diff --git a/data_prepare.py b/data_prepare.py index be45763..5c44f82 100644 --- a/data_prepare.py +++ b/data_prepare.py @@ -3,6 +3,8 @@ import os # Set Java environment variable os.environ['JAVA_HOME'] = '/opt/module/jdk1.8.0_171' +os.environ["PYSPARK_PYTHON"]="/usr/local/bin/python3.6" +os.environ["PYSPARK_DRIVER_PYTHON"]="/usr/local/bin/python3.6" # Parse ratings data into (userID, movieID, rating) def get_ratings_tuple(entry):