pyspark_df_groupby.py

# GroupBy a column and count
df.groupby("column").count().show()

# GroupBy a column and sum
df.groupby("column1").sum("column2").show()

# GroupBy with multiple columns
df.groupby("column1", "column2").count().show()

# GroupBy with multiple columns and sum multiple columns
df.groupby("column1", "column2").sum("column3", "column4").show()