', "ENSG00001027003", 'ENSG00008000303'],
columns=['a', None])
self.input_df_fail = pd.DataFrame(
[[1, 0], [0, 10], [1, 1]],
index=['ENSG00001027003', "ENSG00001027003", 'ENSG00008000303'],
columns=[None, None])
def setUp(self):
logger.init()
self.input_df = pd.DataFrame(
[[1, 2], [0, 10], [1, 9]],
index=['ENSG00001027003', "ENSG00001027003", 'ENSG00008000303'],
columns=['a', 'b'])
self.input_df_nan = pd.DataFrame(
[[1, 0], [0, None], [1, 1]],
index=['ENSG00001027003', "ENSG00001027003", 'ENSG00008000303'],
columns=['a', 'b'])
self.input_df_text = pd.DataFrame(
[["text", 0], [0, "text"], [1, 1]],
index=['ENSG00001027003', "ENSG00001027003", 'ENSG00008000303'],
columns=['a', 'b'])
self.input_df_negative = pd.DataFrame(
[[-1, 0], [0, -2], [1, 1]],
index=['ENSG00001027003', "ENSG00001027003", 'ENSG00008000303'],
columns=['a', 'b'])
def setUp(self):
logger.init()
self.run_parameters = {
"spreadsheet_name_full_path":
"../../data/spreadsheets/TEST_1_gene_expression_binary.tsv",
"results_directory": "./",
"source_hint": "",
"taxonid": '9606',
"impute": "average",
"redis_credential": {
"host": "knowredis.knoweng.org",
"port": 6379,
"password": "******"
},
"pipeline_type": "geneset_characterization_pipeline"
}
self.file_ETL = "TEST_1_gene_expression_binary_ETL.tsv"
self.file_MAP = "TEST_1_gene_expression_binary_MAP.tsv"
self.file_UNMAPPED = "TEST_1_gene_expression_binary_User_To_Ensembl.tsv"
def setUp(self):
logger.init()
self.input_df_good = pd.DataFrame([[1, 0],
[0, 0],
[1, 1]],
index=['ENSG00000000003', "ENSG00000000457", 'ENSG00000000005'],
columns=['a', 'b'])
self.input_df_bad = pd.DataFrame([[1, 0],
[0, 0],
[1, 1]],
index=['ENSG00000000003', "ENSG00000000457", 'S00000005'],
columns=['a', 'b'])
self.input_df_cannot_map = pd.DataFrame([[1, 0],
[0, 0],
[1, 1]],
index=['000000003', "000457", 'S00000005'],
columns=['a', 'b'])
self.run_parameters = {
"spreadsheet_name_full_path": "../data/spreadsheets/example.tsv",
"results_directory": "./",
"redis_credential": {
"host": "knowredis.knoweng.org",
"port": 6379,
"password": "******"
},
"source_hint": "",
"taxonid": '9606'
}
self.output_mapping = "./example_MAP.tsv"
self.golden_output_good = pd.DataFrame([[1, 0],
[0, 0],
[1, 1]],
index=['ENSG00000000003', "ENSG00000000457", 'ENSG00000000005'],
columns=['a', 'b'])
def setUp(self):
logger.init()
self.input_df_dup = pd.DataFrame(
[[1, 0], [0, 0], [1, 1]],
index=['ENSG00000000003', "ENSG00001027003", 'ENSG00000000003'],
columns=['a', 'b'])
self.input_df_nodup = pd.DataFrame(
[[1, 0], [0, 0], [1, 1]],
index=['ENSG00001027003', "ENSG00000002008", 'ENSG00008000303'],
columns=['a', 'b'])
self.golden_output_dedup = pd.DataFrame(
[[1, 0], [0, 0]],
index=["ENSG00000000003", 'ENSG00001027003'],
columns=['a', 'b'])
self.golden_output_nodup = pd.DataFrame(
[[1, 0], [0, 0], [1, 1]],
index=['ENSG00001027003', "ENSG00000002008", 'ENSG00008000303'],
columns=['a', 'b'])
def setUp(self):
