Python人工智能数学基础-概率统计

正态分布

产生正态随机变量：

from scipy.stats import norm

# draw a single sample
print(norm.rvs(), end="\n\n") #产生1个标准正态分布的随机值

# draw 10 samples
print(norm.rvs(size=10), end="\n\n") #产生10个标准正态分布的随机值

# adjust mean ('loc') and standard deviation ('scale')
print(norm.rvs(loc=10, scale=0.1), end="\n\n") #均值为10，标准差为0.1

计算正态分布概率：

from scipy.stats import norm

# probability of x less or equal 0.3
print("P(X <0.3) = {}".format(norm.cdf(0.3)))

# probability of x in [-0.2, +0.2]
print("P(-0.2 < X < 0.2) = {}".format(norm.cdf(0.2) - norm.cdf(-0.2)))

二项分布

产生二项分布随机变量：

import numpy as np
from scipy.stats import binom

# draw a single sample
np.random.seed(42)
print(binom.rvs(p=0.3, n=10), end="\n\n")

# draw 10 samples
print(binom.rvs(p=0.3, n=10, size=10), end="\n\n")

二项分布取特定值的概率：

from scipy.stats import binom

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

# likelihood of X=1 and X=7
print("pmf(X=1) = {}\npmf(X=7) = {}".format(binom.pmf(k=1, p=0.3, n=10), binom.pmf(k=7, p=0.3, n=10)))

# continuous pdf for the plot
x_s = np.arange(11)
y_s = binom.pmf(k=x_s, p=0.3, n=10)
plt.scatter(x_s, y_s, s=100);

二项分布的累计概率：

from scipy.stats import binom

# probability of x less or equal 0.3
print("P(X <=3) = {}".format(binom.cdf(k=3, p=0.3, n=10)))

# probability of x in [-0.2, +0.2]
print("P(2 < X <= 8) = {}".format(binom.cdf(k=8, p=0.3, n=10) - binom.cdf(k=2, p=0.3, n=10)))

泊松分布

产生泊松分布随机变量：

import numpy as np
from scipy.stats import poisson

# draw a single sample
np.random.seed(42)
print(poisson.rvs(mu=10), end="\n\n")

# draw 10 samples
print(poisson.rvs(mu=10, size=10), end="\n\n")

泊松分布概率密度函数：

from scipy.stats import poisson

# additional imports 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 = poisson.pmf(k=x_s, mu=5)
plt.scatter(x_s, y_s, s=100);

泊松分布的累计概率：

from scipy.stats import poisson

# probability of x less or equal 0.3
print("P(X <=3) = {}".format(poisson.cdf(k=3, mu=5)))

# probability of x in [-0.2, +0.2]
print("P(2 < X <= 8) = {}".format(poisson.cdf(k=8, mu=5) - poisson.cdf(k=2, mu=5)))

卡方分布

产生卡方分布随机变量：

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") #df为自由度

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

卡方分布概率密度函数：

from scipy.stats import chi2

# additional imports 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);

卡方分布概率计算：

from scipy.stats import chi2

# probability of x less or equal 0.3
print("P(X <=3) = {}".format(chi2.cdf(x=3, df=4)))

# probability of x in [-0.2, +0.2]
print("P(2 < X <= 8) = {}".format(chi2.cdf(x=8, df=4) - chi2.cdf(x=2, df=4)))

Beta分布

产生Beta分布随机变量：

from scipy.stats import beta

# draw a single sample
np.random.seed(42)
print(beta.rvs(a=2, b=2), end="\n\n")

# draw 10 samples
print(beta.rvs(a=2, b=2, size=10))

Beta分布概率密度函数：

from scipy.stats import beta

# additional import for plotting
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.linspace(0, 1, 100)
y_s = beta.pdf(a=2, b=2, x=x_s)
plt.scatter(x_s, y_s);

Beta分布概率计算：

from scipy.stats import beta

# probability of x less or equal 0.3
print("P(X <0.3) = {:.3}".format(beta.cdf(a=2, b=2, x=0.3)))

# probability of x in [-0.2, +0.2]
print("P(-0.2 < X < 0.2) = {:.3}".format(beta.cdf(a=2, b=2, x=0.2) - beta.cdf(a=2, b=2, x=-0.2)))

相关性分析

import numpy as np
tang = np.array([[10, 10, 8, 9, 7],  
       [4, 5, 4, 3, 3],  
       [3, 3, 1, 1, 1]])
print('data source')
print(tang)

print('corrcoef between rowdata')
print(np.corrcoef(tang))

print('corrcoef between columndata')
print(np.corrcoef(tang,rowvar=0));