如何用几行代码做特征选择

from sklearn.feature_selection import RFE from sklearn.linear_model import LinearRegression #Load boston housing dataset as an example X = np.array(train1[feature_use].fillna(-1))[1:train1.size,:] Y = np.array(train1['target'])[1:train1.size] #print(X) #print(Y) names = feature_use #use linear regression as the model lr = LinearRegression() #rank all features, i.e continue the elimination until the last one rfe = RFE(lr, n_features_to_select=1) rfe.fit(X,Y) print("Features sorted by their score:") #print(sorted(zip(map(lambda x: round(x, 4), rf.feature_importances_), names), reverse=True)) sortedlist = sorted(zip(map(lambda x: round(x, 4), rfe.ranking_), names), reverse=True) print(sortedlist) feature_use = [] for index in sortedlist[len(sortedlist)-70 : ]: if index[0]>0: feature_use.append(index[1]) print(feature_use)

上面的X为数据集的特征集合 Y为标签集合
在sortlist里对特征的重要性进行了排序

最近做机器学习的一点感悟是，特征的影响远比模型参数来的大，特征是现实世界在算法中的倒影。
在特征工程中要对业务有非常深的理解，强调返璞归真，删除无效特征，减少引起干扰的特征。
加特征的过程需要一个一个来，还要多思考这些特征之间的关系，是否是强烈线性相关的。

# random forest select features ''' from sklearn.ensemble import RandomForestRegressor import numpy as np #Load boston housing dataset as an example X = np.array(train1[feature_use].fillna(-1))[1:train1.size,:] Y = np.array(train1['target'])[1:train1.size] print(X) print(Y) names = feature_use rf = RandomForestRegressor() rf.fit(X, Y) print("Features sorted by their score:") print(sorted(zip(map(lambda x: round(x, 4), rf.feature_importances_), names), reverse=True)) '''