# -*- coding: utf-8 -*-
"""
author SparkByExamples.com
"""
from pyspark.sql import SparkSession
spark = SparkSession.builder \
    .master("local[1]") \
    .appName("SparkByExamples.com") \
    .getOrCreate()

filePath="resources/small_zipcode.csv"
df = spark.read.options(header='true', inferSchema='true') \
          .csv(filePath)

df.printSchema()
df.show(truncate=False)


df.fillna(value=0).show()
df.fillna(value=0,subset=["population"]).show()
df.na.fill(value=0).show()
df.na.fill(value=0,subset=["population"]).show()


df.fillna(value="").show()
df.na.fill(value="").show()

df.fillna("unknown",["city"]) \
    .fillna("",["type"]).show()

df.fillna({"city": "unknown", "type": ""}) \
    .show()

df.na.fill("unknown",["city"]) \
    .na.fill("",["type"]).show()

df.na.fill({"city": "unknown", "type": ""}) \
    .show()