泰坦尼克號沉沒之謎，用數據還原真相——Titanic獲救率分析（用pyecharts）

泰坦尼克號獲救率數據分析報告，用數據揭露真相。

一，船上乘客生存率分析報告

泰坦尼克號生存率僅有38%的，可見此次事件救援不力，救生艇嚴重不足，且泰坦尼克號號撞得是冰山，海水冷，沒有救生艇，在水里凍死的乘客不少。

二，哪個年齡段存活率最高（青年人（18歲以下），中年人（18到50歲），老年人（50歲以上））

數據分析：看圖我們得到，年輕人獲救率最高50%，老年人獲救率最低0.39，中年人死亡人數最多。發生生命危險時，自救能力最強的中年人還是起到了中流砥柱的作用。不要再叫猥瑣油膩中年男了哦，他們才是社會的扛把子。

3,女性乘客和男性乘客獲救率分析

從圖中可以看到，女性的獲救率遠遠高於男性，女士優先不是一句空話。

4，船上一等艙二等艙三等艙的乘客貧富差距情況

從圖中可以看出，一等艙占全船24%的人數，消費額時全船的67%的金額。嗯，符合著名的二八法則，80%的財富掌握在20%的人手里。

5，艙位和獲救率關系分析

從圖中可以看出，一等艙的獲救率時三等艙的三倍左右，說明發生沉船事故時，一等艙先上救生艇的，有錢能使鬼推磨，古人誠不欺我也。

 

 附上本人源代碼：

import pandas as pd
import matplotlib.pyplot as plt#導入繪制函數
import numpy as np#導入數組庫
from pylab import *#轉義漢字
mpl.rcParams['font.sans-serif'] = ['SimHei']#
mpl.rcParams['axes.unicode_minus'] = False#

from pyecharts import Pie,Bar,Gauge,EffectScatter,WordCloud,Map,Grid,Line,Timeline
import random


df_Titanic = pd.read_csv('Titanic.csv')
# print(df_Titanic)

#1,一獲救率是多少
def Rescued_rate():

    t1 = df_Titanic['Survived'].count()
    t2 = df_Titanic[df_Titanic['Survived']==1]['Survived'].count()
    t3=round(t2/t1,2)
    print('一，存活率為：{}'.format(t3))


    #Titanic存活率可視化
    attr = ['獲救率','死亡率' ]
    v1 = [t3,(1-t3)]
    pie = Pie('Titanic生存率報告')
    pie.add('生存率', attr, v1, is_label_show=True)
    pie.render('TItanic_1.html')

Rescued_rate()
#2,哪個年齡段存活率最高
def age_survived():
    #18歲以下的人存活率
    young_survived = df_Titanic[(df_Titanic['Age']<=18)&(df_Titanic['Survived']==1)]['Survived'].count()
    young_all = df_Titanic[df_Titanic['Age']<=18]['Survived'].count()
    #18歲到50歲的存活率
    middle_survived = df_Titanic[(df_Titanic['Age']<50)&(df_Titanic['Age']>18)&(df_Titanic['Survived']==1)]['Survived'].count()
    middle_all = df_Titanic[(df_Titanic['Age']<50)&(df_Titanic['Age']>18)]['Survived'].count()
    #50歲以上乘客的存活率
    old_survived = df_Titanic[(df_Titanic['Age'] >= 50) & (df_Titanic['Survived'] == 1)]['Survived'].count()
    old_all = df_Titanic[df_Titanic['Age'] >= 50]['Survived'].count()
    #三者的生存率
    young_odds = round(young_survived/young_all,2)
    middle_odds = round(middle_survived/middle_all,2)
    old_odds = round(old_survived/old_all,2)
    # list=[young_odds,middle_odds,old_odds]
    # max_odds = max(list)
    # df_odds = pd.Series([young_odds,middle_odds,old_odds])
    # df_odds.plot(kind ='bar')
    # plt.show()


    print('二，年輕人，中年人，老年人生存幾率分別為{}，{}，{}'.format(young_odds,middle_odds,old_odds))
    #獲救率可視化對比圖
    attr = ['青少年', '中年人', '老年人']
    v1 = [young_odds,middle_odds,old_odds]
    v2 = [(1-young_odds), (1-middle_odds), (1-old_odds)]
    v3 = [young_all,middle_all,old_all]

    bar = Bar('Titanic不同年齡段獲救率對比')

    bar.add('獲救率', attr, v1, mark_point=['average','max','min'], is_stack=True)
    bar.add('死亡率', attr, v2, mark_line=['min', 'max'], is_stack=True)  # stack是否堆疊顯示
    bar.add('人數',attr,v3,mark_point=['average','max','min'],is_stack=False)
    bar.render('Titanic_2.html')





age_survived()


