From 22b61342606c35968ea15089d42eeca769d1e084 Mon Sep 17 00:00:00 2001 From: ronilpatil Date: Mon, 18 Mar 2024 11:27:30 +0530 Subject: [PATCH] update function name to avoid conflicts --- src/data/load_dataset.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/data/load_dataset.py b/src/data/load_dataset.py index a121dfa..a6d40ed 100644 --- a/src/data/load_dataset.py +++ b/src/data/load_dataset.py @@ -6,7 +6,7 @@ infologger.info('*** Executing: load_dataset.py ***') # load data from given path and return df -def load_data(remote_loc: str) -> pd.DataFrame : +def extract_data(remote_loc: str) -> pd.DataFrame : try : # correct way to read data from drive remote_loc = 'https://drive.google.com/uc?id=' + remote_loc.split('/')[-2] @@ -40,7 +40,7 @@ def main() -> None : # create dir if not present, else execute without any warning/error output_path = home_dir.as_posix() + params['load_dataset']['raw_data'] pathlib.Path(output_path).mkdir(parents = True, exist_ok = True) - data = load_data(params['load_dataset']['drive_link']) + data = extract_data(params['load_dataset']['drive_link']) save_data(data, output_path = output_path, file_name = params['load_dataset']['file_name']) infologger.info('program terminated normally!')