From 4144c563daba33e459088778675e80cb2eba85bb Mon Sep 17 00:00:00 2001 From: Asmaa AlSaggaf <41995957+aumsaggaf@users.noreply.github.com> Date: Tue, 21 Jan 2020 01:23:58 +0300 Subject: [PATCH] Updated etl.py Fixed wrong description for the process_log_data function. --- Data Lakes with Spark/Project Data Lake with Spark/etl.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Data Lakes with Spark/Project Data Lake with Spark/etl.py b/Data Lakes with Spark/Project Data Lake with Spark/etl.py index e678fc2..bffa8e0 100644 --- a/Data Lakes with Spark/Project Data Lake with Spark/etl.py +++ b/Data Lakes with Spark/Project Data Lake with Spark/etl.py @@ -72,7 +72,7 @@ def process_song_data(spark, input_data, output_data): def process_log_data(spark, input_data, output_data): """ - Description: This function loads log_data from S3 and processes it by extracting the songs and artist tables + Description: This function loads log_data from S3 and processes it by extracting the users, time, and songplays tables and then again loaded back to S3. Also output from previous function is used in by spark.read.json command Parameters: