数据处理之Matplotlib

数据处理之Matplotlib

使用 Anaconda
Numpy，matplotlib库来完成一些数据统计操作

---

1.绘制正弦曲线，并设置标题、坐标轴名称、坐标轴范围

import numpy as np 
import matplotlib.pyplot as plt 
from pylab import mpl 
mpl.rcParams['font.sans-serif'] = ['FangSong'] 
mpl.rcParams['axes.unicode_minus'] = False
x = np.arange(0, 2*np.pi, 0.01) 
y = np.sin(x) >>> plt.plot(x, y) 
plt.title(u'正弦曲线', fontdict={'size':20})      # 设置标题 
plt.xlabel(u'弧度', fontdict={'size':16})         # 显示横轴名称 
plt.ylabel(u'正弦值', fontdict={'size':16})       # 显示纵轴名称 
plt.axis([-0.1*np.pi, 2.1*np.pi, -1.1, 1.1])     # 设置坐标轴范围 
plt.show()

---

2.同一坐标系中绘制多种曲线并通过样式、宽度、颜色加以区分

 import numpy as np 
 import matplotlib.pyplot as plt 
 from pylab import mpl
 mpl.rcParams['font.sans-serif'] = ['FangSong']
 mpl.rcParams['axes.unicode_minus'] = False
 x = np.linspace(-4, 4, 200)
 f1 = np.power(10, x)
 f2 = np.power(np.e, x)
 f3 = np.power(2, x)
 plt.plot(x, f1, 'r', ls='-', linewidth=2, label='$10^x$')
 plt.plot(x, f2, 'b', ls='--', linewidth=2, label='$e^x$') 
 plt.plot(x, f3, 'g', ls=':', linewidth=2, label='$2^x$') 
 plt.axis([-4, 4, -0.5, 8]) 
 plt.text(1, 7.5, r'$10^x$', fontsize=16) 
 plt.text(2.2, 7.5, r'$e^x$', fontsize=16) 
 plt.text(3.2, 7.5, r'$2^x$', fontsize=16) 
 plt.title('幂函数曲线', fontsize=16)
 plt.legend(loc='upper left') 
 plt.show()

---

3.绘制多轴图，即将多幅子图绘制在同一画板

import matplotlib.pyplot as plt 
plt.subplot(221) # 两行两列的第1个位置 
plt.axis([-1, 2, -1, 2])
plt.axhline(y=0.5, color='b') 
plt.axhline(y=0.5, xmin=0.25, xmax=0.75, color='r')
plt.subplot(222) # 两行两列的第2个位置 
plt.axis([-1, 2, -1, 2])
plt.axvline(x=0, ymin=0, linewidth=4, color='r') 
plt.axvline(x=1.0, ymin=-0.5, ymax=0.5, linewidth=4, color='g') 
plt.subplot(212) # 两行一列的第2个位置 
plt.axis([-1, 2, -1, 2]) 
plt.axvspan(1.25, 1.55, facecolor='g', alpha=0.5) 
plt.axhspan(0.25, 0.75, facecolor='0.5', alpha=0.5) 
plt.show()

---

4.直方图的绘制

import numpy as np 
import matplotlib.pyplot as plt 
data = np.random.normal(5.0, 3.0, 1000) 
plt.hist(data) 
bins = np.arange(-5, 16, 1) 
plt.hist(data, bins) # 使用自定义的分段区域 
plt.show()

---

5.绘制散点图

import numpy as np 
import matplotlib.pyplot as plt 
x = np.random.rand(50) 
y = np.random.rand(50) 
area = np.pi * (15 * np.random.rand(50))**2 
color = 2 * np.pi * np.random.rand(50) 
plt.scatter(x, y, s=area, c=color, alpha=0.5, cmap=plt.cm.hsv)
plt.show()

---

6.绘制盒状图

import numpy as np  
import matplotlib.pyplot as plt  
import pandas as pd
def list_generator(mean,dis,number):#封装一下这个函数，用来后面生成数据
    return np.random.normal(mean,dis*dis,number)#normal分布，输入的参数是均值、标准差以及生成
    的数量
#我们生成四组数据用来做实验，我们都只生成100个数据
list1=list_generator(0.8531,0.0956,100)
list2=list_generator(0.8631,0.0656,100)
list3=list_generator(0.8731,0.1056,100)
list4=list_generator(0.8831,0.0756,100)
#把四个list导入到pandas的数据结构中，dataframe
data = pd.DataFrame({"Hausdorff":list1,
                     "City-block":list2,
                     "Wasserstein":list3,
                     "KL-divergence":list4})
data.boxplot()#这里，pandas自己有处理的过程，很方便哦。
plt.ylabel("ARI")
plt.xlabel("Dissimilarity Measures")#我们设置横纵坐标的标题。
plt.show()

---

7. 2D

import numpy as np 
import matplotlib.pyplot as plt 
y, x = np.ogrid[-2:2:200j, -3:3:300j] 
z = x * np.exp( - x**2 - y**2) 
extent = [np.min(x), np.max(x), np.min(y), np.max(y)] 
plt.subplot(121) 
cs = plt.contour(z, 10, extent=extent) 
plt.clabel(cs)
plt.subplot(122) 
plt.contourf(x.reshape(-1), y.reshape(-1), z, 20) 
plt.show() 

---

8. 3D绘图

import numpy as np 
import matplotlib.pyplot as plt 
import mpl_toolkits.mplot3d 
x, y = np.mgrid[-2:2:50j,-2:2:50j] 
z = x*np.exp(-x**2-y**2) 
ax = plt.subplot(111,projection='3d')
ax.plot_surface(x,y,z,rstride=2,cstride=1,cmap=plt.cm.coolwarm,alpha=0.8) 
ax.set_xlabel('x') 
ax.set_ylabel('y') 
ax.set_zlabel('z') 
plt.show()