python课的作业_Anscombe's quartet

最新推荐文章于 2025-02-06 15:27:21 发布

原创最新推荐文章于 2025-02-06 15:27:21 发布 · 506 阅读

1 ·

CC 4.0 BY-SA版权

本文通过导入多个Python库，如pandas、numpy等，对Anscombe数据集进行深入分析，包括计算不同子集的均值、方差及相关系数，并使用statsmodels库建立线性回归模型，最后利用seaborn绘制了散点图。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

题目：

代码：

import random  
  
import numpy as np  
import scipy as sp  
import pandas as pd  
import matplotlib.pyplot as plt  
import seaborn as sns  
  
import statsmodels.api as sm  
import statsmodels.formula.api as smf  
import statistics as sta   
import scipy.stats.stats as stats  
  
  
anscombe = sns.load_dataset("anscombe")  
print(anscombe)  
  
Xarray_I = anscombe.x[:10].values    
Xarray_II = anscombe.x[11:21].values  
Xarray_III = anscombe.x[22:32].values  
Xarray_IV = anscombe.x[33:43].values  
  
print("Xarray in I:", Xarray_I)  
print("Xarray in II:", Xarray_II)  
print("Xarray in III:", Xarray_III)  
print("Xarray in IV:", Xarray_IV)  
  
Xmean_I = np.mean(Xarray_I)           
print("mean of x in I: ", Xmean_I)  
Xmean_II = np.mean(Xarray_II)  
print("mean of x in II: ", Xmean_II)  
Xmean_III = np.mean(Xarray_III)  
print("mean of x in III: ", Xmean_III)  
Xmean_IV = np.mean(Xarray_IV)  
print("mean of x in IV: ", Xmean_IV)  
  
Xvariance_I = sta.variance(Xarray_I)    
print("variance of x in I: ", Xvariance_I)  
Xvariance_II = sta.variance(Xarray_II)  
print("variance of x in II: ", Xvariance_II)  
Xvariance_III = sta.variance(Xarray_III)  
print("variance of x in III: ", Xvariance_III)  
Xvariance_IV = sta.variance(Xarray_IV)  
print("variance of x in IV: ", Xvariance_IV)  
  
print(' ')  
  
Yarray_I = anscombe.y[:10].values   
Yarray_II = anscombe.y[11:21].values  
Yarray_III = anscombe.y[22:32].values  
Yarray_IV = anscombe.y[33:43].values  
  
print("Yarray in I:", Yarray_I)  
print("Yarray in II:", Yarray_II)  
print("Yarray in III:", Yarray_III)  
print("Yarray in IV:", Yarray_IV)  
  
Ymean_I = np.mean(Yarray_I)    
print("mean of y in I: ", Ymean_I)  
Ymean_II = np.mean(Yarray_II)  
print("mean of y in II: ", Ymean_II)  
Ymean_III = np.mean(Yarray_III)  
print("mean of y in III: ", Ymean_III)  
Ymean_IV = np.mean(Yarray_IV)  
print("mean of y in IV: ", Ymean_IV)  
  
Yvariance_I = sta.variance(Yarray_I)    
print("variance of y in I: ", Yvariance_I)  
Yvariance_II = sta.variance(Yarray_II)  
print("variance of y in II: ", Yvariance_II)  
Yvariance_III = sta.variance(Yarray_III)  
print("variance of y in III: ", Yvariance_III)  
Yvariance_IV = sta.variance(Yarray_IV)  
print("variance of y in IV: ", Yvariance_IV)  
  
print('')  
cof_I = stats.pearsonr(Xarray_I, Yarray_I)[0]  
cof_II = stats.pearsonr(Xarray_II, Yarray_II)[0]  
cof_III = stats.pearsonr(Xarray_III, Yarray_III)[0]  
cof_IV = stats.pearsonr(Xarray_IV, Yarray_IV)[0]  
print("correlation coefficient of I: ", cof_I)  
print("correlation coefficient of II: ", cof_II)  
print("correlation coefficient of III: ", cof_III)  
print("correlation coefficient of IV: ", cof_IV)  
  
print(" ")  
  
X_I = sm.add_constant(Xarray_I)     
model_I = sm.OLS(Yarray_I, X_I)  
result_I = model_I.fit()  
params_I = result_I.params  
print("DatasetI: y =", params_I[0], "+", params_I[1], "* x")  
  
X_II = sm.add_constant(Xarray_II)  
model_II = sm.OLS(Yarray_II, X_II)  
result_II = model_II.fit()  
params_II = result_II.params  
print("DatasetII: y =", params_II[0], "+", params_II[1], "* x")  
  
X_III = sm.add_constant(Xarray_III)  
model_III = sm.OLS(Yarray_III, X_III)  
result_III = model_III.fit()  
params_III = result_III.params  
print("DatasetIII: y =", params_III[0], "+", params_III[1], "* x")  
  
X_IV = sm.add_constant(Xarray_IV)  
model_IV = sm.OLS(Yarray_IV, X_IV)  
result_IV = model_IV.fit()  
params_IV = result_IV.params  
print("DatasetIV: y =", params_IV[0], "+", params_IV[1], "* x")  
  
sns.set(style='whitegrid')      
g = sns.FacetGrid(anscombe, col="dataset", hue="dataset", size=3)  
g.map(plt.scatter, 'x', 'y')  
plt.show()

结果展示：