logger.init()
self.input_phenotype_df = pd.DataFrame(
[[1, 0], [0, 0], [1, 1], [0, 1], [0, 0]],
index=['a', "b", 'c', 'd', 'e'],
columns=['a', 'b'])
self.input_phenotype_df_bad_value = pd.DataFrame(
[[1, 0], [3, 0], [1, 1], [0, 1], [0, 0]],
index=['a', "b", 'c', 'd', 'e'],
columns=['a', 'b'])
self.input_phenotype_df_nan = pd.DataFrame(
[[1, 0], [0, None], [0, 1], [1, 0], [0, 1], [1, 1]],
index=['a', "b", 'c', 'd', 'e', 'f'],
columns=['a', 'b'])
self.input_phenotype_df_negative = pd.DataFrame([[1.1], [-2.2], [3.3]],
index=['a', 'b', 'f'],
columns=['drug1'])
self.input_phenotype_df_pearson = pd.DataFrame(
[[1.1, 0.1], [-2.2, 1.2], [3.3, 2.3]],
index=['d', 'e', 'f'],
columns=['drug1', 'drug2'])
def setUp(self):
logger.init()
self.run_parameters = {
"spreadsheet_name_full_path":
"../../data/spreadsheets/TEST_1_gene_expression_real_number.tsv",
"phenotype_name_full_path":
"../../data/spreadsheets/TEST_1_phenotype_pearson.tsv",
"results_directory": "./",
"source_hint": "",
"taxonid": '9606',
"impute": "average",
"pipeline_type": "samples_clustering_pipeline",
"correlation_measure": 'pearson',
"redis_credential": {
"host": "knowredis.knoweng.org",
"port": 6379,
"password": "******"
}
}
self.file_ETL = "TEST_1_gene_expression_real_number_ETL.tsv"
self.file_MAP = "TEST_1_gene_expression_real_number_MAP.tsv"
self.file_UNMAPPED = "TEST_1_gene_expression_real_number_User_To_Ensembl.tsv"
self.phenotype_ETL = "TEST_1_phenotype_pearson_ETL.tsv"
def setUp(self):
logger.init()
self.input_df_good = pd.DataFrame(
[[1, 0], [0, 0], [1, 1]],
index=['ENSG00000000003', "ENSG00000000457", 'ENSG00000000005'],
columns=['a', 'b'])
self.input_phenotype = pd.DataFrame([[1.1, 2.2, 3.3]],
index=['drug1'],
columns=['a', 'b', 'c'])
self.run_parameters = {
"spreadsheet_name_full_path": "../data/spreadsheets/example.tsv",
"phenotype_name_full_path": ".. /data/spreadsheets/phenotype.tsv",
"results_directory": "./",
"redis_credential": {
"host": "knowredis.knoweng.org",
"port": 6379,
"password": "******"
},
"source_hint": "",
"taxonid": '9606',
"pipeline_type": "gene_priorization_pipeline",
"input_data_type": ""
}
columns=['a', 'b', 'c'])
self.golden_output_remove = pd.DataFrame([[2, 0, 0], [4, 1, 1]],
index=["bb", 'cc'],
columns=['a', 'b', 'c'])
self.golden_output_average = pd.DataFrame(
[[1, 1, 0.5], [2, 0, 0], [4, 1, 1]],
index=['aa', "bb", 'cc'],
columns=['a', 'b', 'c'])
def tearDown(self):
del self.input_df
def test_impute_na_average(self):
ret = SpreadSheet.impute_na(self.input_df, "average")
npytest.assert_array_equal(self.golden_output_average, ret)
def test_impute_na_remove(self):
ret = SpreadSheet.impute_na(self.input_df, "remove")
npytest.assert_array_equal(self.golden_output_remove, ret)
def test_impute_na_bad_option(self):
ret = SpreadSheet.impute_na(self.input_df, "bad")
npytest.assert_array_equal(self.input_df, ret)
if __name__ == '__main__':
logger.init()
unittest.main()
