get_churned_users

def get_churned_users(df):
    """
    Find out the users that cancelled so we can identify who churned.
    Return updated dataframe with additional column identifying as such
    """
    cancelled_ids = df.filter('page == "Cancellation Confirmation"').select("userId").distinct()
    # Convert to list to be used to filter later
    cancelled_ids = cancelled_ids.toPandas()['userId'].tolist()
    # 1 when a user churned and 0 when they did not
    df = df.withColumn("Churn", when((col("userId").isin(cancelled_ids)),lit('1')).otherwise(lit('0')))
    
    return df