用 scikit-learn 和 Pandas 制作機器學習模型，但我認為它的准確性有問題

Question

我正在使用 Pandas 和 scikit-learning 處理分類模型。 我發現模型的准確率太高而且都一樣，我不知道為什么

decision_tree = tree.DecisionTreeClassifier()
decision_tree = decision_tree.fit(X_train,y_train)
print("Test set accuracy = ", model.score(X_test, y_test))

Test set accuracy =  0.9615384615384616

logistic_regression = LogisticRegression()
logistic_regression.fit(X_train,y_train)
print("Test set accuracy = ", model.score(X_test, y_test))

Test set accuracy =  0.9615384615384616

support_vector = SVC()
support_vector.fit(X_train,y_train)
print("Test set accuracy = ", model.score(X_test, y_test))

Test set accuracy =  0.9615384615384616

我預計分類模型的准確率會有所不同，但事實並非如此，我認為它的准確率太高了。 但我不知道出了什么問題:(如果你能幫忙，我將非常感謝..

Answer 1

從評論中，您需要運行此代碼：

decision_tree = tree.DecisionTreeClassifier()
decision_tree = decision_tree.fit(X_train,y_train)
print("Test set accuracy = ", decision_tree.score(X_test, y_test))


logistic_regression = LogisticRegression()
logistic_regression.fit(X_train,y_train)
print("Test set accuracy = ", logistic_regression.score(X_test, y_test))



support_vector = SVC()
support_vector.fit(X_train,y_train)
print("Test set accuracy = ", support_vector.score(X_test, y_test))

在您的原始代碼中，您始終運行代碼中未定義的model ，這就是您獲得相同分數的原因