PYTHON

PySpark find columns with null values

# Find Count of Null, None, NaN of All DataFrame Columns
from pyspark.sql import functions as F
df.select([F.count(F.when(F.isnan(c) | F.col(c).isNull(), c)).alias(c) 
           for c in df.columns]).show()

pyspark check all columns for null values

from pyspark.sql.functions import isnan, when, count, col

df.select([count(when(isnan(c), c)).alias(c) for c in df.columns]).show()
+-------+----------+---+
|session|timestamp1|id2|
+-------+----------+---+
|      0|         0|  3|
+-------+----------+---+

check null all column pyspark

data_indexed.select([count(when(col(c).isNull(),c)).alias(c) for c in data_indexed.columns]).toPandas().T