pivot (GroupedData)
Pivots a column of the current DataFrame and performs the specified aggregation.
Syntax
pivot(pivot_col, values=None)
Parameters
Parameter | Type | Description |
|---|---|---|
| str | Name of the column to pivot. |
| list, optional | List of values that will be translated to columns in the output |
Returns
GroupedData
Examples
Python
from pyspark.sql import Row, functions as sf
df1 = spark.createDataFrame([
Row(course="dotNET", year=2012, earnings=10000),
Row(course="Java", year=2012, earnings=20000),
Row(course="dotNET", year=2012, earnings=5000),
Row(course="dotNET", year=2013, earnings=48000),
Row(course="Java", year=2013, earnings=30000),
])
# Compute the sum of earnings for each year by course with each course as a separate column.
df1.groupBy("year").pivot("course", ["dotNET", "Java"]).sum("earnings").sort("year").show()
# +----+------+-----+
# |year|dotNET| Java|
# +----+------+-----+
# |2012| 15000|20000|
# |2013| 48000|30000|
# +----+------+-----+
# Without specifying column values (less efficient).
df1.groupBy("year").pivot("course").sum("earnings").sort("year").show()
# +----+-----+------+
# |year| Java|dotNET|
# +----+-----+------+
# |2012|20000| 15000|
# |2013|30000| 48000|
# +----+-----+------+
# Using a nested column as the pivot column.
df2 = spark.createDataFrame([
Row(training="expert", sales=Row(course="dotNET", year=2012, earnings=10000)),
Row(training="junior", sales=Row(course="Java", year=2012, earnings=20000)),
Row(training="expert", sales=Row(course="dotNET", year=2012, earnings=5000)),
Row(training="junior", sales=Row(course="dotNET", year=2013, earnings=48000)),
Row(training="expert", sales=Row(course="Java", year=2013, earnings=30000)),
])
df2.groupBy("sales.year").pivot("sales.course").agg(sf.sum("sales.earnings")).sort("year").show()
# +----+-----+------+
# |year| Java|dotNET|
# +----+-----+------+
# |2012|20000| 15000|
# |2013|30000| 48000|
# +----+-----+------+