grouped_multiple = df.groupby(['Team', 'Pos']).agg({'Age': ['mean', 'min', 'max']})
grouped_multiple.columns = ['age_mean', 'age_min', 'age_max']
grouped_multiple = grouped_multiple.reset_index()
print(grouped_multiple)
import pandas as pd
# Group multiple columns and get statistics
df = df.groupby(["store", "type"])["weekly_sales"].sum()
# Group multiple columns and multiple statistics
df = df.groupby(["store", "type"])["weekly_sales"].agg([sum, min, max])
# Display DataFrame
print(df)In [11]: df.groupby(['col5', 'col2']).size()
Out[11]:
col5 col2
1 A 1
D 3
2 B 2
3 A 3
C 1
4 B 1
5 B 2
6 B 1
dtype: int64
#formatting
candidates_salary_by_month = candidates_df.groupby('month').agg(num_cand_month = \
('num_candidates', 'sum'), \
avg_sal = ('salary', 'mean')).style.format('{:.0f}')
print(candidates_salary_by_month)df['COUNTER'] =1 #initially, set that counter to 1.
group_data = df.groupby(['Alphabet','Words'])['COUNTER'].sum() #sum function
print(group_data)Group By X means put all those with the same value for X in the one group.
Group By X, Y means put all those with the same values for both X and Y in the one group.