ch07.py

# coding: utf-8


import sys
from python_environment_check import check_packages
from scipy.special import comb
import math
import numpy as np
import matplotlib.pyplot as plt
from sklearn.base import BaseEstimator
from sklearn.base import ClassifierMixin
from sklearn.preprocessing import LabelEncoder
from sklearn.base import clone
from sklearn.pipeline import _name_estimators
import operator
from sklearn import datasets
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier 
from sklearn.pipeline import Pipeline
from sklearn.model_selection import cross_val_score
from sklearn.metrics import roc_curve
from sklearn.metrics import auc
from itertools import product
from sklearn.model_selection import GridSearchCV
import pandas as pd
from sklearn.ensemble import BaggingClassifier
from sklearn.metrics import accuracy_score
from sklearn.ensemble import AdaBoostClassifier
import xgboost as xgb

# # Machine Learning with PyTorch and Scikit-Learn  
# # -- Code Examples

# ## Package version checks

# Add folder to path in order to load from the check_packages.py script:



sys.path.insert(0, '..')


# Check recommended package versions:





d = {
    'numpy': '1.21.2',
    'scipy': '1.7.0',
    'matplotlib': '3.4.3',
    'sklearn': '1.0',
    'pandas': '1.3.2',
    'xgboost': '1.5.0',
}
check_packages(d)


# # Chapter 7 - Combining Different Models for Ensemble Learning


# ### Overview

# - [Learning with ensembles](#Learning-with-ensembles)
# - [Combining classifiers via majority vote](#Combining-classifiers-via-majority-vote)
#     - [Implementing a simple majority vote classifier](#Implementing-a-simple-majority-vote-classifier)
#     - [Using the majority voting principle to make predictions](#Using-the-majority-voting-principle-to-make-predictions)
#     - [Evaluating and tuning the ensemble classifier](#Evaluating-and-tuning-the-ensemble-classifier)
# - [Bagging – building an ensemble of classifiers from bootstrap samples](#Bagging----Building-an-ensemble-of-classifiers-from-bootstrap-samples)
#     - [Bagging in a nutshell](#Bagging-in-a-nutshell)
#     - [Applying bagging to classify examples in the Wine dataset](#Applying-bagging-to-classify-examples-in-the-Wine-dataset)
# - [Leveraging weak learners via adaptive boosting](#Leveraging-weak-learners-via-adaptive-boosting)
#     - [How boosting works](#How-boosting-works)
#     - [Applying AdaBoost using scikit-learn](#Applying-AdaBoost-using-scikit-learn)
# - [Gradient boosting -- training an ensemble based on loss gradients](#Gradient-boosting----training-an-ensemble-based-on-loss-gradients)
#   - [Comparing AdaBoost with gradient boosting](#Comparing-AdaBoost-with-gradient-boosting)
#   - [Outlining the general gradient boosting algorithm](#Outlining-the-general-gradient-boosting-algorithm)
#   - [Explaining the gradient boosting algorithm for classification](#Explaining-the-gradient-boosting-algorithm-for-classification)
#   - [Illustrating gradient boosting for classification](#Illustrating-gradient-boosting-for-classification)
#   - [Using XGBoost](#Using-XGBoost)
# - [Summary](#Summary)






# # Learning with ensembles













def ensemble_error(n_classifier, error):
    k_start = int(math.ceil(n_classifier / 2.))
    probs = [comb(n_classifier, k) * error**k * (1-error)**(n_classifier - k)
             for k in range(k_start, n_classifier + 1)]
    return sum(probs)




ensemble_error(n_classifier=11, error=0.25)






error_range = np.arange(0.0, 1.01, 0.01)
ens_errors = [ensemble_error(n_classifier=11, error=error)
              for error in error_range]






plt.plot(error_range, 
         ens_errors, 
         label='Ensemble error', 
         linewidth=2)

plt.plot(error_range, 
         error_range, 
         linestyle='--',
         label='Base error',
         linewidth=2)

plt.xlabel('Base error')
plt.ylabel('Base/Ensemble error')
plt.legend(loc='upper left')
plt.grid(alpha=0.5)
#plt.savefig('figures/07_03.png', dpi=300)
plt.show()



