datawhale_Day2_task02_随机抽样

这两天太忙，待重新学习

随机抽样

二项分布

import numpy as np
import matplotlib.pyplot as plt
from scipy import stats

np.random.seed(20200605)
n = 9# 做某件事情的次数
p = 0.1# 做某件事情成功的概率
size = 50000
x = np.random.binomial(n, p, size)
'''或者使用binom.rvs
#使用binom.rvs(n, p, size=1)函数模拟一个二项随机变量,可视化地表现概率
y = stats.binom.rvs(n, p, size=size)#返回一个numpy.ndarray
'''
print(np.sum(x == 0) / size)  # 0.3897

plt.hist(x)
plt.xlabel('随机变量：成功次数')
plt.ylabel('样本中出现的次数')
plt.show()
#它返回一个列表，列表中每个元素表示随机变量中对应值的概率
s = stats.binom.pmf(range(10), n, p)
print(np.around(s, 3))
# [0.387 0.387 0.172 0.045 0.007 0.001 0.    0.    0.    0.   ]

泊松分布

import numpy as np
from scipy import stats
import matplotlib.pyplot as plt

np.random.seed(20200605)
lam = 42 / 6# 平均值：平均每十分钟接到42/6次订票电话
size = 50000
x = np.random.poisson(lam, size)
'''或者
#模拟服从泊松分布的50000个随机变量
x = stats.poisson.rvs(lam,size=size)
'''
print(np.sum(x == 6) / size)  # 0.14988

plt.hist(x)
plt.xlabel('随机变量：每十分钟接到订票电话的次数')
plt.ylabel('50000个样本中出现的次数')
plt.show()
#用poisson.pmf(k, mu)求对应分布的概率:概率质量函数 (PMF)
x = stats.poisson.pmf(6, lam)
print(x)  # 0.14900277967433773

超几何分布

import numpy as np
from scipy import stats
import matplotlib.pyplot as plt

np.random.seed(20200605)
size = 500000
x = np.random.hypergeometric(ngood=7, nbad=13, nsample=12, size=size)
'''或者
#用rvs(M, n, N, loc=0, size=1, random_state=None)模拟
x = stats.hypergeom.rvs(M=20,n=7,N=12,size=size)
'''
print(np.sum(x == 3) / size)  # 0.198664

plt.hist(x, bins=8)
plt.xlabel('狗的数量')
plt.ylabel('50000个样本中出现的次数')
plt.title('超几何分布',fontsize=20)
plt.show()

"""
M 为总体容量
n 为总体中具有成功标志的元素的个数
N,k 表示抽取N个元素有k个是成功元素
"""
x = range(8)
#用hypergeom.pmf(k, M, n, N, loc)来计算k次成功的概率
s = stats.hypergeom.pmf(k=x, M=20, n=7, N=12)
print(np.round(s, 3))
# [0.    0.004 0.048 0.199 0.358 0.286 0.095 0.01 ]

均匀分布

import numpy as np
import matplotlib.pyplot as plt
from scipy import stats

np.random.seed(20200614)
a = 0
b = 100
size = 50000
x = np.random.uniform(a, b, size=size)
print(np.all(x >= 0))  # True
print(np.all(x < 100))  # True
y = (np.sum(x < 50) - np.sum(x < 10)) / size
print(y)  # 0.40144

plt.hist(x, bins=20)
plt.show()

a = stats.uniform.cdf(10, 0, 100)
b = stats.uniform.cdf(50, 0, 100)
print(b - a)  # 0.4

正态分布

import numpy as np
import matplotlib.pyplot as plt
from scipy import stats

np.random.seed(20200614)
size = 50000
x = np.random.randn(size)
y1 = (np.sum(x < 1) - np.sum(x < -1)) / size
y2 = (np.sum(x < 2) - np.sum(x < -2)) / size
y3 = (np.sum(x < 3) - np.sum(x < -3)) / size
print(y1)  # 0.68596
print(y2)  # 0.95456
print(y3)  # 0.99744

plt.hist(x, bins=20)
plt.show()

y1 = stats.norm.cdf(1) - stats.norm.cdf(-1)
y2 = stats.norm.cdf(2) - stats.norm.cdf(-2)
y3 = stats.norm.cdf(3) - stats.norm.cdf(-3)
print(y1)  # 0.6826894921370859
print(y2)  # 0.9544997361036416
print(y3)  # 0.9973002039367398

指数分布

import numpy as np
import matplotlib.pyplot as plt
from scipy import stats

np.random.seed(20200614)
lam = 7
size = 50000
x = np.random.exponential(1 / lam, size)
'''或者
#rvs(loc=0, scale=1/lam, size=size, random_state=None)模拟
'''
y1 = (np.sum(x < 1 / 7)) / size
y2 = (np.sum(x < 2 / 7)) / size
y3 = (np.sum(x < 3 / 7)) / size
print(y1)  # 0.63218
print(y2)  # 0.86518
print(y3)  # 0.95056

plt.hist(x, bins=20)
plt.show()

y1 = stats.expon.cdf(1 / 7, scale=1 / lam)
y2 = stats.expon.cdf(2 / 7, scale=1 / lam)
y3 = stats.expon.cdf(3 / 7, scale=1 / lam)
print(y1)  # 0.6321205588285577
print(y2)  # 0.8646647167633873
print(y3)  # 0.950212931632136

等等未完待续