uhho

def s3_to_pandas(client, bucket, key, header=None):

    # get key using boto3 client
    obj = client.get_object(Bucket=bucket, Key=key)
    gz = gzip.GzipFile(fileobj=obj['Body'])
    
    # load stream directly to DF
    return pd.read_csv(gz, header=header, dtype=str)

def s3_to_pandas_with_processing(client, bucket, key, header=None):

niranjv

# A virtualenv running Python3.6 on Amazon Linux/EC2 (approximately) simulates the Python 3.6 Docker container used by Lambda
# and can be used for developing/testing Python 3.6 Lambda functions
# This script installs Python 3.6 on an EC2 instance running Amazon Linux and creates a virtualenv running this version of Python
# This is required because Amazon Linux does not come with Python 3.6 pre-installed 
# and several packages available in Amazon Linux are not available in the Lambda Python 3.6 runtime

# The script has been tested successfully on a t2.micro EC2 instance (Root device type: ebs; Virtualization type: hvm)
# running Amazon Linux AMI 2017.03.0 (HVM), SSD Volume Type - ami-c58c1dd3
# and was developed with the help of AWS Support