# # Combining classifiers via majority vote

# ## Implementing a simple majority vote classifier 




np.argmax(np.bincount([0, 0, 1], 
                      weights=[0.2, 0.2, 0.6]))




ex = np.array([[0.9, 0.1],
               [0.8, 0.2],
               [0.4, 0.6]])

p = np.average(ex, 
               axis=0, 
               weights=[0.2, 0.2, 0.6])
p




np.argmax(p)





# Scikit-learn 0.16 and newer requires reversing the parent classes
# See https://github.com/rasbt/machine-learning-book/discussions/205 for more details
import sklearn
base_classes = (ClassifierMixin, BaseEstimator) if sklearn.__version__ >= "0.16" else (BaseEstimator, ClassifierMixin)

# class MajorityVoteClassifier(BaseEstimator, 
#                             ClassifierMixin):

class MajorityVoteClassifier(*base_classes):
    """ A majority vote ensemble classifier

    Parameters
    ----------
    classifiers : array-like, shape = [n_classifiers]
      Different classifiers for the ensemble

    vote : str, {'classlabel', 'probability'} (default='classlabel')
      If 'classlabel' the prediction is based on the argmax of
        class labels. Else if 'probability', the argmax of
        the sum of probabilities is used to predict the class label
        (recommended for calibrated classifiers).

    weights : array-like, shape = [n_classifiers], optional (default=None)
      If a list of `int` or `float` values are provided, the classifiers
      are weighted by importance; Uses uniform weights if `weights=None`.

    """
    def __init__(self, classifiers, vote='classlabel', weights=None):

        self.classifiers = classifiers
        self.named_classifiers = {key: value for key, value
                                  in _name_estimators(classifiers)}
        self.vote = vote
        self.weights = weights

    def fit(self, X, y):
        """ Fit classifiers.

        Parameters
        ----------
        X : {array-like, sparse matrix}, shape = [n_examples, n_features]
            Matrix of training examples.

        y : array-like, shape = [n_examples]
            Vector of target class labels.

        Returns
        -------
        self : object

        """
        if self.vote not in ('probability', 'classlabel'):
            raise ValueError(f"vote must be 'probability' or 'classlabel'"
                             f"; got (vote={self.vote})")

        if self.weights and len(self.weights) != len(self.classifiers):
            raise ValueError(f'Number of classifiers and weights must be equal'
                             f'; got {len(self.weights)} weights,'
                             f' {len(self.classifiers)} classifiers')

        # Use LabelEncoder to ensure class labels start with 0, which
        # is important for np.argmax call in self.predict
        self.lablenc_ = LabelEncoder()
        self.lablenc_.fit(y)
        self.classes_ = self.lablenc_.classes_
        self.classifiers_ = []
        for clf in self.classifiers:
            fitted_clf = clone(clf).fit(X, self.lablenc_.transform(y))
            self.classifiers_.append(fitted_clf)
        return self

    def predict(self, X):
        """ Predict class labels for X.

        Parameters
        ----------
        X : {array-like, sparse matrix}, shape = [n_examples, n_features]
            Matrix of training examples.

        Returns
        ----------
        maj_vote : array-like, shape = [n_examples]
            Predicted class labels.
            
        """
        if self.vote == 'probability':
            maj_vote = np.argmax(self.predict_proba(X), axis=1)
        else:  # 'classlabel' vote

            #  Collect results from clf.predict calls
            predictions = np.asarray([clf.predict(X)
                                      for clf in self.classifiers_]).T

            maj_vote = np.apply_along_axis(
                                      lambda x:
                                      np.argmax(np.bincount(x,
                                                weights=self.weights)),
                                      axis=1,
                                      arr=predictions)
        maj_vote = self.lablenc_.inverse_transform(maj_vote)
        return maj_vote

    def predict_proba(self, X):
        """ Predict class probabilities for X.

