Question

所以我正在使用RandomForest和GridsearchCV做一些参数。这是我的代码。

#Import 'GridSearchCV' and 'make_scorer'
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import make_scorer

Create the parameters list you wish to tune
parameters = {'n_estimators':[5,10,15]}

#Initialize the classifier
clf = GridSearchCV(RandomForestClassifier(), parameters)

#Make an f1 scoring function using 'make_scorer' 
f1_scorer = make_scorer(f1_scorer)

#Perform grid search on the classifier using the f1_scorer as the scoring method
grid_obj = GridSearchCV(clf, param_grid=parameters, scoring=f1_scorer,cv=5)

print(clf.get_params().keys())

#Fit the grid search object to the training data and find the optimal parameters
grid_obj = grid_obj.fit(X_train_100,y_train_100)

所以问题是以下错误：＆＃34; ValueError：估算器GridSearchCV的参数max_features无效。使用estimator.get_params().keys()检查可用参数列表。＆＃34;

我按照错误给出的建议和print的输出（clf.get_params（）。keys（））如下所示。然而，即使我将这些标题复制并粘贴到我的参数字典中，我仍然会收到错误。我一直在寻找堆栈溢出，大多数人都使用非常类似的参数字典来挖掘。任何人都知道如何解决这个问题？再次感谢！

dict_keys（[＆＃39; pre_dispatch＆＃39;，＆＃39; cv＆＃39;，＆＃39; estimator__max_features＆＃39;，＆＃39; param_grid＆＃39;，＆＃39; refit＆＃39; ，＆＃39; estimator__min_impurity_split＆＃39;，＆＃39; n_jobs＆＃39;，＆＃39; estimator__random_state＆＃39;，＆＃39; error_score＆＃39;，＆＃39; verbose＆＃39;，＆＃39; estimator__min_samples_split＆＃39;，＆＃39; estimator__n_jobs＆＃39;，＆＃39; fit_params＆＃39;，＆＃39; estimator__min_weight_fraction_leaf＆＃39;，＆＃39;评分＆＃39;，＆＃39; estimator__warm_start＆＃39;，＆＃39; estimator__criterion＆＃39;，＆＃39; estimator__verbose＆＃39;，＆＃39; estimator__bootstrap＆＃39;，＆＃39; estimator__class_weight＆＃39;，＆＃39; estimator__oob_score＆＃39;，＆＃39; iid＆＃39;，＆＃39; estimator＆＃39;，＆＃39; estimator__max_depth＆＃39;，＆＃39; estimator__max_leaf_nodes＆＃39;，＆＃39; estimator__min_samples_leaf＆＃39;，＆＃39; estimator__n_estimators＆＃39;，＆＃39; return_train_score＆＃39;]）

Answer 1

我认为问题在于两行：

clf = GridSearchCV(RandomForestClassifier(), parameters)
grid_obj = GridSearchCV(clf, param_grid=parameters, scoring=f1_scorer,cv=5)

这实际上是在创建一个具有以下结构的对象：

grid_obj = GridSearchCV(GridSearchCV(RandomForestClassifier()))

可能比你想要的还要多GridSearchCV。

GridsearchCV与RandomForest

1 个答案: