Question

我正在用sklearn库中的决策树来实现Adaboost算法，一旦我预测了结果，我将得到一个错误的解释，谢谢：

错误是： AdaBoostClassifier的algorithm ='SAMME.R'要求弱学习者支持使用predict_proba方法计算类概率。请更改基本估算器或改为设置algorithm ='SAMME'。

数据集来自UCI存储库，您可以从以下链接访问它： https://archive.ics.uci.edu/ml/machine-learning-databases/heart-disease/

代码如下：

from sklearn.model_selection import *
from sklearn.ensemble import AdaBoostClassifier
from sklearn.tree import DecisionTreeClassifier
np.random.seed(1)
selected_features=['sex', 'cp','fbs', 'exang']
X=datascaled[selected_features]
Y=datascaled['num']
# Split the dataset in two equal parts
X_train, X_test, y_train, y_test = train_test_split(
    X, Y, test_size=0.3, random_state=0)
param_grid = {"base_estimator__criterion" : ["gini", "entropy"],
              "base_estimator__splitter" :   ["best", "random"],
              "n_estimators": [1, 2]
             }


DTC = DecisionTreeClassifier(random_state = 11, max_features = "auto", class_weight = "balanced",max_depth = None)

ABC = AdaBoostClassifier(base_estimator = DTC)

# run grid search
model1=GridSearchCV(ABC, param_grid=param_grid, scoring = 'accuracy')
model1.fit(X_train,y_train)
#The best hyper parameters set
print("Best Hyper Parameters:\n",model1.best_params_)
prediction=model1.predict(X_test)
#importing the metrics module
from sklearn import metrics
#evaluation(Accuracy)
print("Accuracy:",metrics.accuracy_score(prediction,y_test))
#evaluation(Confusion Metrix)
print("Confusion Metrix:\n",metrics.confusion_matrix(prediction,y_test))
#after tuning
import pandas as pd
import numpy as np
from sklearn import preprocessing
import matplotlib.pyplot as plt 
plt.rc("font", size=14)
from time import *
from sklearn import metrics
n_folds=10
model=AdaBoostClassifier(random_state = 11,base_estimator= 'entropy', n_estimators= 2)
cv = 10
t0 = time()
y_pred = cross_val_predict(model, X=X, y=Y, n_jobs=-1, cv=cv)

t = time() - t0
print("=" * 52)
print("time cost: {}".format(t))
print()
print("confusion matrix\n", metrics.confusion_matrix(y, y_pred))
print()
print("\t\taccuracy: {}".format(metrics.accuracy_score(y, y_pred)))
print("\t\troc_auc_score: {}".format(metrics.roc_auc_score(y, y_pred)))
print("\t\tcohen_kappa_score: {}".format(metrics.cohen_kappa_score(y, y_pred)))
print()
print("\t\tclassification report")
print("-" * 52)
print(metrics.classification_report(y, y_pred))

Adaboosting合奏学习

0 个答案: