def _get_merged_df()

in notebook/utils/wf.py [0:0]

• 14 lines of code
• 6 McCabe index (conditional complexity)

    def _get_merged_df(cls, bucket, prefix, s3_client, show_header=True, has_header=True, maxkeys=10) :
        
        files = []
        skip = 0
        kwargs = {'Bucket': bucket, 'Prefix': prefix, 'MaxKeys': maxkeys}
        resp = s3_client.list_objects_v2(**kwargs)
        
        for obj in resp['Contents'] :
            
            if has_header and not show_header :
                skip = 1
                
            if has_header and show_header :
                files.append(pd.read_csv("s3://{}/{}".format(bucket, obj["Key"])))
            else :
                files.append(pd.read_csv("s3://{}/{}".format(bucket, obj["Key"]), skiprows=skip, header=None))
                
        df = pd.concat(files)

        return df