Install Spark and run word count. This program counts word of file pg5000.txt and print result.

Usage:

{SPARK_DIR}/bin/spark-submit IKDDHw3_1.py

Movie recommendation using MLlib of Spark.
This program trains model with data /lesson/ratings.dat and reads file userRating.dat as input printing top 10 movies result according to it. Besides, /lesson/movies.dat is table for program to look up movie data.

Ratings contained in the file /lesson/ratings.dat and useRatings.dat are in the following format:

UserID::MovieID::Rating::Timestamp

Movie information in the file /lesson/movies.dat are in the following format:

MovieID::Title::Genres

Usage:

{SPARK_DIR}/bin/spark-submit IKDDHw3_2.py