CODEWITHSUNDEEP
pythonmachine-learningclassificationpredictionstacking-context
Elena
Elena

Reputation: 61

StackingClassifier has no atribute to predict_proba()

I am trying to construct a stacking classifier for predicting each class, at the same time I need the probability for each elemnt to be in the predicted class. I tried using the predict_proba() method but I seem to run to the same error "'StackingClassifier' object has no attribute 'pedict_proba'". Please help!

hgbm = HistGradientBoostingClassifier(l2_regularization=3, learning_rate=0.5, random_state=42, class_weight="balanced")
bbc = BalancedBaggingClassifier(
    estimator = hgbm,
    n_estimators = 10, 
    random_state = 42,
    n_jobs = -1,

)

brf = BalancedRandomForestClassifier(n_estimators = 200, random_state = 42, n_jobs = -1)
CLF =  RidgeClassifier(random_state = 42, alpha = 0.8, max_iter = 200, class_weight = 'balanced')
Class_st = StackingClassifier(estimators=[("BalancedBaggingClassifier", bbc),
                                   ("BalancedRandomForestClassifier", brf)],
                       final_estimator = CLF, stack_method='predict_proba', cv = 5, n_jobs = -1)

Class_st.fit(X_train, y_train)
prob = Class_st.pedict_proba(X_test)

The error:

'StackingClassifier' object has no attribute 'pedict_proba'

Upvotes: 1

Views: 469

Answers (1)

Saxtheowl
Saxtheowl

Reputation: 4658

There is a typo in your code you have predict_proba(), but you typed pedict_proba() . so this should be prob = Class_st.predict_proba(X_test)

Also RidgeClassifier used as your final estimator does not have the predict_proba() method by default

Use it like this instead:

from sklearn.linear_model import RidgeClassifierCV

CLF = RidgeClassifierCV(cv=5, alphas=[0.8], class_weight='balanced')

Upvotes: 1

Related Questions