        Parameters
        ----------
        X : {array-like, sparse matrix}, shape = [n_examples, n_features]
            Training vectors, where n_examples is the number of examples and
            n_features is the number of features.

        Returns
        ----------
        avg_proba : array-like, shape = [n_examples, n_classes]
            Weighted average probability for each class per example.

        """
        probas = np.asarray([clf.predict_proba(X)
                             for clf in self.classifiers_])
        avg_proba = np.average(probas, axis=0, weights=self.weights)
        return avg_proba

    def get_params(self, deep=True):
        """ Get classifier parameter names for GridSearch"""
        if not deep:
            return super().get_params(deep=False)
        else:
            out = self.named_classifiers.copy()
            for name, step in self.named_classifiers.items():
                for key, value in step.get_params(deep=True).items():
                    out[f'{name}__{key}'] = value
            return out



# ## Using the majority voting principle to make predictions





iris = datasets.load_iris()
X, y = iris.data[50:, [1, 2]], iris.target[50:]
le = LabelEncoder()
y = le.fit_transform(y)

X_train, X_test, y_train, y_test =       train_test_split(X, y, 
                        test_size=0.5, 
                        random_state=1,
                        stratify=y)






clf1 = LogisticRegression(penalty='l2', 
                          C=0.001,
                          solver='lbfgs',
                          random_state=1)

clf2 = DecisionTreeClassifier(max_depth=1,
                              criterion='entropy',
                              random_state=0)

clf3 = KNeighborsClassifier(n_neighbors=1,
                            p=2,
                            metric='minkowski')

pipe1 = Pipeline([['sc', StandardScaler()],
                  ['clf', clf1]])
pipe3 = Pipeline([['sc', StandardScaler()],
                  ['clf', clf3]])

clf_labels = ['Logistic regression', 'Decision tree', 'KNN']

print('10-fold cross validation:\n')
for clf, label in zip([pipe1, clf2, pipe3], clf_labels):
    scores = cross_val_score(estimator=clf,
                             X=X_train,
                             y=y_train,
                             cv=10,
                             scoring='roc_auc')
    print(f'ROC AUC: {scores.mean():.2f} '
          f'(+/- {scores.std():.2f}) [{label}]')




# Majority Rule (hard) Voting

mv_clf = MajorityVoteClassifier(classifiers=[pipe1, clf2, pipe3])

clf_labels += ['Majority voting']
all_clf = [pipe1, clf2, pipe3, mv_clf]

for clf, label in zip(all_clf, clf_labels):
    scores = cross_val_score(estimator=clf,
                             X=X_train,
                             y=y_train,
                             cv=10,
                             scoring='roc_auc')
    print(f'ROC AUC: {scores.mean():.2f} '
          f'(+/- {scores.std():.2f}) [{label}]')



# # Evaluating and tuning the ensemble classifier





colors = ['black', 'orange', 'blue', 'green']
linestyles = [':', '--', '-.', '-']
for clf, label, clr, ls         in zip(all_clf,
               clf_labels, colors, linestyles):

    # assuming the label of the positive class is 1
    y_pred = clf.fit(X_train,
                     y_train).predict_proba(X_test)[:, 1]
    fpr, tpr, thresholds = roc_curve(y_true=y_test,
                                     y_score=y_pred)
    roc_auc = auc(x=fpr, y=tpr)
    plt.plot(fpr, tpr,
             color=clr,
             linestyle=ls,
             label=f'{label} (auc = {roc_auc:.2f})')

plt.legend(loc='lower right')
plt.plot([0, 1], [0, 1],
         linestyle='--',
         color='gray',
         linewidth=2)

plt.xlim([-0.1, 1.1])
plt.ylim([-0.1, 1.1])
plt.grid(alpha=0.5)
plt.xlabel('False positive rate (FPR)')
plt.ylabel('True positive rate (TPR)')


