s3.upload_fileobj gives error a bytes-like object is required
Going off this reference, it seems you'll need to wrap a gzip.GzipFile
object around your BytesIO
which will then perform the compression for you.
import ioimport gzipbuffer = io.BytesIO() with gzip.GzipFile(fileobj=buffer, mode="wb") as f: f.write(df.to_csv().encode())buffer.seek(0)s3.upload_fileobj(buffer, bucket, key)
Minimal Verifiable Example
import ioimport gzipimport zlib# Encodedf = pd.DataFrame({'A':[1,2,3], 'B':[6,7,8]})buffer = io.BytesIO() with gzip.GzipFile(fileobj=buffer, mode="wb") as f: f.write(df.to_csv().encode())buffer.getvalue()# b'\x1f\x8b\x08\x00\xf0\x0b\x11]\x02\xff\xd3q\xd4q\xe22\xd01\xd41\xe32\xd41\xd21\xe72\xd21\xd6\xb1\xe0\x02\x00Td\xc2\xf5\x17\x00\x00\x00'
# Decodeprint(zlib.decompress(out.getvalue(), 16+zlib.MAX_WBITS).decode())# ,A,B# 0,1,6# 1,2,7# 2,3,8
The only you need is a TextIOWrapper, as to_csv
expects a string
while upload_fileobj
expects bytes
def upload_file(dataframe, bucket, key): """dat=DataFrame, bucket=bucket name in AWS S3, key=key name in AWS S3""" s3 = boto3.client('s3') csv_buffer = io.BytesIO() w = io.TextIOWrapper(csv_buffer) dataframe.to_csv(w, compression='gzip') w.seek(0) s3.upload_fileobj(csv_buffer, bucket, key)
And the code uploads fine
$ cat test.csv,A,B0,1,61,2,72,3,8
You could try something like this.
import pandas as pdimport iodf = pd.DataFrame({'A':[1,2,3], 'B':[6,7,8]})def upload_file(dataframe, bucket, key): """dat=DataFrame, bucket=bucket name in AWS S3, key=key name in AWS S3""" s3 = boto3.client('s3') csv_buffer = io.StringIO() dataframe.to_csv(csv_buffer, compression='gzip') csv_buffer.seek(0) s3.upload_fileobj(csv_buffer, bucket, key)upload_file(df, your-bucket, your-key)