#3，女性存活率和男性存活率哪個高
def Rescued_rate_man():
    s_man =df_Titanic[(df_Titanic['Sex']=='male')&(df_Titanic['Survived']==1)]['Sex'].count()#獲救的男人數
    c_man = df_Titanic[df_Titanic['Sex']=='male']['Sex'].count()#男人總數
    rescued_man = round(s_man/c_man,2)#男人獲救率
    s_woman = df_Titanic[(df_Titanic['Sex']=='female')&(df_Titanic['Survived']==1)]['Sex'].count()
    c_woman = df_Titanic[df_Titanic['Sex']=='female']['Sex'].count()
    rescued_woman = round(s_woman/c_woman,2)
    if rescued_woman > rescued_man:
        print('三，女性獲救率高')
    else:
        print('三，男性獲救率高')

    #
    attr = ['女性', '男性']
    v1 = [rescued_woman,rescued_man]
    # v2 = [(1 - rescued_woman), (1 - rescued_man)]
    v3 = [c_woman,c_man]

    bar = Bar('Titanic——男性女性獲救率報告')

    bar.add('獲救率', attr, v1, mark_point=['average', 'max', 'min'], is_stack=True)
    # bar.add('死亡率', attr, v2,mark_point=['average', 'max', 'min'],  is_stack=True)
    bar.add('人數', attr, v3,mark_point=['average', 'max', 'min'], is_stack=False)# stack是否堆疊顯示
    bar.render('Titanic_3.html')








Rescued_rate_man()


#船上的貧富差距
def wealth_gap():
    #一等艙的人均消費
    consume_one = round(df_Titanic[df_Titanic['Pclass']==1]['Fare'].mean(),2)
    consume_two = round(df_Titanic[df_Titanic['Pclass']==2]['Fare'].mean(),2)
    consume_three = round(df_Titanic[df_Titanic['Pclass']==3]['Fare'].mean(),2)
    consume_std = round(df_Titanic['Fare'].std(),2)
    #一等艙二等艙三等艙的人數
    person_one = df_Titanic[df_Titanic['Pclass']==1]['Survived'].count()
    person_two = df_Titanic[df_Titanic['Pclass'] == 2]['Survived'].count()
    person_three = df_Titanic[df_Titanic['Pclass'] == 3]['Survived'].count()
    #一等艙二等艙三等艙的消費總額
    consumeall_one =df_Titanic[df_Titanic['Pclass']==1]['Fare'].sum()
    consumeall_two = df_Titanic[df_Titanic['Pclass'] == 2]['Fare'].sum()
    consumeall_three = df_Titanic[df_Titanic['Pclass'] == 3]['Fare'].sum()

    print('四，一等艙人均消費：{}，二等艙人均消費：{}，三等艙人均消費:{},人均消費標准差：{}'.format(consume_one,consume_two,consume_three,consume_std))

    #可視化
    attr = ['一等艙', '二等艙','三等艙']
    v2 = [consume_one,consume_two,consume_three]
    v1 = [person_one,person_two,person_three]
    v3 = [consumeall_one,consumeall_two,consumeall_three]

    bar = Bar('Titanic——貧富差距報告')

    bar.add('人均消費', attr, v2, mark_point=['average', 'max', 'min'], is_stack=False)
    bar.add('艙位人數', attr, v1,mark_point=['average', 'max', 'min'],  is_stack=False)  # stack是否堆疊顯示
    bar.add('消費總額', attr, v3, mark_point=['average', 'max', 'min'],is_stack=False)
    bar.render('Titanic_4.html')

wealth_gap()

