头哥教学平台-泰坦尼克生还预测-可视化与探索性数据分析

第1关 存活率与性别和船舱等级之间的关系

import pandas as pd
import numpy as np
import seaborn as sns
import warnings
warnings.filterwarnings("ignore")
sns.set()
import matplotlib.pyplot as plt
from matplotlib.pyplot import MultipleLocator

def student():
    # ********* Begin *********#
    a = pd.read_csv('Task1/train.csv')
    fig,axes = plt.subplots(1,2)
    sns.violinplot(x='Pclass',y='Age',data=a,split=True,ax=axes[0],hue='Survived')
    sns.violinplot(x='Sex',y='Age',split=True,data=a,hue='Survived',ax=axes[1])
    plt.savefig('Task1/img/T1.png')
    plt.show()
    # ********* End *********#

第2关 各个口岸的生还率

import pandas as pd
import numpy as np
import seaborn as sns
import warnings
warnings.filterwarnings("ignore")
sns.set()
import matplotlib.pyplot as plt
from matplotlib.pyplot import MultipleLocator

def student():
    # ********* Begin *********#

    a = pd.read_csv('Task2/train.csv')
    sns.factorplot(data=a,x='Embarked',y='Survived')
    plt.savefig('Task2/img/T1.png')
    plt.show()


    # ********* End *********#

第3关 统计各登船口岸的登船人数以及生还率

import pandas as pd
import numpy as np
import seaborn as sns
import warnings
warnings.filterwarnings("ignore")
sns.set()
import matplotlib.pyplot as plt


def student():
    # ********* Begin *********#
    a = pd.read_csv('Task3/train.csv')
    fig,ax = plt.subplots(2,2,figsize=(10,10))
    sns.countplot("Embarked",data=a,ax=ax[0,0])
    ax[0,0].set_title("No.Of Passengers Boarded")
    sns.countplot("Embarked",hue="Sex",data=a,ax=ax[0,1])
    ax[0,1].set_title("Male-Female Split for Embarked")
    sns.countplot("Embarked",hue="Survived",data=a,ax=ax[1,0])
    ax[1,0].set_title("Embarked vs Survived")
    sns.countplot("Embarked",hue='Pclass',data=a,ax=ax[1,1])
    ax[1,1].set_title("Embarked vs Pclass")
    plt.savefig("Task3/img/T1.jpg")
    plt.show()


    # ********* End *********#

第4关 船客兄弟姐妹妻子丈夫的数量与生存率之间的关系

import pandas as pd
import numpy as np
import seaborn as sns
import warnings
warnings.filterwarnings("ignore")
sns.set()
import matplotlib.pyplot as plt


def student():
    # ********* Begin *********#
    data = pd.read_csv("Task4/train.csv")
    f,ax = plt.subplots(1,2,figsize=(10,10))
    sns.barplot(x="SibSp",y="Survived",data=data,ax=ax[0])
    ax[0].set_title("SibSp vs Survived")
    sns.catplot(x="SibSp",y="Survived",data=data,ax=ax[1],kind="point")
    ax[1].set_title("SibSp vs Survived")
    plt.close(2)
    plt.savefig("Task4/img/T1.png")
    
    # ********* End *********#