Load CSV file

data = spark.read.csv("/path/to/file.csv", header=True, inferSchema=True)

Display data

display(data)

Filter column with condition

data.filter(data["col"] == "value").show()
data.filter(data["col"] != "value1").show()
data.filter( (data.col1 > 1) & (data.col1 < 99) ).show()
data.filter( (data.col1 == "dog") | (data.col1 == "cat") ).show()

Create new column with existing data but multiply new column by 2

data.withColumn("new_col",data["col"]*2).show()

Exclude column

data.drop("col").show()

Exclude duplicate rows

data.distinct().count()

Exclude duplicate rows for specific column

data.dropDuplicates(["col"]).count())

Sort data by column

data.orderBy("col").show()

Get avg/max/min for col2 grouped by col

from pyspark.sql.functions import min, max, avg
data.groupBy("col").agg(
    avg(data.col2),
    max(data.col2),
    min(data.col2)).show()