from pyspark.sql import SparkSession
from pyspark.sql.types import *
import os
def getUser(spark,path):
struct1 = StructType([
StructField("user", StringType(), True),
StructField("vedios", StringType(), True),
StructField("id", IntegerType(), True)
])
df = spark.read.csv(path, schema=struct1, sep="", header=True)
df.createOrReplaceTempView("users1")
df = spark.sql("select * from users1")
return df
def getMovies(spark,path):
df = spark.read.csv(path, header=True)
df.createOrReplaceTempView("movies")
df = spark.sql("select * from movies ")
return df
if __name__ == '__main__':
os.environ['JAVA_HOME'] = 'C:Program FilesJavajdk1.8.0_211'
print(o