in 5. MLOps SageMaker Project/sagemaker-workshop-preprocess-seedcode-v1/pipelines/preprocess/preprocess.py [0:0]
def load_data(file_list: list):
# Define dates, and columns to use
use_cols = [
"fare_amount",
"lpep_pickup_datetime",
"lpep_dropoff_datetime",
"passenger_count",
"PULocationID",
"DOLocationID",
]
# Concat input files with select columns
dfs = []
for file in file_list:
dfs.append(pd.read_csv(file, usecols=use_cols))
return pd.concat(dfs, ignore_index=True)