#plt.savefig('figures/07_04', dpi=300)
plt.show()




sc = StandardScaler()
X_train_std = sc.fit_transform(X_train)






all_clf = [pipe1, clf2, pipe3, mv_clf]

x_min = X_train_std[:, 0].min() - 1
x_max = X_train_std[:, 0].max() + 1
y_min = X_train_std[:, 1].min() - 1
y_max = X_train_std[:, 1].max() + 1

xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.1),
                     np.arange(y_min, y_max, 0.1))

f, axarr = plt.subplots(nrows=2, ncols=2, 
                        sharex='col', 
                        sharey='row', 
                        figsize=(7, 5))

for idx, clf, tt in zip(product([0, 1], [0, 1]),
                        all_clf, clf_labels):
    clf.fit(X_train_std, y_train)
    
    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
    Z = Z.reshape(xx.shape)

    axarr[idx[0], idx[1]].contourf(xx, yy, Z, alpha=0.3)
    
    axarr[idx[0], idx[1]].scatter(X_train_std[y_train==0, 0], 
                                  X_train_std[y_train==0, 1], 
                                  c='blue', 
                                  marker='^',
                                  s=50)
    
    axarr[idx[0], idx[1]].scatter(X_train_std[y_train==1, 0], 
                                  X_train_std[y_train==1, 1], 
                                  c='green', 
                                  marker='o',
                                  s=50)
    
    axarr[idx[0], idx[1]].set_title(tt)

plt.text(-3.5, -5., 
         s='Sepal width [standardized]', 
         ha='center', va='center', fontsize=12)
plt.text(-12.5, 4.5, 
         s='Petal length [standardized]', 
         ha='center', va='center', 
         fontsize=12, rotation=90)

#plt.savefig('figures/07_05', dpi=300)
plt.show()




mv_clf.get_params()






params = {'decisiontreeclassifier__max_depth': [1, 2],
          'pipeline-1__clf__C': [0.001, 0.1, 100.0]}

grid = GridSearchCV(estimator=mv_clf,
                    param_grid=params,
                    cv=10,
                    scoring='roc_auc')
grid.fit(X_train, y_train)

for r, _ in enumerate(grid.cv_results_['mean_test_score']):
    mean_score = grid.cv_results_['mean_test_score'][r]
    std_dev = grid.cv_results_['std_test_score'][r]
    params = grid.cv_results_['params'][r]
    print(f'{mean_score:.3f} +/- {std_dev:.2f} {params}')




print(f'Best parameters: {grid.best_params_}')
print(f'ROC AUC: {grid.best_score_:.2f}')


# **Note**  
# By default, the default setting for `refit` in `GridSearchCV` is `True` (i.e., `GridSeachCV(..., refit=True)`), which means that we can use the fitted `GridSearchCV` estimator to make predictions via the `predict` method, for example:
# 
#     grid = GridSearchCV(estimator=mv_clf, 
#                         param_grid=params, 
#                         cv=10, 
#                         scoring='roc_auc')
#     grid.fit(X_train, y_train)
#     y_pred = grid.predict(X_test)
# 
# In addition, the "best" estimator can directly be accessed via the `best_estimator_` attribute.



grid.best_estimator_.classifiers




mv_clf = grid.best_estimator_




mv_clf.set_params(**grid.best_estimator_.get_params())




mv_clf



# # Bagging -- Building an ensemble of classifiers from bootstrap samples





# ## Bagging in a nutshell





# ## Applying bagging to classify examples in the Wine dataset





df_wine = pd.read_csv('https://archive.ics.uci.edu/ml/'
                      'machine-learning-databases/wine/wine.data',
                      header=None)

df_wine.columns = ['Class label', 'Alcohol', 'Malic acid', 'Ash',
                   'Alcalinity of ash', 'Magnesium', 'Total phenols',
                   'Flavanoids', 'Nonflavanoid phenols', 'Proanthocyanins',
                   'Color intensity', 'Hue', 'OD280/OD315 of diluted wines',
                   'Proline']

