我尝试创建模型，创建模型，使用SelectFromModel选择特征，然后转储模型，当我以相同阈值重新加载模型时，出现Fitting错误，同时使用SelectFromModel进行转换
from numpy import loadtxt
from numpy import sort
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.feature_selection import SelectFromModel
import pickle
# load data
print("X Shape ",X.shape," Test Shape ",encoded.shape)
X_train, X_test, y_train, y_test = train_test_split(X, encoded, test_size=0.33, random_state=7)
print("Train Shape ",X_train.shape," Test Shape ",X_test.shape)
num_trees=100
# fit model on all training data
model = RandomForestClassifier(n_estimators=num_trees, max_features='sqrt',criterion='entropy')
model.fit(X_train, y_train)
# select features using threshold
selection = SelectFromModel(model, threshold=0.014, prefit=True)
select_X_train = selection.transform(X_train)
print(select_X_train.shape)
# train model
selection_model = RandomForestClassifier(n_estimators=num_trees, max_features='sqrt',criterion='entropy')
selection_model.fit(select_X_train, y_train)
# eval model
select_X_test = selection.transform(X_test)
print(select_X_test.shape)
y_pred = selection_model.predict(select_X_test)
predictions = [round(value) for value in y_pred]
accuracy = accuracy_score(y_test, predictions)
print("Thresh=%.3f, n=%d, Accuracy: %.2f%%" % (0.009, select_X_train.shape[1], accuracy*100.0))
pickle.dump(selection_model, open("SelectedModel.sav", 'wb'))
pickle.dump(selection_model, open("ParentModel.sav", 'wb'))
print("Train Shape ",select_X_train.shape," Test Shape ",select_X_test.shape)
输出：
X Shape (18103, 34) Test Shape (18103,)
Train Shape (12129, 34) Test Shape (5974, 34)
(12129, 27)
(5974, 27)
Thresh=0.009, n=27, Accuracy: 98.26%
Train Shape (12129, 27) Test Shape (5974, 27)
尝试重新加载模型
import numpy as np
loaded_Parentmodel = pickle.load(open("ParentModel.sav", 'rb'))
loaded_Selectedmodel = pickle.load(open("ParentModel.sav", 'rb'))
selection = SelectFromModel(loaded_Parentmodel, threshold=0.014, prefit=True)
from sklearn.externals import joblib
X1 = validationDfs.drop(['NEWSTATUS'], axis=1).values
Y1 = validationDfs[['NEWSTATUS']].values
print("Validation Shape Prior Selection",X1.shape)
select_X1 = selection.transform(X1)
错误：
Validation Shape Prior Selection (739, 34)
ValueError: X has a different shape than during fitting.