process dataframe in groups code example

Example: Groups the DataFrame using the specified columns

# Groups the DataFrame using the specified columns

df.groupBy().avg().collect()
# [Row(avg(age)=3.5)]
sorted(df.groupBy('name').agg({'age': 'mean'}).collect())
# [Row(name='Alice', avg(age)=2.0), Row(name='Bob', avg(age)=5.0)]
sorted(df.groupBy(df.name).avg().collect())
# [Row(name='Alice', avg(age)=2.0), Row(name='Bob', avg(age)=5.0)]
sorted(df.groupBy(['name', df.age]).count().collect())
# [Row(name='Alice', age=2, count=1), Row(name='Bob', age=5, count=1)]