Boston房价数据分析

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

#读取数据
def Get_data():
    names=['CRIM','ZN','INDUS','CHAS','NOX','RM','AGE',
           'DIS','RAD','TAX','PRTATTO','B','LSTAT','MEDV']
    data=pd.read_csv("housing.csv",names=names,delim_whitespace=True)
    return data

#数据可视化
def Date_visualization(data):
    names=['CRIM','ZN','INDUS','CHAS','NOX','RM','AGE',
           'DIS','RAD','TAX','PRTATTO','B','LSTAT','MEDV']
    #1、相关性分析
    fig=plt.figure(dpi=128)
    ax=fig.add_subplot(111)
    #matshow():把矩阵或数组绘制成图像
    #dataframe.corr():返回一个相关系数矩阵
    axf=ax.matshow(data.corr(),vmin=-1,vmax=1,interpolation='None')
    fig.colorbar(axf)
    #坐标轴设置
    ticks=np.arange(0,14)
    ax.set_xticks(ticks)
    ax.set_yticks(ticks)
    ax.set_xticklabels(names)
    ax.set_yticklabels(names)
    ax.set_title('Housing Price of Correlation',fontsize=21)
    plt.savefig('Housing Price of Correlation.png')
    plt.show()

    
    #2、箱线图
    #利用pd.dateframe.plot()画图：
    #data.plot(kind='box',subplot=True,layout=(4,4),sharex=False,sharey=False,fontsize=8)
    
    fig=plt.figure(dpi=128)

    for i in range(14):
        plt.subplot(4,4,(i+1))
        #将DataFrame对象data转成ndarray数组,否则报错
        plt.boxplot(data.values[:,i])
        plt.xlabel(names[i])
    
    plt.savefig('Housing Price of Box.png')
    plt.show()
    
    #3、密度图
    #利用pd.dateframe.plot()画图：
    #data.plot(kind='density',subplot=True,layout=(4,4),sharex=False,sharey=False,fontsize=1)
    
    fig=plt.figure(dpi=128)

    for i in range(14):
        plt.subplot(4,4,(i+1))
        #将DataFrame对象data转成ndarray数组,否则报错
        plt.hist(data.values[:,i])
        plt.xlabel(names[i])
    
    plt.savefig('Housing Price of Hist.png')
    plt.show()

    #4、散点矩阵图
    #利用pd.plotting.scatter_matrix()画图：
    fig=plt.figure(dpi=128)

    pd.plotting.scatter_matrix(data)
    
    plt.savefig('Housing Price of Scatter.png')
    plt.show()


def main():
    data=Get_data()
    Date_visualization(data)

if __name__ == "__main__":
    main()