6 Sparkify Session Count and Avg Song Count/Session

sparkify_6_avg_song_count_per_session.py

user_engagement = data\
    .groupBy('userId', 'sessionId')\
    .agg(F.max('itemInSession').alias('itemCount'))\
    .groupBy('userId')\
    .agg({"itemCount": "mean", "sessionId": "count"})\
    .withColumnRenamed('count(sessionId)', 'sessionCount')\
    .withColumnRenamed('avg(itemCount)', 'meanSongCount')\
    .orderBy('userId')

user_engagement.show(10)