# if the Wine dataset is temporarily unavailable from the
# UCI machine learning repository, un-comment the following line
# of code to load the dataset from a local path:

# df_wine = pd.read_csv('wine.data', header=None)

# drop 1 class
df_wine = df_wine[df_wine['Class label'] != 1]

y = df_wine['Class label'].values
X = df_wine[['Alcohol', 'OD280/OD315 of diluted wines']].values






le = LabelEncoder()
y = le.fit_transform(y)

X_train, X_test, y_train, y_test =            train_test_split(X, y, 
                             test_size=0.2, 
                             random_state=1,
                             stratify=y)





tree = DecisionTreeClassifier(criterion='entropy', 
                              max_depth=None,
                              random_state=1)

bag = BaggingClassifier(base_estimator=tree,
                        n_estimators=500, 
                        max_samples=1.0, 
                        max_features=1.0, 
                        bootstrap=True, 
                        bootstrap_features=False, 
                        n_jobs=1, 
                        random_state=1)






tree = tree.fit(X_train, y_train)
y_train_pred = tree.predict(X_train)
y_test_pred = tree.predict(X_test)

tree_train = accuracy_score(y_train, y_train_pred)
tree_test = accuracy_score(y_test, y_test_pred)
print(f'Decision tree train/test accuracies '
      f'{tree_train:.3f}/{tree_test:.3f}')

bag = bag.fit(X_train, y_train)
y_train_pred = bag.predict(X_train)
y_test_pred = bag.predict(X_test)

bag_train = accuracy_score(y_train, y_train_pred) 
bag_test = accuracy_score(y_test, y_test_pred) 
print(f'Bagging train/test accuracies '
      f'{bag_train:.3f}/{bag_test:.3f}')






x_min = X_train[:, 0].min() - 1
x_max = X_train[:, 0].max() + 1
y_min = X_train[:, 1].min() - 1
y_max = X_train[:, 1].max() + 1

xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.1),
                     np.arange(y_min, y_max, 0.1))

f, axarr = plt.subplots(nrows=1, ncols=2, 
                        sharex='col', 
                        sharey='row', 
                        figsize=(8, 3))


for idx, clf, tt in zip([0, 1],
                        [tree, bag],
                        ['Decision tree', 'Bagging']):
    clf.fit(X_train, y_train)

    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
    Z = Z.reshape(xx.shape)

    axarr[idx].contourf(xx, yy, Z, alpha=0.3)
    axarr[idx].scatter(X_train[y_train == 0, 0],
                       X_train[y_train == 0, 1],
                       c='blue', marker='^')

    axarr[idx].scatter(X_train[y_train == 1, 0],
                       X_train[y_train == 1, 1],
                       c='green', marker='o')

    axarr[idx].set_title(tt)

axarr[0].set_ylabel('OD280/OD315 of diluted wines', fontsize=12)

plt.tight_layout()
plt.text(0, -0.2,
         s='Alcohol',
         ha='center',
         va='center',
         fontsize=12,
         transform=axarr[1].transAxes)

#plt.savefig('figures/07_08.png', dpi=300, bbox_inches='tight')
plt.show()



