机器学习 - 特征筛选与降维

特征决定了最优效果的上限，算法与模型只是让效果更逼近这个上限，所以特征工程与选择什么样的特征很重要！

以下是一些特征筛选与降维技巧

# -*- coding:utf-8 -*-
import scipy as sc
import libsvm_file_process as data_process
import numpy as np
from minepy import MINE
from sklearn.feature_selection import VarianceThreshold
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
from sklearn.feature_selection import f_regression
from sklearn.feature_selection import RFE
from sklearn.svm import SVR
from sklearn.linear_model import LogisticRegression
from sklearn.decomposition import PCA
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

class feature_select:
    """
    特征筛选方式：
        相关链接：http://scikit-learn.org/stable/modules/classes.html#module-sklearn.feature_selection
        皮尔逊相关性
        互信息
        单因素 - 卡方判断，F值，假正率
        方差过滤
        递归特征消除法 - 每次消除一个特征，依据是特征前面的系数
        基于模型（LR/GBDT等）的特征选择 SelectFromModel
            模型（LR/GBDT）必须有feature_importances_ 或 coef_这个属性
    降维：
        PCA（unsurperised）：一般用于无监督情况下的降维，有监督的时候，也可以小幅降维 去除噪音，然后再使用LDA 降维

        LDA（surperised）:本质上是一个分类器,在使用上，要求降低的维度要小于分类的维度
    """

    def __init__(self):
        self.data_path = "/trainData/libsvm2/"
        self.trainData = ["20180101"]
        # 计算互信息
        self.mine = MINE(alpha=0.6, c=15, est="mic_approx")
        # 方差过滤 一般用于无监督学习
        self.variance_filter = VarianceThreshold(threshold=0.1)
        # chi2 - 卡方检验; f_regression - f值; SelectFpr-假正率;等
        self.chi_squared = SelectKBest(f_regression, k=2)
        # 递归特征消除
        self.estimator = LogisticRegression()  # SVR(kernel="linear")
        self.selector = RFE(self.estimator, 5, step=1)
        # PCA 降维
        self.pca = PCA(n_components=5)
        # LDA 降维
        self.lda = LinearDiscriminantAnalysis(n_components=2)

    def select(self):
        for i in range(len(self.trainData)):
            generator = data_process.get_data_batch(self.data_path + self.trainData[i] + "/part-00000", 100000)
            labels, features = generator.next()
            # 方差过滤
            filter1 = self.variance_filter.fit_transform(features)
            print filter1.shape, features.shape
            print self.variance_filter.get_support()
            # 卡方检验
            filter2 = self.chi_squared.fit_transform(features, labels)
            print filter2.shape
            print self.chi_squared.get_support()
            # 递归特征消除（比较耗时 暂时先注释掉）
            # self.selector.fit(features, labels)
            # print self.selector.support_
            # PCA 降维
            transform1 = self.pca.fit_transform(features)
            print ‘transform1:‘, transform1
            # LDA降维
            self.lda.fit(features, labels)
            transform2 = self.lda.transform(features)
            print ‘transform2:‘, transform2
            for j in range(int(features.shape[1]) - 870):
                features_j = features[0:, j + 870: j + 871]
                self.mine.compute_score(features_j.flatten(), labels.flatten())
                # 计算互信息
                print self.mine.mic()
                # 计算皮尔逊系数
                print j, sc.stats.pearsonr(features_j.reshape(-1, 1), labels.reshape(-1, 1))

if __name__ == ‘__main__‘:
    feature_util = feature_select()
    feature_util.select()

原文地址：https://www.cnblogs.com/tengpan-cn/p/8445224.html