matplotlib.pyplot中的hist函数

# -*- coding:utf-8 -*-
import numpy as np
import matplotlib.pyplot as plt

#概率分布直方图
#高斯分布
#均值为0
mean = 0
#标准差为1，反应数据集中还是分散的值
sigma = 1
x=mean+sigma*np.random.randn(10000)
fig,(ax0,ax1) = plt.subplots(nrows=2,figsize=(9,6))
#第二个参数是柱子宽一些还是窄一些，越大越窄越密
ax0.hist(x,40,normed=1,histtype='bar',facecolor='yellowgreen',alpha=0.75)
##pdf概率分布图，一万个数落在某个区间内的数有多少个
ax0.set_title('pdf')
ax1.hist(x,20,normed=1,histtype='bar',facecolor='pink',alpha=0.75,cumulative=True,rwidth=0.8)
#cdf累计概率函数，cumulative累计。比如需要统计小于5的数的概率
ax1.set_title("cdf")
fig.subplots_adjust(hspace=0.4)
plt.show()

# -*- coding:utf-8 -*-
import numpy as np
import matplotlib.pyplot as plt

matplotlib.pyplot.hist(
x, bins=10, range=None, normed=False, 
weights=None, cumulative=False, bottom=None, 
histtype=u'bar', align=u'mid', orientation=u'vertical', 
rwidth=None, log=False, color=None, label=None, stacked=False, 
hold=None, **kwargs)

# -*- coding:utf-8 -*-
import numpy as np
import matplotlib.mlab as mlab
import matplotlib.pyplot as plt

# example data
mu = 100  # mean of distribution
sigma = 15  # standard deviation of distribution
x = mu + sigma * np.random.randn(10000)

num_bins = 50
# the histogram of the data
n, bins, patches = plt.hist(x, num_bins, normed=1, facecolor='blue', alpha=0.5)
# add a 'best fit' line
y = mlab.normpdf(bins, mu, sigma)
plt.plot(bins, y, 'r--')
plt.xlabel('Smarts')
plt.ylabel('Probability')
plt.title(r'Histogram of IQ: $\mu=100$, $\sigma=15$')

# Tweak spacing to prevent clipping of ylabel
plt.subplots_adjust(left=0.15)
plt.show()

# -*- coding:utf-8 -*-
import pandas as pd
import numpy as np
import random


data = np.zeros((1000,1000),dtype=int)
for i in range(len(data)):#这里速度比较慢，因为随机给1000*1000的数组赋值
    for j in range(len(data[0])):
        data[i][j] = random.randint(1,20)#赋值的范围是1-20中的任意一个

#首先构造数据，这里注意构造的是一维数组可以使用pandas中的Series，如果是二维数组使用DataFrame。
data_m = pd.DataFrame(data)
data_m = data_m[1].value_counts()#注意value_counts函数统计一个series上的数据情况
data_m = data_m.sort_index()#给统计后的数据排序
print(data_m)

#随后开始画直方图
import matplotlib.pyplot as plt
plt.hist(data[0])
plt.show()

plt.hist(data[0],bins=20)
plt.show()

import matplotlib.pyplot as plt
plt.hist(data[0])
plt.show()

import matplotlib.pyplot as plt
plt.hist(data[0],bins=20)
plt.show()

# -*- coding: utf-8 -*-
import numpy as np
import matplotlib
import matplotlib.mlab as mlab
import matplotlib.pyplot as plt
import pandas as pd


data = pd.read_csv("D:/apaper/pic/s2.csv")
data.head()
songTi = matplotlib.font_manager.FontProperties(fname='C:\Windows\Fonts\simsun.ttc')

x = data.loc[:,'n_songs']
#normed=True是频率图，默认是频数图
plt.hist(x, bins=30, range=(0,100), normed=True,
                weights=None, cumulative=False, bottom=None,
                histtype=u'bar', align=u'left', orientation=u'vertical',
                rwidth=0.8, log=False, color=None, label=None, stacked=False,
                hold=None)
plt.xticks(fontproperties=songTi,fontsize=12)
plt.yticks(fontproperties=songTi,fontsize=12)
plt.xlabel('用户听歌数量（首）',fontproperties=songTi,fontsize=14)
plt.ylabel('人数占比（%）',fontproperties=songTi,fontsize=14)
# plt.legend(fontsize=12)
fig = plt.gcf()
fig.set_size_inches(7.2, 4.2)
fig.savefig('D:/apaper/pic/用户听歌数量2.png', dpi=100)
plt.show()

songTi = matplotlib.font_manager.FontProperties(fname='C:\Windows\Fonts\simsun.ttc')

plt.xticks(fontproperties=songTi,fontsize=12)
plt.yticks(fontproperties=songTi,fontsize=12)
plt.xlabel('用户听歌数量（首）',fontproperties=songTi,fontsize=14)
plt.ylabel('人数占比（%）',fontproperties=songTi,fontsize=14)
# plt.legend(fontsize=12)

fig = plt.gcf()
fig.set_size_inches(7.2, 4.2)
fig.savefig('D:/apaper/pic/用户听歌数量2.png', dpi=100)