2018年大数据比赛专科组 第3部分 数据可视化

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from pandas import DataFrame,Series

df = pd.read_table('tiantic')

# 扇形图，也就是饼图
s1 = (df['Sex'] == 'female').sum()
s2 = (df['Sex'] == 'male').sum()
list1 = [s1,s2]
list2 = ['female','male']
# expl是为了分割圆
expl = [0,0.1]
# 使圆为一个正圆
plt.axes(aspect=1)
plt.pie(x = list1, labels= list2,explode=expl,autopct='%3.1f %%')
plt.title("Sex Proportion")
plt.savefig('6.png')
plt.show()

#以下是两种不同的方式去画堆叠柱状图
# 1、堆叠柱状图
d1 = ((df["Pclass"]==1)&(df["Survived"]==0)).sum()
d11 = ((df["Pclass"]==1)&(df["Survived"]==1)).sum()
d2 = ((df["Pclass"]==2)&(df["Survived"]==0)).sum()
d22 = ((df["Pclass"]==2)&(df["Survived"]==1)).sum()
d3 = ((df["Pclass"]==3)&(df["Survived"]==0)).sum()
d33 = ((df["Pclass"]==3)&(df["Survived"]==1)).sum()
lists = [d1,d2,d3]
lists1= [d11,d22,d33]
name_list = ["1",'2',"3"]
plt.rcParams['font.sans-serif']=['SimHei']
plt.bar(range(len(lists)),lists,label = 'Unsurvived',fc='r')
plt.bar(range(len(lists)),lists1,bottom = lists,label = 'Survived',tick_label=name_list,fc='g')
plt.xlabel("乘客等级")
plt.ylabel('人数')
plt.title("各乘客等级的获救与遇难情况")
plt.legend()
plt.savefig("7.png")
plt.show()

# 2、堆叠柱状图
x1 = df.Embarked[df.Survived == 0].value_counts()
x2 = df.Embarked[df.Survived == 1].value_counts()
x = pd.DataFrame({"未获救":x1,"获救":x2})
plt.rcParams['font.sans-serif']=['SimHei']
x.plot.bar(stacked= True)
plt.title("各登陆港口乘客的获救与遇难情况")
plt.xlabel("登录港口")
plt.ylabel("人数")
plt.legend()
plt.savefig('8.png')
plt.show()