Adaboost

1. AdaBoost

Boosting refers to an ensemble method in which many predictors are trained and each predictor learns from the errors of its predecessor.

2. Boosting

More formally, in boosting many weak learners are combined to form a strong learner. A weak learner is a model doing slightly better than random guessing. For example, a decision tree with a maximum-depth of one, known as a decision-stump, is a weak learner.

3. Boosting

In boosting, an ensemble of predictors are trained sequentially and each predictor tries to correct the errors made by its predecessor. The two boosting methods you'll explore in this course are AdaBoost and Gradient Boosting.

4. Adaboost

AdaBoost stands for Adaptive Boosting. In AdaBoost, each predictor pays more attention to the instances wrongly predicted by its predecessor by constantly changing the weights of training instances. Furthermore, each predictor is assigned a coefficient alpha that weighs its contribution in the ensemble's final prediction. Alpha depends on the predictor's training error.

5. AdaBoost: Training

As shown in the diagram, there are N predictors in total. First, predictor1 is trained on the initial dataset (X,y), and the training error for predictor1 is determined. This error can then be used to determine alpha1 which is predictor1's coefficient. Alpha1 is then used to determine the weights W(2) of the training instances for predictor2. Notice how the incorrectly predicted instances shown in green acquire higher weights. When the weighted instances are used to train predictor2, this predictor is forced to pay more attention to the incorrectly predicted instances. This process is repeated sequentially, until the N predictors forming the ensemble are trained.

6. Learning Rate

An important parameter used in training is the learning rate, eta. Eta is a number between 0 and 1; it is used to shrink the coefficient alpha of a trained predictor. It's important to note that there's a trade-off between eta and the number of estimators. A smaller value of eta should be compensated by a greater number of estimators.

7. AdaBoost: Prediction

Once all the predictors in the ensemble are trained, the label of a new instance can be predicted depending on the nature of the problem. For classification, each predictor predicts the label of the new instance and the ensemble's prediction is obtained by weighted majority voting. For regression, the same procedure is applied and the ensemble's prediction is obtained by performing a weighted average. It's important to note that individual predictors need not to be CARTs. However CARTs are used most of the time in boosting because of their high variance.

8. AdaBoost Classification in sklearn (Breast Cancer dataset)

Alright, let's fit an AdaBoostClassifier to the breast cancer dataset and evaluate its ROC-AUC score. Note that the dataset is already loaded. After importing AdaBoostClassifier, DecisionTreeClassifier, roc_auc_score, and train_test_split, split the data into 70%-train and 30%-test as shown here.

9. AdaBoost Classification in sklearn (Breast Cancer dataset)

Now instantiate a DecisionTreeClassifier with the parameter max_depth set to 1. After that, instantiate an AdaBoostClassifier called adb_clf consisting of 100 decision-stumps. This can be done by setting the parameters base_estimator to dt and n_estimators to 100. Then, fit adb_clf to the training set and predict the probability of obtaining the positive class in the test set as shown here. This enables you to evaluate the ROC-AUC score of adb_clf by calling the function roc_auc_score and passing the parameters y_test and y_pred_proba.

10. AdaBoost Classification in sklearn (Breast Cancer dataset)

Finally, you can print the result which shows that the AdaBoostClassifier achieves a ROC-AUC score of about 0-dot-99.

11. Let's practice!

Now it's your turn.

This exercise is part of the course

Machine Learning with Tree-Based Models in Python

IntermediateSkill Level

4.9+

Start Course for Free

Classification and Regression Trees (CART) are a set of supervised learning models used for problems involving classification and regression. In this chapter, you'll be introduced to the CART algorithm.

Exercise 1: Decision tree for classification Exercise 2: Train your first classification tree Exercise 3: Evaluate the classification tree Exercise 4: Logistic regression vs classification tree Exercise 5: Classification tree Learning Exercise 6: Growing a classification tree Exercise 7: Using entropy as a criterion Exercise 8: Entropy vs Gini index Exercise 9: Decision tree for regression Exercise 10: Train your first regression tree Exercise 11: Evaluate the regression tree Exercise 12: Linear regression vs regression tree

The bias-variance tradeoff is one of the fundamental concepts in supervised machine learning. In this chapter, you'll understand how to diagnose the problems of overfitting and underfitting. You'll also be introduced to the concept of ensembling where the predictions of several models are aggregated to produce predictions that are more robust.

Exercise 1: Generalization Error Exercise 2: Complexity, bias and variance Exercise 3: Overfitting and underfitting Exercise 4: Diagnose bias and variance problems Exercise 5: Instantiate the model Exercise 6: Evaluate the 10-fold CV error Exercise 7: Evaluate the training error Exercise 8: High bias or high variance?Exercise 9: Ensemble Learning Exercise 10: Define the ensemble Exercise 11: Evaluate individual classifiers Exercise 12: Better performance with a Voting Classifier

Bagging is an ensemble method involving training the same algorithm many times using different subsets sampled from the training data. In this chapter, you'll understand how bagging can be used to create a tree ensemble. You'll also learn how the random forests algorithm can lead to further ensemble diversity through randomization at the level of each split in the trees forming the ensemble.

Exercise 1: Bagging Exercise 2: Define the bagging classifier Exercise 3: Evaluate Bagging performance Exercise 4: Out of Bag Evaluation Exercise 5: Prepare the ground Exercise 6: OOB Score vs Test Set Score Exercise 7: Random Forests (RF)Exercise 8: Train an RF regressor Exercise 9: Evaluate the RF regressor Exercise 10: Visualizing features importances

Boosting refers to an ensemble method in which several models are trained sequentially with each model learning from the errors of its predecessors. In this chapter, you'll be introduced to the two boosting methods of AdaBoost and Gradient Boosting.

Exercise 1: Adaboost

Current Exercise

Exercise 2: Define the AdaBoost classifier Exercise 3: Train the AdaBoost classifier Exercise 4: Evaluate the AdaBoost classifier Exercise 5: Gradient Boosting (GB)Exercise 6: Define the GB regressor Exercise 7: Train the GB regressor Exercise 8: Evaluate the GB regressor Exercise 9: Stochastic Gradient Boosting (SGB)Exercise 10: Regression with SGB Exercise 11: Train the SGB regressor Exercise 12: Evaluate the SGB regressor

The hyperparameters of a machine learning model are parameters that are not learned from data. They should be set prior to fitting the model to the training set. In this chapter, you'll learn how to tune the hyperparameters of a tree-based model using grid search cross validation.

Exercise 1: Tuning a CART's Hyperparameters Exercise 2: Tree hyperparameters Exercise 3: Set the tree's hyperparameter grid Exercise 4: Search for the optimal tree Exercise 5: Evaluate the optimal tree Exercise 6: Tuning a RF's Hyperparameters Exercise 7: Random forests hyperparameters Exercise 8: Set the hyperparameter grid of RF Exercise 9: Search for the optimal forest Exercise 10: Evaluate the optimal forest Exercise 11: Congratulations!