from pyspark.sql import SparkSession

spark = SparkSession \
    .builder \
    .appName("Python Spark SQL basic example") \
    .config("spark.some.config.option", "some-value") \
    .getOrCreate()

import pyspark.sql.functions as F

Load some data

df = spark.read.load("DEX03s - 2019-10-07.csv",
                     format="csv", sep=",", inferSchema="true", header="true")

Find columns that are more than 90% null

threshold = df.count() * .90
null_counts = df.select([F.count(F.when(F.col(c).isNull(), c)).alias(c) for c in df.columns]).collect()[0].asDict()
to_drop = [k for k, v in null_counts.items() if v >= threshold ]

Drop Null columns

clean = df.drop(*to_drop)
display(clean)

Create a subset of records

subsetDF = cleanDF.limit(100).select("COMMENT_DESC")
map = { 'zip': ['ZIP'], 'moved': ['MOVED'], 'apt': ['APT'], 'box': ['P O BOX'],'street': ['STREET','ADDRESS']  }

print(subsetDF.count())
subsetDF.show()