x['Items'][i]["coupon_Id"]) + "," + str( x['Items'][i]["rating"]) + "," + str( x['Items'][i]["timestamp"]) f.write(string) f.write("\n") print("Datasets Updated") key = 'ratings_1_1.txt' fn = '/home/hadoop/ratings_1_1.txt' k = Key(bucket) k.key = key k.set_contents_from_filename(fn) k.make_public() os.remove(fn) stdin, stdout = sys.stdin, sys.stdout reload(sys) sys.stdin, sys.stdout = stdin, stdout sys.setdefaultencoding('utf-8') if __name__ == "__main__": if len(sys.argv) != 2: print("Usage: Path-to-test.py <path-to-file>") exit(-1) sc = SparkContext(appName="Coupons") sc.setLogLevel("ERROR") load_data = sc.textFile("s3a://ccfinalproject/ratings_1_1.txt") split_data = load_data.map(lambda l: l.split(','))