#頭等艙的生存率是否高於三等艙

def Survival_comparison():
    #一等艙的獲救率
    s1=df_Titanic[(df_Titanic['Pclass']==1)&(df_Titanic['Survived']==1)]['Survived'].count()
    c1 = df_Titanic[df_Titanic['Pclass']==1]['Survived'].count()
    svl_1 = round(s1/c1,2)
    #二等艙的獲救率
    s2 = df_Titanic[(df_Titanic['Pclass'] == 2) & (df_Titanic['Survived'] == 1)]['Survived'].count()
    c2 = df_Titanic[df_Titanic['Pclass'] == 2]['Survived'].count()
    svl_2 = round(s2 / c2,2)
    #三等艙的獲救率
    s3 = df_Titanic[(df_Titanic['Pclass'] == 3) & (df_Titanic['Survived'] == 1)]['Survived'].count()
    c3 = df_Titanic[df_Titanic['Pclass'] == 3]['Survived'].count()
    svl_3 = round(s3 / c3,2)
    if svl_1>svl_2>svl_3:
        print('五，一等艙二等艙三等艙的獲救率分別為：{}，{}，{},一等艙獲救率最高'.format(svl_1,svl_2,svl_3))
    else:
        print('獲救率和艙位關系不大')
    #艙位和獲救率的關系
    attr = ['一等艙', '二等艙', '三等艙']
    v2 = [c1/100, c2/100,c3/100]
    v1 = [svl_1,svl_2,svl_3]

    bar = Bar('Titanic——艙位和獲救率關系')

    bar.add('獲救率', attr, v1, mark_point=['average', 'max', 'min'], is_stack=False)
    bar.add('艙位人數(/百人)', attr, v2, mark_point=['average', 'max', 'min'], is_stack=False)  # stack是否堆疊顯示
    bar.render('Titanic_4.html')


Survival_comparison()
#6，帶家屬的乘客占的比率，有家屬是否會影響生存率
def family_survived():
    family_yes = df_Titanic[(df_Titanic['SibSp']==1)|(df_Titanic['Parch']==1)]['Survived'].count()#帶家屬的乘客人數
    family_no = df_Titanic[(df_Titanic['SibSp'] == 0) & (df_Titanic['Parch'] == 0)]['Survived'].count()#不帶家屬的乘客人數
    family_all = df_Titanic['Survived'].count()
    family_odds = round(family_yes/family_all,2)
    #帶家屬獲救的人數
    family_survive = df_Titanic[(df_Titanic['SibSp']==1)|(df_Titanic['Parch']==1)&(df_Titanic['Survived']==1)]['Survived'].count()
    #不帶家屬獲救的人數
    family_no_survive = df_Titanic[(df_Titanic['SibSp']==0)&(df_Titanic['Parch']==0)&(df_Titanic['Survived']==1)]['Survived'].count()

    #帶家屬獲救的幾率
    family_survive_odds = round(family_survive/family_yes,2)
    #不帶家屬獲救的幾率
    familyno_survive_odds = round(family_no_survive / family_no, 2)
    if family_survive_odds>familyno_survive_odds:
        print('六，帶家屬的生存率為{}，不帶家屬的生存率為{},帶家屬的生存率高一些'.format(family_survive_odds,familyno_survive_odds))
    else:
        print('帶家屬的乘客獲救幾率和其他乘客一樣')

family_survived()

#七，從哪個港口登陸是否影響生存率
def port_survived():
    #S口進入獲救的人數
    S_survived = df_Titanic[(df_Titanic['Survived']==1)&(df_Titanic['Embarked']=='S')]['Survived'].count()
    #S口進入的總人數
    S_all = df_Titanic[df_Titanic['Embarked']=='S']['Survived'].count()
    #C口進入獲救的人數
    C_survived = df_Titanic[(df_Titanic['Survived']==1)&(df_Titanic['Embarked']=='C')]['Survived'].count()
    #C口進入的總人數
    C_all = df_Titanic[df_Titanic['Embarked'] == 'C']['Survived'].count()
    #Q口進入獲救的人數
    Q_survived = df_Titanic[(df_Titanic['Survived']==1)&(df_Titanic['Embarked']=='Q')]['Survived'].count()
    #Q口進入的總人數
    Q_all = df_Titanic[df_Titanic['Embarked'] == 'Q']['Survived'].count()
    #從S，C,Q,進入生存的幾率
    s_odds = round(S_survived/S_all,2)
    c_odds = round(C_survived/C_all,2)
    q_odds = round(Q_survived/Q_all,2)
    print('七，s,c,q港口進入的乘客的生存率分別為{}，{}，{}'.format(s_odds,c_odds,q_odds))
port_survived()