使用sklearn进行特征选择

from sklearn.feature_selection import VarianceThreshold
X = [[0, 0, 1], 
     [0, 1, 0], 
     [1, 0, 0], 
     [0, 1, 1], 
     [0, 1, 0], 
     [0, 1, 1]]
sel = VarianceThreshold(threshold=(.8 * (1 - .8)))
result = sel.fit_transform(X)
print(X, "\n" ,result)
复制代码

from sklearn.datasets import load_iris
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
iris = load_iris()
X, y = iris.data, iris.target
X_new = SelectKBest(chi2, k=2).fit_transform(X, y)
print(X.shape, X_new.shape)
# (150, 4) (150, 2)
复制代码

from sklearn.datasets import load_breast_cancer
from sklearn.feature_selection import SelectFdr, chi2
X, y = load_breast_cancer(return_X_y=True)
X_new = SelectFdr(chi2, alpha=0.01).fit_transform(X, y)
X.shape, X_new.shape
# ((569, 30), (569, 16))
复制代码

from sklearn.svm import SVC
from sklearn.datasets import load_digits
from sklearn.feature_selection import RFE
import matplotlib.pyplot as plt
# Load the digits dataset
digits = load_digits()
X = digits.images.reshape((len(digits.images), -1))
y = digits.target
# (1797, 8, 8) 1797 (1797, 64) (1797,)
print(digits.images.shape, len(digits.images), X.shape, y.shape) 
# 创建RFE对象并对每个像素进行排序
svc = SVC(kernel="linear", C=1)
rfe = RFE(estimator=svc, n_features_to_select=1, step=1)
rfe.fit(X, y)
print(digits.images[0].shape) # (8, 8)
ranking = rfe.ranking_.reshape(digits.images[0].shape)
# Plot pixel ranking
plt.matshow(ranking, cmap=plt.cm.Blues)
plt.colorbar()
plt.title("Ranking of pixels with RFE")
plt.show()
复制代码

import matplotlib.pyplot as plt
from sklearn.svm import SVC
from sklearn.model_selection import StratifiedKFold
from sklearn.feature_selection import RFECV
from sklearn.datasets import make_classification
# 使用3个信息丰富的特征构建分类任务
X, y = make_classification(n_samples=1000, n_features=25, n_informative=3,
                           n_redundant=2, n_repeated=0, n_classes=8,
                           n_clusters_per_class=1, random_state=0)
print(X.shape, y.shape) # (1000, 25) (1000,)
# Create the RFE object and compute a cross-validated score.
svc = SVC(kernel="linear")
# “准确度”评分与正确分类数成正比
min_features_to_select = 1  # Minimum number of features to consider
rfecv = RFECV(estimator=svc, step=1, cv=StratifiedKFold(2),
              scoring='accuracy',
              min_features_to_select=min_features_to_select)
rfecv.fit(X, y)
# Optimal number of features : 3
print("Optimal number of features : %d" % rfecv.n_features_)
# 画出特征数与交叉验证分数的对比
plt.figure()
plt.xlabel("Number of features selected") 
plt.ylabel("Cross validation score (nb of correct classifications)")
plt.plot(range(min_features_to_select,
               len(rfecv.grid_scores_) + min_features_to_select),
         rfecv.grid_scores_)
plt.show()
复制代码

from sklearn.datasets import load_diabetes
diabetes = load_diabetes()
X, y = diabetes.data, diabetes.target
复制代码

import matplotlib.pyplot as plt
import numpy as np
from sklearn.linear_model import LassoCV
lasso = LassoCV().fit(X, y)
importance = np.abs(lasso.coef_)
feature_names = np.array(diabetes.feature_names)
plt.bar(height=importance, x=feature_names)
plt.title("Feature importances via coefficients")
plt.show()
复制代码

from sklearn.feature_selection import SelectFromModel
from time import time
threshold = np.sort(importance)[-3] + 0.01
tic = time()
sfm = SelectFromModel(lasso, threshold=threshold).fit(X, y)
toc = time()
print("Features selected by SelectFromModel: "
      f"{feature_names[sfm.get_support()]}")
print(f"Done in {toc - tic:.3f}s")
# Features selected by SelectFromModel: ['s1' 's5']
# Done in 0.067s
复制代码

from sklearn.feature_selection import SequentialFeatureSelector
tic_fwd = time()
sfs_forward = SequentialFeatureSelector(lasso, n_features_to_select=2,
                                        direction='forward').fit(X, y)
toc_fwd = time()
tic_bwd = time()
sfs_backward = SequentialFeatureSelector(lasso, n_features_to_select=2,
                                         direction='backward').fit(X, y)
toc_bwd = time()
print("Features selected by forward sequential selection: "
      f"{feature_names[sfs_forward.get_support()]}")
print(f"Done in {toc_fwd - tic_fwd:.3f}s")
print("Features selected by backward sequential selection: "
      f"{feature_names[sfs_backward.get_support()]}")
print(f"Done in {toc_bwd - tic_bwd:.3f}s")
# Features selected by forward sequential selection: ['bmi' 's5']
# Done in 2.177s
# Features selected by backward sequential selection: ['bmi' 's5']
# Done in 6.433s
复制代码