titanic barplot

 

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns


titanic_df =pd.read_csv('train.csv')
def get_category(age):
  cat=''
  if age <= -1: cat = 'Unknown'
  elif age <= 5: cat = 'Baby'
  elif age <= 12: cat = 'Child'
  elif age <= 18: cat = 'Teenager'
  elif age <= 25: cat = 'Student'
  elif age <= 35: cat = 'Young Adult'
  elif age <= 60: cat = 'Adult'
  else: cat = 'Elderly'
              
  return cat


plt.figure(figsize=(10,6))

#X축의 값을 순차적으로 표시하기 위한 설정 
group_names = ['Unknown', 'Baby', 'Child', 'Teenager', 'Student', 'Young Adult', 'Adult', 'Elderly']

# lambda 식에 위에서 생성한 get_category( ) 함수를 반환값으로 지정. 
# get_category(X)는 입력값으로 'Age' 컬럼값을 받아서 해당하는 cat 반환
titanic_df['Age_cat'] = titanic_df['Age'].apply(lambda x : get_category(x))

titanic_df
sns.barplot(x='Age_cat', y = 'Survived', hue='Sex', data=titanic_df, order=group_names)