一、variance特征的选择

使用的是 low variance小方差

二、代码的实例

from sklearn.feature_selection import VarianceThreshold

from sklearn import datasets

import matplotlib.pyplot as plt

import numpy as np

d:\python3.7.4\lib\importlib\_bootstrap.py:219: RuntimeWarning: numpy.ufunc size changed, may indicate binary incompatibility. Expected 192 from C header, got 216 from PyObject
  return f(*args, **kwds)

X,y = datasets.load_iris(True)
# 可视化，数据X，不能进行可视化！4个属性，4维空间
X.shape
vt = VarianceThreshold(threshold=0.5)
# 自古多情留不住，从来套路得人心！
vt.fit(X)
X2 = vt.transform(X)
X2[:5]

array([[5.1, 1.4, 0.2],
       [4.9, 1.4, 0.2],
       [4.7, 1.3, 0.2],
       [4.6, 1.5, 0.2],
       [5. , 1.4, 0.2]])

可视化

from mpl_toolkits.mplot3d.axes3d import Axes3D

fig = plt.figure(figsize=(9,6))#二维
ax3 = Axes3D(fig)
ax3.scatter(X2[:,0],X2[:,1],X2[:,2],c = y)
ax3.view_init(90,0)#调整3D图像视图方向！

output_4_0.png

X,y = datasets.load_wine(True)

# 阈值，给多好合适呢？
# 代码验证，给多个选择一个最好的！
# 后验！
vt = VarianceThreshold(1.0)
X3 = vt.fit_transform(X)
X3.shape
display(X[:5],X3[:5])

array([[1.423e+01, 1.710e+00, 2.430e+00, 1.560e+01, 1.270e+02, 2.800e+00,
        3.060e+00, 2.800e-01, 2.290e+00, 5.640e+00, 1.040e+00, 3.920e+00,
        1.065e+03],
       [1.320e+01, 1.780e+00, 2.140e+00, 1.120e+01, 1.000e+02, 2.650e+00,
        2.760e+00, 2.600e-01, 1.280e+00, 4.380e+00, 1.050e+00, 3.400e+00,
        1.050e+03],
       [1.316e+01, 2.360e+00, 2.670e+00, 1.860e+01, 1.010e+02, 2.800e+00,
        3.240e+00, 3.000e-01, 2.810e+00, 5.680e+00, 1.030e+00, 3.170e+00,
        1.185e+03],
       [1.437e+01, 1.950e+00, 2.500e+00, 1.680e+01, 1.130e+02, 3.850e+00,
        3.490e+00, 2.400e-01, 2.180e+00, 7.800e+00, 8.600e-01, 3.450e+00,
        1.480e+03],
       [1.324e+01, 2.590e+00, 2.870e+00, 2.100e+01, 1.180e+02, 2.800e+00,
        2.690e+00, 3.900e-01, 1.820e+00, 4.320e+00, 1.040e+00, 2.930e+00,
        7.350e+02]])



array([[   1.71,   15.6 ,  127.  ,    5.64, 1065.  ],
       [   1.78,   11.2 ,  100.  ,    4.38, 1050.  ],
       [   2.36,   18.6 ,  101.  ,    5.68, 1185.  ],
       [   1.95,   16.8 ,  113.  ,    7.8 , 1480.  ],
       [   2.59,   21.  ,  118.  ,    4.32,  735.  ]])