数据科学分布——卡方分布

概念

通俗的讲就是通过小数量的样本容量去预估总体容量的分布情况。
卡方检验就是统计样本的实际观测值与理论推断值之间的偏离程度。

若n个相互独立的随机变量ξ₁，ξ₂，…,ξn ，均服从标准正态分布（也称独立同分布于标准正态分布），则这n个服从标准正态分布的随机变量的平方和构成一新的随机变量，其分布规律称为卡方分布（chi-square distribution）。

其中

# 加载功能包
import numpy as np
import scipy.stats as stats
import matplotlib.pyplot as plt
import matplotlib.style as style
from IPython.core.display import HTML

# 指定大小
%matplotlib inline
style.use('fivethirtyeight')
plt.rcParams['figure.figsize']=(14,7)
plt.figure(dpi=100)

# PDF 概率密度函数
plt.plot(np.linspace(0,20,100),stats.chi2.pdf(np.linspace(0,20,100),df=4))
# linspace选择取值；chi2为卡方分布
plt.fill_between(np.linspace(0,20,100),stats.chi2.pdf(np.linspace(0,20,100),df=4),alpha=.15)
# 进行图像填充

# CDF累计概率密度函数
plt.plot(np.linspace(0,20,100),stats.chi2.cdf(np.linspace(0,20,100),df=4))

# 补充图设置：LEGEND、TICKS与TITLE
plt.xticks(np.arange(0,21,2))
plt.text(x=8, y=0.2, s="PDF(normed)", alpha = .75, weight="bold", color="#008fd5")
plt.text(x=10, y=0.8, s="CDF", alpha = .75, weight="bold", color="#fc4f30")
plt.xticks(np.arange(0,21,2))
plt.tick_params(axis = 'both', which ='major', labelsize = 18)
plt.axhline(y = 0, color ='black', linewidth = 1.3, alpha = 7)
plt.text(x = -2, y = 1.2, s = r"Chi-Squared $(\chi^{2})$ Distribution - Overview", fontsize = 26, weight = 'bold', alpha = .75)
plt.text(x = -2, y = 1.1, s = " $y \\sim \\chi^{2}(k)$, given $k$=4.", fontsize = 19, alpha = .75)

自由度

plt.figure(dpi=100)

# PDF k = 1
plt.plot(np.linspace(0,15,500),stats.chi2.pdf(np.linspace(0,15,500),df=1))
plt.fill_between(np.linspace(0,15,500),stats.chi2.pdf(np.linspace(0,15,500),df=1),alpha=.15)

# PDF k = 3
plt.plot(np.linspace(0,15,500),stats.chi2.pdf(np.linspace(0,15,500),df=3))
plt.fill_between(np.linspace(0,15,500),stats.chi2.pdf(np.linspace(0,15,500),df=3),alpha=.15)

# PDF k = 6
plt.plot(np.linspace(0,15,100),stats.chi2.pdf(np.linspace(0,15,100),df=6))
plt.fill_between(np.linspace(0,15,100),stats.chi2.pdf(np.linspace(0,15,100),df=6),alpha=.15)

# LEGEND TICKS TITLE
plt.text(x=2, y=0.65, s="$k = 1$", rotation=65, alpha = .75, weight="bold", color="#008fd5")
plt.text(x=3, y=0.65, s="k = 3", rotation=65, alpha = .75, weight="bold", color="#fc4f30")
plt.text(x=4, y=0.65, s="k = 6", rotation=65, alpha = .75, weight="bold", color="#e5ae38")
plt.tick_params(axis = 'both', which ='major', labelsize = 18)
plt.axhline(y = 0, color ='black', linewidth = 1.3, alpha = 7)
plt.text(x = -1, y = 2.5, s = "Chi-Squared Distribution - $ k $", fontsize = 26, weight = 'bold', alpha = .75)

随机生成

import numpy as np
from scipy.stats import chi2

# draw a single sample
np.random.seed(42)
print(chi2.rvs(df=4),end="\n\n")

# draw 10 samples
print(chi2.rvs(df=4,size=10), end="\n\n")

4.787358779738473

[2.98892946 2.76456717 2.76460459 9.29942882 5.73341246 2.262156
4.93962895 3.99792053 0.43182989 1.34248457]

概率密度函数

from scipy.stats import chi2

# additional imoprts for plotting purpose
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
plt.rcParams["figure.figsize"] = (14,7)

# continuous pdf for the plot
x_s = np.arange(15)
y_s = chi2.pdf(x=x_s,df=4)
plt.scatter(x_s, y_s,s=100);

累积概率密度函数

from scipy.stats import chi2

# probabolity of x less or equal 3
print("P(X<=3)={}".format(chi2.cdf(x=3,df=4)))

# probability of x in [2,8]
print("P(2<X<8)={}".format(chi2.cdf(x=8,df=4)-chi2.cdf(x=2,df=4)))

P(X<=3)=0.4421745996289252
P(2<X<8)=0.6441806878992138