Save Dataframe to csv directly to s3 Python

Question

I have a pandas DataFrame that I want to upload to a new CSV file. The problem is that I don\'t want to save the file locally before transferring it to s3. Is there any meth

Answer 1

I read a csv with two columns from bucket s3, and the content of the file csv i put in pandas dataframe.

Example:

config.json

{
  "credential": {
    "access_key":"xxxxxx",
    "secret_key":"xxxxxx"
}
,
"s3":{
       "bucket":"mybucket",
       "key":"csv/user.csv"
   }
}

cls_config.json

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import os
import json

class cls_config(object):

    def __init__(self,filename):

        self.filename = filename


    def getConfig(self):

        fileName = os.path.join(os.path.dirname(__file__), self.filename)
        with open(fileName) as f:
        config = json.load(f)
        return config

cls_pandas.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import pandas as pd
import io

class cls_pandas(object):

    def __init__(self):
        pass

    def read(self,stream):

        df = pd.read_csv(io.StringIO(stream), sep = ",")
        return df

cls_s3.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import boto3
import json

class cls_s3(object):

    def  __init__(self,access_key,secret_key):

        self.s3 = boto3.client('s3', aws_access_key_id=access_key, aws_secret_access_key=secret_key)

    def getObject(self,bucket,key):

        read_file = self.s3.get_object(Bucket=bucket, Key=key)
        body = read_file['Body'].read().decode('utf-8')
        return body

test.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

from cls_config import *
from cls_s3 import *
from cls_pandas import *

class test(object):

    def __init__(self):
        self.conf = cls_config('config.json')

    def process(self):

        conf = self.conf.getConfig()

        bucket = conf['s3']['bucket']
        key = conf['s3']['key']

        access_key = conf['credential']['access_key']
        secret_key = conf['credential']['secret_key']

        s3 = cls_s3(access_key,secret_key)
        ob = s3.getObject(bucket,key)

        pa = cls_pandas()
        df = pa.read(ob)

        print df

if __name__ == '__main__':
    test = test()
    test.process()

Answer 2

You can use:

from io import StringIO # python3; python2: BytesIO 
import boto3

bucket = 'my_bucket_name' # already created on S3
csv_buffer = StringIO()
df.to_csv(csv_buffer)
s3_resource = boto3.resource('s3')
s3_resource.Object(bucket, 'df.csv').put(Body=csv_buffer.getvalue())

Answer 3

since you are using boto3.client(), try:

import boto3
from io import StringIO #python3 
s3 = boto3.client('s3', aws_access_key_id='key', aws_secret_access_key='secret_key')
def copy_to_s3(client, df, bucket, filepath):
    csv_buf = StringIO()
    df.to_csv(csv_buf, header=True, index=False)
    csv_buf.seek(0)
    client.put_object(Bucket=bucket, Body=csv_buf.getvalue(), Key=filepath)
    print(f'Copy {df.shape[0]} rows to S3 Bucket {bucket} at {filepath}, Done!')

copy_to_s3(client=s3, df=df_to_upload, bucket='abc', filepath='def/test.csv')

Answer 4

I found this can be done using client also and not just resource.

from io import StringIO
import boto3
s3 = boto3.client("s3",\
                  region_name=region_name,\
                  aws_access_key_id=aws_access_key_id,\
                  aws_secret_access_key=aws_secret_access_key)
csv_buf = StringIO()
df.to_csv(csv_buf, header=True, index=False)
csv_buf.seek(0)
s3.put_object(Bucket=bucket, Body=csv_buf.getvalue(), Key='path/test.csv')