# -*- coding: utf-8 -*-
"""
author SparkByExamples.com
"""
from pyspark.sql import SparkSession
spark = SparkSession.builder \
         .appName('SparkByExamples.com') \
         .getOrCreate()

data = [("James", "Sales", 3000),
    ("Michael", "Sales", 4600),
    ("Robert", "Sales", 4100),
    ("Maria", "Finance", 3000),
    ("James", "Sales", 3000),
    ("Scott", "Finance", 3300),
    ("Jen", "Finance", 3900),
    ("Jeff", "Marketing", 3000),
    ("Kumar", "Marketing", 2000),
    ("Saif", "Sales", 4100)
  ]
columns = ["Name","Dept","Salary"]
df = spark.createDataFrame(data=data,schema=columns)
df.distinct().show()
print("Distinct Count: " + str(df.distinct().count()))

# Using countDistrinct()
from pyspark.sql.functions import countDistinct
df2=df.select(countDistinct("Dept","Salary"))
df2.show()

print("Distinct Count of Department & Salary: "+ str(df2.collect()[0][0]))

df.createOrReplaceTempView("PERSON")
spark.sql("select distinct(count(*)) from PERSON").show()