[Pandas] groupby 카테고라이징

import pandas as pd

df = pd.read_csv('data/occupations.csv')

occ_groups = df.groupby('occupation')
# type(age_groupsBy)
mean_occ_groups = occ_groups.mean(numeric_only=True)
mean_occ_groups.sort_values('age')

 

 

 

직업별 여성 비율 높은 순서 구하기

import pandas as pd

df = pd.read_csv('data/occupations.csv')

# 여기에 코드를 작성하세요
# df.head()

occ_group = df.groupby('occupation')
df_male = df.loc[df['gender']=='M']
male_group = df_male.groupby('occupation')
# print(male_group.count())

df_female = df.loc[df['gender']=='F']
female_group = df_female.groupby('occupation')
# print(female_group.count())

count_occ = occ_group.count()

female_ratio_occ_by_gen = female_group.count() / count_occ
female_ratio_occ_by_gen.fillna(0, inplace=True)
female_ratio_occ_by_gen['gender'].sort_values(ascending=False)