in src/preprocess.py [0:0]
def build(self):
self._logger.info("Loading data from data manifest %s", self._data_manifest)
data_paths = self._data_manifest.get("data")
df_array = []
for index, value in enumerate(data_paths):
df = self._download_file(index, value["bucketName"], value["objectKey"])
df_array.append(df)
if len(df_array):
return pd.concat(df_array)