Pandas DataFrame ke Parket S3
import awswrangler as wr
wr.pandas.to_parquet(
dataframe=df,
path="s3://my-bucket/key/my-file.parquet"
)
batman_on_leave
import awswrangler as wr
wr.pandas.to_parquet(
dataframe=df,
path="s3://my-bucket/key/my-file.parquet"
)import pyarrow.parquet as pq
import s3fs
dataset = pq.ParquetDataset('s3://<s3_path_to_folder_or_file>',
filesystem=s3fs.S3FileSystem(), filters=[('colA', '=', 'some_value'), ('colB', '>=', some_number)])
table = dataset.read()
df = table.to_pandas()