numpy 的布尔值切片

我们做模型时，可能需要画不同类别的标记不同颜色的值，因此就需要的numpy的布尔值索引，比如说：

# 导入可视化工具包
import matplotlib.pyplot as plt
%matplotlib inline
from sklearn.datasets import load_iris
from sklearn.cluster import KMeans
import numpy as np
import pandas as pd

X=load_iris().data
clf = KMeans(n_clusters=3,random_state=0)
clf.fit(X)
label = clf.predict(X)

# 颜色和标签列表
colors_list = ['red', 'blue', 'green']
labels_list = ['1','2','3']
x=X
for i in range(3):
    plt.scatter(x[label==i,0], x[label== i,1], s=100,c=colors_list[i],label=labels_list[i])
    
# 聚类中心点
plt.scatter(clf.cluster_centers_[:,0],clf.cluster_centers_[:,1], s=300,c='black',label='Centroids')

plt.legend()
plt.xlabel('Annual Income (k$)')
plt.ylabel('Spending Score (1-100)')
plt.show()

下面介绍一下用法以及例子

#构造数据
import  numpy as np      
names=np.array(["Bob","Joe","Will","Bob","Will","Joe","Joe"])
np1=np.random.randn(7,4)
print(names)
print(np1)

['Bob' 'Joe' 'Will' 'Bob' 'Will' 'Joe' 'Joe']
[[-0.48639127  0.65433213 -0.55487863 -1.41199409]
 [ 0.63196795  0.8091702   0.52156802 -0.7897757 ]
 [-0.2681137   1.58992163 -0.55409051  1.08141762]
 [-0.358811   -0.89604778  1.3655091   0.56664758]
 [ 1.22746199  0.47409502 -0.90998782  0.57441837]
 [-0.23616238 -1.18461867  0.68114549  1.25545332]
 [ 0.04767722  0.9783612  -0.70834461 -0.30132274]]

#布尔值索引
print(names=="Bob")
print(np1[names=="Bob"])

[ True False False  True False False False]
[[-0.48639127  0.65433213 -0.55487863 -1.41199409]
 [-0.358811   -0.89604778  1.3655091   0.56664758]]

#将布尔型数组跟切片混合使用
print(np1[names=="Bob",2:])

[[-0.55487863 -1.41199409]
 [ 1.3655091   0.56664758]]

#也可用不等号（！=），负号对条件进行操作
print(np1[names!="Bob"])

[[ 0.63196795  0.8091702   0.52156802 -0.7897757 ]
 [-0.2681137   1.58992163 -0.55409051  1.08141762]
 [ 1.22746199  0.47409502 -0.90998782  0.57441837]
 [-0.23616238 -1.18461867  0.68114549  1.25545332]
 [ 0.04767722  0.9783612  -0.70834461 -0.30132274]]

#多种条件组合（&，|等）
np1[(names=="Bob")|(names=="Will")]

array([[-0.48639127,  0.65433213, -0.55487863, -1.41199409],
       [-0.2681137 ,  1.58992163, -0.55409051,  1.08141762],
       [-0.358811  , -0.89604778,  1.3655091 ,  0.56664758],
       [ 1.22746199,  0.47409502, -0.90998782,  0.57441837]])

#为了将data中的所有负值都设置为0
np1[np1<0]=0
print(np1)

[[0.         0.65433213 0.         0.        ]
 [0.63196795 0.8091702  0.52156802 0.        ]
 [0.         1.58992163 0.         1.08141762]
 [0.         0.         1.3655091  0.56664758]
 [1.22746199 0.47409502 0.         0.57441837]
 [0.         0.         0.68114549 1.25545332]
 [0.04767722 0.9783612  0.         0.        ]]