具有两个目标 Python 的特征选择

如何解决具有两个目标 Python 的特征选择

我有一个包含 11 个属性的数据框，其中两个是目标。我想选择要处理的加权属性。但是，我只能通过将一个属性固定为类来找到属性选择，就我而言，我有两个。我该如何解决？我试过了。

dat=pd.read_csv("data.csv")
X = dat[:-1]
y = dat[1:]  
from sklearn.feature_selection import RFE
from sklearn.linear_model import LogisticRegression
model = LogisticRegression()
rfe = RFE(model,3)
fit = rfe.fit(X,y)
print("Num Features: %s" % (fit.n_features_))
print("Selected Features: %s" % (fit.support_))
print("Feature Ranking: %s" % (fit.ranking_))

使用以下示例：

{'Unnamed:': {0: 0,1: 1,2: 2,3: 3,4: 4},'0': {0: 0,'lat': {0: 4132327000.0,1: 4132323000.0,2: 4132319000.0,3: 4132316000.0,4: 4132310000.0},'lng': {0: 201491778.0,1: 201492068.0,2: 201492358.0,3: 201492982.0,4: 201492395.0},'angle': {0: 143.787324,1: 176.575953,2: 176.575951,3: 172.046101,4: 184.433275},'vel': {0: 4.908362,1: 4.054739,2: 4.054739,3: 3.76571,4: 6.341526},'vel_x': {0: 3.670851,1: 3.235835,2: 3.235839,3: 2.777059,4: 3.838336},'vel_y': {0: 3.258354,1: 2.443416,2: 2.44341,3: 2.543328,4: 5.047982},'d': {0: 4.908362,'dx': {0: 2.90314,1: 2.903142,2: 0.242451,3: 0.242451,4: 0.521688},'dy': {0: 3.9648,1: 3.9648,2: 4.052189,3: 4.052189,4: 3.733803},'a': {0: 9.351342e-07,1: 0.8536232,2: 8.077179e-09,3: 0.2890291,4: 2.575816},'ax': {0: 4.8e-05,1: 0.435016,2: 5e-06,3: 6.012898,4: 1.061277},'ay': {0: 5.5e-05,1: 5.701771,2: 6e-06,3: 0.099918,4: 2.504655}}

所以，我想保留 lat 和 lng，但试图找到那些增强预测的属性。