Month: November 2019

spark= SparkSession.builder \
.master(“local”) \
.appName(“Data Exploration”) \
.getOrCreate()

#load data as Spark DataFrame
data2=spark.read.format(“csv”) \
.option(“header”,”true”) \
.option(“mode”,”DROPMALFORMED”) \
.load(‘/home/Desktop//input/*.csv’)

from pyspark.sql.functions import col
for col_name in data7.columns:
data7 = data7.withColumn(col_name, col(col_name).cast(‘float’))

 

data7.printSchema()