similarity_metric, connectivity_metric
def write_success(file_name, start_time_msg):
# Create timestamp
timestamp = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')
# Write timestamp to file_name
f = open(file_name, 'w')
f.write(start_time_msg + "\n")
f.write("external_query_many.py completed at {}\n".format(timestamp))
f.close()
def write_failure(file_name, start_time_msg):
# Record stacktrace
_, _, exc_traceback = sys.exc_info()
# Write stacktrace to file_name
f = open(file_name, "w")
f.write(start_time_msg + "\n")
traceback.print_exc(exc_traceback, file=f)
f.close()
if __name__ == "__main__":
args = build_parser().parse_args(sys.argv[1:])
setup_logger.setup(verbose=args.verbose)
main(args)
# Location of gcts processed using R code
gct_loc_r_code = "/cmap/data/proteomics/produced_by_jjaffe_code/dry/wget_processed/"
gct_r_code_suffix = "*GCP*.gct"
# Location of gcts processed using dry
gct_loc_dry = "/cmap/data/proteomics/dry/2016-10-10/"
# Suffix for files created with dry
dry_suffix = ".gct.dry.processed.gct"
##########
# Setup logger
logger = logging.getLogger(setup_logger.LOGGER_NAME)
setup_logger.setup(verbose=False)
# Get R files
all_r_files = glob.glob(gct_loc_r_code + gct_r_code_suffix)
assert len(all_r_files) > 0, "No R files were found!"
logger.debug("{} R files found".format(len(all_r_files)))
# For each R file, see if we can find its complementary file created with dry
# Only keep the R files with a complement
r_files = []
dry_files = []
for r_file in all_r_files:
dry_file_path = os.path.join(
gct_loc_dry,
s3 = mock.Mock()
s3.Object = mock.Mock()
s3.Object.return_value.get = mock.MagicMock()
s3Dict = {"Body": True}
def s3_get_item(key):
return s3Dict[key]
s3.Object.return_value.get.__getitem__.side_effect = s3_get_item
# happy path
s3.Object.return_value.get.read = mock.Mock()
ltb.json.loads = mock.Mock(return_value={"id": "fake_id"})
returned_tuple = ltb.get_panorama_request_and_parse(
s3, bucket_name, current_gct_key)
expected_tuple = ("fake_id", "this_plate_name")
self.assertEqual(expected_tuple, returned_tuple)
#unhappy path s3 reading exception
s3.Object.side_effect = Exception("failure")
with self.assertRaises(Exception) as context:
returned_tuple = ltb.get_panorama_request_and_parse(
s3, bucket_name, current_gct_key)
self.assertEqual("failure", context.exception[0][0])
if __name__ == "__main__":
setup_logger.setup(verbose=True)
unittest.main()
assert len(meta_value) == num_wells, (
"The entry {} has length {}, which is not equal to num_wells: {}.".
format(meta_key, len(meta_value), num_wells))
# Append the metadata_dict to plate_and_well_dict
df_dict = plate_and_well_dict.copy()
df_dict.update(metadata_dict)
# Convert dict to df and rearrange columns appropriately
temp_df = pd.DataFrame.from_dict(df_dict)
cols = [PLATE_FIELD, WELL_FIELD] + sorted(metadata_dict.keys())
out_df = temp_df[cols]
return out_df
def undo_log_transform_if_needed(data_df, prov_code):
"""Undo log transformation if L2X is in prov_code."""
if LOG_TRANSFORM_PROV_CODE_ENTRY in prov_code:
out_df = np.exp2(data_df)
else:
out_df = data_df
return out_df
if __name__ == "__main__":
args = build_parser().parse_args(sys.argv[1:])
setup_logger.setup()
main(args)
