# 50th Percentile
def q50(x):
return x.quantile(0.5)
# 90th Percentile
def q90(x):
return x.quantile(0.9)
my_DataFrame.groupby(['AGGREGATE']).agg({'MY_COLUMN': [q50, q90, 'max']})df.groupby("Column1", sort=True)["Column2"].mean()In [8]: grouped = df.groupby('A')
In [9]: grouped = df.groupby(['A', 'B'])
# Aggregate on the entire DataFrame without group
df.agg({"age": "max"}).collect()
# [Row(max(age)=5)]
from pyspark.sql import functions as F
df.agg(F.min(df.age)).collect()
# [Row(min(age)=2)]df.groupby(lambda _ : True).agg(new_col_name = ('col_name', 'agg_function'))