# to manually clean up, later
with tempfile.TemporaryDirectory() as temp:
# export the `data` directory from the visualization
viz.export_data(temp)
temp_pathlib = pathlib.Path(temp)
# iterate through all of the files that we just extracted above
for file in temp_pathlib.iterdir():
# if the file is a csv file, copy it to the final dest
if file.suffix == '.csv':
data.append(pd.read_csv(file))
# shutil.copy(file, dest)
return data
if __name__ == '__main__':
db = client.dbClient()
outputs = db.default_output_names(CURRENT_STAGE)
output_dir_data = os.getenv("OUTPUT_DIR")
output_dir_visuals = os.path.join(output_dir_data, "Visuals")
out_frequency_collapsed_table = os.path.join(output_dir_data, outputs["data"][0])
out_frequency_uid_collapsed_table = os.path.join(output_dir_data, outputs["data"][1])
out_relative_collapsed_table_artifact = os.path.join(output_dir_data, outputs["data"][2])
out_relative_collapsed_table_artifact_uid = os.path.join(output_dir_data, outputs["data"][3])
out_id_freq_table = os.path.join(output_dir_visuals, outputs["visuals"][0])
out_otu_freq_table = os.path.join(output_dir_visuals, outputs["visuals"][1])
out_id_rel_freq_table = os.path.join(output_dir_visuals, outputs["visuals"][2])
out_otu_rel_freq_table = os.path.join(output_dir_visuals, outputs["visuals"][3])
out_stacked_frequency = os.path.join(output_dir_visuals, outputs["visuals"][4])
:param file: The file containing the metadata
:param header: val of 1 headers are first line in file, val of -1 headers are in the first column of the file
:param nan_val: The value of empty items in the file
:param separator: The sperator of the itmes in the file
:return:
"""
if header == 1:
df = pd.read_csv(file, sep=separator, header=header)
elif header == -1:
df = pd.read_csv(file, sep=separator, header=None)
df = df.T
headers = df.iloc[0, :]
df.columns = headers
df = df.iloc[1:, :]
# Replace nan values
df = df.replace(nan_val, np.NaN)
# Export to json for db entry
json_data = df.to_json(orient="records")
return json.loads(json_data)
if __name__ == '__main__':
metadata_file = os.getenv('META_FILE')
data = import_data(metadata_file, -1, separator="\t")
db_client = client.dbClient()
for item in data:
db_client.insert_one(item,"metadata")
db_client.close()
def get_sample_locations(criteria):
db = client.dbClient()
docs = db.query(criteria, 'samples')
db.close()
return docs
def __init__(self, jsonTable, outputDir):
self.data = self.parseTable(jsonTable)
self.outputDir = "./" + outputDir
self.dbClient = client.dbClient()
self.downloadProcess()
self.dbClient.close()
