#Importing the required libraries
import pandas as pd
from pyspark.sql.types import *
from pyspark.ml.regression import RandomForestRegressor
from pyspark.mllib.util import MLUtils
from pyspark.ml import Pipeline
from pyspark.ml.tuning import CrossValidator, ParamGridBuilder
from pyspark.ml.evaluation import RegressionEvaluator
from pyspark.ml.linalg import Vectors
from pyspark.ml import Pipeline
from pyspark.ml.tuning import CrossValidator, ParamGridBuilder
from pyspark.mllib.fpm import *
from pyspark.sql import SparkSession

spark = SparkSession     .builder     .appName("Python Spark")     .config("spark.some.config.option", "some-value")

# read the data
df = pd.read_json("events.json")

df = (df.rdd.map(lambda x: (x[1],[x[0]])).reduceByKey(lambda x,y: x+y).sortBy(lambda k_v: (k_v[0], sorted(k_v[1], key=lambda x: x[1], reverse=True))).collect())