File "/usr/lib/spark/python/lib/pyspark.zip/pyspark/sql/column.py", line 443, in isin code example

Example 1: A distributed collection of data grouped into named columns

# A distributed collection of data grouped into named columns

people = sqlContext.read.parquet("...")

ageCol = people.age

# To create DataFrame using SQLContext
people = sqlContext.read.parquet("...")
department = sqlContext.read.parquet("...")

people.filter(people.age > 30).join(
  department, people.deptId == department.id).groupBy(
  department.name, "gender").agg({"salary": "avg", "age": "max"})

Example 2: Create a DataFrame with single pyspark.sql.types.LongType column named id, containing elements in a range

# Create a DataFrame with single column named id, containing elements in a range

spark.range(1, 7, 2).collect()
# [Row(id=1), Row(id=3), Row(id=5)]

spark.range(3).collect()
# [Row(id=0), Row(id=1), Row(id=2)]