# # Leveraging weak learners via adaptive boosting

# ## How boosting works











y = np.array([1, 1, 1, -1, -1, -1,  1,  1,  1, -1])
yhat = np.array([1, 1, 1, -1, -1, -1, -1, -1, -1, -1])
correct = (y == yhat)
weights = np.full(10, 0.1)
print(weights)

epsilon = np.mean(~correct)
print(epsilon)




alpha_j = 0.5 * np.log((1-epsilon) / epsilon)
print(alpha_j)




update_if_correct = 0.1 * np.exp(-alpha_j * 1 * 1)
print(update_if_correct)




update_if_wrong_1 = 0.1 * np.exp(-alpha_j * 1 * -1)
print(update_if_wrong_1)




update_if_wrong_2 = 0.1 * np.exp(-alpha_j * -1 * 1)
print(update_if_wrong_2)




weights = np.where(correct == 1, update_if_correct, update_if_wrong_1)
print(weights)




normalized_weights = weights / np.sum(weights)
print(normalized_weights)


# ## Applying AdaBoost using scikit-learn





tree = DecisionTreeClassifier(criterion='entropy', 
                              max_depth=1,
                              random_state=1)

ada = AdaBoostClassifier(base_estimator=tree,
                         n_estimators=500, 
                         learning_rate=0.1,
                         random_state=1)




tree = tree.fit(X_train, y_train)
y_train_pred = tree.predict(X_train)
y_test_pred = tree.predict(X_test)

tree_train = accuracy_score(y_train, y_train_pred)
tree_test = accuracy_score(y_test, y_test_pred)
print(f'Decision tree train/test accuracies '
      f'{tree_train:.3f}/{tree_test:.3f}')

ada = ada.fit(X_train, y_train)
y_train_pred = ada.predict(X_train)
y_test_pred = ada.predict(X_test)

ada_train = accuracy_score(y_train, y_train_pred) 
ada_test = accuracy_score(y_test, y_test_pred) 
print(f'AdaBoost train/test accuracies '
      f'{ada_train:.3f}/{ada_test:.3f}')




x_min, x_max = X_train[:, 0].min() - 1, X_train[:, 0].max() + 1
y_min, y_max = X_train[:, 1].min() - 1, X_train[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.1),
                     np.arange(y_min, y_max, 0.1))

f, axarr = plt.subplots(1, 2, sharex='col', sharey='row', figsize=(8, 3))


for idx, clf, tt in zip([0, 1],
                        [tree, ada],
                        ['Decision tree', 'AdaBoost']):
    clf.fit(X_train, y_train)

    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
    Z = Z.reshape(xx.shape)

    axarr[idx].contourf(xx, yy, Z, alpha=0.3)
    axarr[idx].scatter(X_train[y_train == 0, 0],
                       X_train[y_train == 0, 1],
                       c='blue', marker='^')
    axarr[idx].scatter(X_train[y_train == 1, 0],
                       X_train[y_train == 1, 1],
                       c='green', marker='o')
    axarr[idx].set_title(tt)

axarr[0].set_ylabel('OD280/OD315 of diluted wines', fontsize=12)

plt.tight_layout()
plt.text(0, -0.2,
         s='Alcohol',
         ha='center',
         va='center',
         fontsize=12,
         transform=axarr[1].transAxes)

# plt.savefig('figures/07_11.png', dpi=300, bbox_inches='tight')
plt.show()


# # Gradient boosting -- training an ensemble based on loss gradients

# ## Comparing AdaBoost with gradient boosting

# ## Outlining the general gradient boosting algorithm

# ## Explaining the gradient boosting algorithm for classification

# ## Illustrating gradient boosting for classification





















# ## Using XGboost 







xgb.__version__




model = xgb.XGBClassifier(n_estimators=1000, learning_rate=0.01, max_depth=4, random_state=1, use_label_encoder=False)


gbm = model.fit(X_train, y_train)

y_train_pred = gbm.predict(X_train)
y_test_pred = gbm.predict(X_test)

gbm_train = accuracy_score(y_train, y_train_pred) 
gbm_test = accuracy_score(y_test, y_test_pred) 
print(f'XGboost train/test accuracies '
      f'{gbm_train:.3f}/{gbm_test:.3f}')



# # Summary

# ...

# ---
# 
# Readers may ignore the next cell.