def test_top_bottom(self):
top_gct_path = os.path.join(FUNCTIONAL_TESTS_DIR, "test_merge_top.gct")
bottom_gct_path = os.path.join(FUNCTIONAL_TESTS_DIR, "test_merge_bottom.gct")
expected_gct_path = os.path.join(FUNCTIONAL_TESTS_DIR, "test_merged_top_bottom.gct")
top_gct = pg.parse(top_gct_path)
bottom_gct = pg.parse(bottom_gct_path)
expected_gct = pg.parse(expected_gct_path)
# Merge top and bottom
concated_gct = cg.vstack([top_gct, bottom_gct], [], False)
pd.util.testing.assert_frame_equal(expected_gct.data_df, concated_gct.data_df, check_names=False)
pd.util.testing.assert_frame_equal(expected_gct.row_metadata_df, concated_gct.row_metadata_df, check_names=False)
pd.util.testing.assert_frame_equal(expected_gct.col_metadata_df, concated_gct.col_metadata_df, check_names=False)
def main(args):
# Record start_time
start_time = datetime.datetime.now()
start_time_msg = "external_query_many.py started at {}".format(
start_time.strftime('%Y-%m-%d %H:%M:%S'))
# Create output directory
assert os.path.exists(args.out_dir), "args.out_dir: {}".format(
args.out_dir)
try:
# Read and unpack config file
(cells, internal_gct_dir, bg_gct_dir,
fields_to_aggregate_for_internal_profiles, similarity_metric,
connectivity_metric) = read_config_file(args.psp_on_clue_config_path)
# Read in the external profiles only once
external_gct = parse(args.external_gct_path)
# If requested, do introspect
(_, introspect_gct) = introspect.do_steep_and_sip(
external_gct, similarity_metric, connectivity_metric,
args.fields_to_aggregate_for_external_profiles)
# Write introspect result
actual_out_introspect_name = os.path.join(args.out_dir,
OUT_INTROSPECT_NAME)
wg.write(introspect_gct,
actual_out_introspect_name,
data_null="NaN",
metadata_null="NaN",
filler_null="NaN")
# Initialize list to store connectivity gcts
list_of_conn_gcts = []
# Loop over cell lines in corpus
for cell in cells:
# Import gct with the internal profiles for this cell line
internal_gct_path = os.path.join(
internal_gct_dir,
INTERNAL_GCT_FORMAT.format(assay=args.assay, cell=cell))
internal_gct = parse(internal_gct_path)
# Import gct with the similarity matrix for this cell line
bg_gct_path = os.path.join(
bg_gct_dir, BG_GCT_FORMAT.format(assay=args.assay, cell=cell))
bg_gct = parse(bg_gct_path)
(sim_gct, conn_gct) = eq.do_steep_and_sip(
external_gct, internal_gct, bg_gct, "spearman", "ks_test",
args.fields_to_aggregate_for_external_profiles,
fields_to_aggregate_for_internal_profiles)
# Append this connectivity gct
list_of_conn_gcts.append(conn_gct)
# Write all output gcts if requested
if args.all:
out_steep_name = os.path.join(
args.out_dir, OUT_STEEP_FORMAT.format(cell=cell))
out_sip_name = os.path.join(args.out_dir,
OUT_SIP_FORMAT.format(cell=cell))
wg.write(sim_gct, out_steep_name)
wg.write(conn_gct, out_sip_name)
# Concatenate connectivity GCTs
concated = cg.vstack(list_of_conn_gcts)
actual_out_concated_name = os.path.join(args.out_dir,
OUT_CONCATED_NAME)
# Write concatenated result
wg.write(concated,
actual_out_concated_name,
data_null="NaN",
filler_null="NaN",
metadata_null="NaN")
# Write success.txt with timestamp
success_path = os.path.join(args.out_dir, "success.txt")
write_success(success_path, start_time_msg)
# Return how much time it took
end_time = datetime.datetime.now()
seconds_elapsed = (end_time - start_time).seconds
logger.info("external_query_many.py completed in {:.0f} sec.".format(
seconds_elapsed))
except Exception:
failure_path = os.path.join(args.out_dir, "failure.txt")
msg = "external_query_many.py failed. See {} for stacktrace.".format(
failure_path)
# Write failure.txt
write_failure(failure_path, start_time_msg)
# Raise exception
logger.error(msg)
raise Exception(msg)
return None