Last active
March 25, 2018 16:48
-
-
Save vgiri2015/d084dc0336136175ca05d0be21c127d0 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
df = sc.parallelize([(1, 'Y','F',"Giri",'Y'), (2, 'N','V',"Databricks",'N'),(3,'Y','B',"SparkEdge",'Y'),(4,'N','X',"Spark",'N')]).toDF(["id", "flag1","flag2","name","flag3"]) | |
print 'Show Dataframe' | |
df.show() | |
print 'Actual Schema of the df' | |
df.printSchema() | |
for a_dftype in df.dtypes: | |
col_name = a_dftype[0] | |
col_type = a_dftype[1] | |
# print df.select(col_name).collect()[0][0] | |
if col_type=='string' and (df.select(col_name).distinct().collect()[0][0] =='N' or df.select(col_name).distinct().collect()[0][0] =='Y'): | |
df = df.withColumn(col_name,df[col_name].cast("boolean")).drop(df[col_name]) | |
else: | |
df = df.withColumn(col_name,df[col_name]).drop(df[col_name]) | |
print 'df with True/False Value after Data Type changes' | |
df.show() | |
print 'Modified Schema of the df' | |
df.printSchema() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment