泰坦尼克号获救率数据分析报告，用数据揭露真相。
一，船上乘客生存率分析报告
泰坦尼克号生存率仅有38%的，可见此次事件救援不力，救生艇严重不足，且泰坦尼克号号撞得是冰山，海水冷，没有救生艇，在水里冻死的乘客不少。
二，哪个年龄段存活率最高（青年人（18岁以下），中年人（18到50岁），老年人（50岁以上））
数据分析：看图我们得到，年轻人获救率最高50%，老年人获救率最低0.39，中年人死亡人数最多。发生生命危险时，自救能力最强的中年人还是起到了中流砥柱的作用。不要再叫猥琐油腻中年男了哦，他们才是社会的扛把子。
3,女性乘客和男性乘客获救率分析
从图中可以看到，女性的获救率远远高于男性，女士优先不是一句空话。
4，船上一等舱二等舱三等舱的乘客贫富差距情况
从图中可以看出，一等舱占全船24%的人数，消费额时全船的67%的金额。嗯，符合著名的二八法则，80%的财富掌握在20%的人手里。
5，舱位和获救率关系分析
从图中可以看出，一等舱的获救率时三等舱的三倍左右，说明发生沉船事故时，一等舱先上救生艇的，有钱能使鬼推磨，古人诚不欺我也。
附上本人源代码：
import pandas as pd
import matplotlib.pyplot as plt#导入绘制函数
import numpy as np#导入数组库
from pylab import *#转义汉字
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) #1,一获救率是多少
def Rescued_rate(): t1 = df_Titanic['Survived'].count()
t2 = df_Titanic[df_Titanic['Survived']==1]['Survived'].count()
t3=round(t2/t1,2)
print('一，存活率为：{}'.format(t3)) #Titanic存活率可视化
attr = ['获救率','死亡率' ]
v1 = [t3,(1-t3)]
pie = Pie('Titanic生存率报告')
pie.add('生存率', attr, v1, is_label_show=True)
pie.render('TItanic_1.html') Rescued_rate()
#2,哪个年龄段存活率最高
def age_survived():
#18岁以下的人存活率
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岁到50岁的存活率
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岁以上乘客的存活率
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，年轻人，中年人，老年人生存几率分别为{}，{}，{}'.format(young_odds,middle_odds,old_odds))
#获救率可视化对比图
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不同年龄段获救率对比') bar.add('获救率', 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是否堆叠显示
bar.add('人数',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个高
def Rescued_rate_man():
s_man =df_Titanic[(df_Titanic['Sex']=='male')&(df_Titanic['Survived']==1)]['Sex'].count()#获救的男人数
c_man = df_Titanic[df_Titanic['Sex']=='male']['Sex'].count()#男人总数
rescued_man = round(s_man/c_man,2)#男人获救率
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，女性获救率高')
else:
print('三，男性获救率高') #
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——男性女性获救率报告') bar.add('获救率', 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('人数', attr, v3,mark_point=['average', 'max', 'min'], is_stack=False)# stack是否堆叠显示
bar.render('Titanic_3.html') Rescued_rate_man() #船上的贫富差距
def wealth_gap():
#一等舱的人均消费
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)
#一等舱二等舱三等舱的人数
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()
#一等舱二等舱三等舱的消费总额
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('四，一等舱人均消费：{}，二等舱人均消费：{}，三等舱人均消费:{},人均消费标准差：{}'.format(consume_one,consume_two,consume_three,consume_std)) #可视化
attr = ['一等舱', '二等舱','三等舱']
v2 = [consume_one,consume_two,consume_three]
v1 = [person_one,person_two,person_three]
v3 = [consumeall_one,consumeall_two,consumeall_three] bar = Bar('Titanic——贫富差距报告') bar.add('人均消费', attr, v2, mark_point=['average', 'max', 'min'], is_stack=False)
bar.add('舱位人数', attr, v1,mark_point=['average', 'max', 'min'], is_stack=False) # stack是否堆叠显示
bar.add('消费总额', attr, v3, mark_point=['average', 'max', 'min'],is_stack=False)
bar.render('Titanic_4.html') wealth_gap() #头等舱的生存率是否高于三等舱 def Survival_comparison():
#一等舱的获救率
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)
#二等舱的获救率
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)
#三等舱的获救率
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('五，一等舱二等舱三等舱的获救率分别为：{}，{}，{},一等舱获救率最高'.format(svl_1,svl_2,svl_3))
else:
print('获救率和舱位关系不大')
#舱位和获救率的关系
attr = ['一等舱', '二等舱', '三等舱']
v2 = [c1/100, c2/100,c3/100]
v1 = [svl_1,svl_2,svl_3] bar = Bar('Titanic——舱位和获救率关系') bar.add('获救率', attr, v1, mark_point=['average', 'max', 'min'], is_stack=False)
bar.add('舱位人数(/百人)', attr, v2, mark_point=['average', 'max', 'min'], is_stack=False) # stack是否堆叠显示
bar.render('Titanic_4.html') Survival_comparison()
#6，带家属的乘客占的比率，有家属是否会影响生存率
def family_survived():
family_yes = df_Titanic[(df_Titanic['SibSp']==1)|(df_Titanic['Parch']==1)]['Survived'].count()#带家属的乘客人数
family_no = df_Titanic[(df_Titanic['SibSp'] == 0) & (df_Titanic['Parch'] == 0)]['Survived'].count()#不带家属的乘客人数
family_all = df_Titanic['Survived'].count()
family_odds = round(family_yes/family_all,2)
#带家属获救的人数
family_survive = df_Titanic[(df_Titanic['SibSp']==1)|(df_Titanic['Parch']==1)&(df_Titanic['Survived']==1)]['Survived'].count()
#不带家属获救的人数
family_no_survive = df_Titanic[(df_Titanic['SibSp']==0)&(df_Titanic['Parch']==0)&(df_Titanic['Survived']==1)]['Survived'].count() #带家属获救的几率
family_survive_odds = round(family_survive/family_yes,2)
#不带家属获救的几率
familyno_survive_odds = round(family_no_survive / family_no, 2)
if family_survive_odds>familyno_survive_odds:
print('六，带家属的生存率为{}，不带家属的生存率为{},带家属的生存率高一些'.format(family_survive_odds,familyno_survive_odds))
else:
print('带家属的乘客获救几率和其他乘客一样') family_survived() #七，从哪个港口登陆是否影响生存率
def port_survived():
#S口进入获救的人数
S_survived = df_Titanic[(df_Titanic['Survived']==1)&(df_Titanic['Embarked']=='S')]['Survived'].count()
#S口进入的总人数
S_all = df_Titanic[df_Titanic['Embarked']=='S']['Survived'].count()
#C口进入获救的人数
C_survived = df_Titanic[(df_Titanic['Survived']==1)&(df_Titanic['Embarked']=='C')]['Survived'].count()
#C口进入的总人数
C_all = df_Titanic[df_Titanic['Embarked'] == 'C']['Survived'].count()
#Q口进入获救的人数
Q_survived = df_Titanic[(df_Titanic['Survived']==1)&(df_Titanic['Embarked']=='Q')]['Survived'].count()
#Q口进入的总人数
Q_all = df_Titanic[df_Titanic['Embarked'] == 'Q']['Survived'].count()
#从S，C,Q,进入生存的几率
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港口进入的乘客的生存率分别为{}，{}，{}'.format(s_odds,c_odds,q_odds))
port_survived()