p206_majority_vote_classifier.py

'''majority_voting_classifier.py

Majority Voting is the combination of the predictions of multiple 
classifiers by majority voting.

This improves the accuracy of the prediction.

Implement a Majority Voter and apply it to several classifiers

Plot the Receiver Operating Curves of the individual classifiers and
the overall majority voting.

Finally, get the parameters so we can see how to access the classifier's
    parameters and tune the classifiers by a GridSearch

Created on Jul 9, 2016

from Python Machine Learning by Sebastian Raschka under the following license

The MIT License (MIT)

Copyright (c) 2015, 2016 SEBASTIAN RASCHKA (mail@sebastianraschka.com)

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

@author: richard lyman
'''
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 numpy as np       
import ocr_utils 
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier 
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import roc_curve
from sklearn.metrics import auc
import matplotlib.pyplot as plt
from sklearn.model_selection import GridSearchCV

class MajorityVoteClassifier(BaseEstimator, 
                             ClassifierMixin):
    """ A majority vote ensemble classifier

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

    vote : str, {'classlabel', 'probability'} (default='label')
      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_samples, n_features]
            Matrix of training samples.

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

        Returns
        -------
        self : object

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

        if self.weights and len(self.weights) != len(self.classifiers):
            raise ValueError('Number of classifiers and weights must be equal'
                             '; got %d weights, %d classifiers'
                             % (len(self.weights), len(self.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_samples, n_features]
            Matrix of training samples.

        Returns
        ----------
        maj_vote : array-like, shape = [n_samples]
            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_samples, n_features]
            Training vectors, where n_samples is the number of samples and
            n_features is the number of features.

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

        """
        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(MajorityVoteClassifier, self).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['%s__%s' % (name, key)] = value
            return out

charsToTrain=(48,51)
nChars = 500
y, X, y_test, X_test, labels  = ocr_utils.load_E13B(chars_to_train = charsToTrain , columns=(9,17), nChars=nChars)

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)
       


clf1 = LogisticRegression(penalty='l2', 
                          C=0.001, 
                          random_state=0, solver='lbfgs')

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]])
kys = pipe1.get_params()

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("ROC AUC: %0.2f (+/- %0.2f) [%s]" 
               % (scores.mean(), scores.std(), label))
    
mv_clf = MajorityVoteClassifier(
classifiers=[pipe1, clf2, pipe3])
clf_labels += ['Majority Voting']
all_clf = [pipe1, clf2, pipe3, mv_clf]
print()
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("Accuracy: %0.2f (+/- %0.2f) [%s]"% (scores.mean(), scores.std(), label))    
    


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='%s (auc = %0.2f)' % (label, roc_auc))
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()
title='Majority Vote Receiver Operation Curve'
plt.title(title)
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
ocr_utils.show_figures(plt,title)   

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

from itertools import product

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='^',label=labels[0],
                                  s=50)
    
    axarr[idx[0], idx[1]].scatter(X_train_std[y_train==1, 0], 
                                  X_train_std[y_train==1, 1], 
                                  c='red', 
                                  marker='o',label=labels[1],
                                  s=50) 
    axarr[idx[0], idx[1]].set_title(tt)
    axarr[idx[0], idx[1]].set_ylabel(labels[0], fontsize=12)
    axarr[idx[0], idx[1]].set_xlabel(labels[1], fontsize=12)    

ocr_utils.show_figures(plt, title)

import pprint
print()
pprint.pprint(mv_clf.get_params())
print()
  


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)

params=grid.cv_results_['params']
mean_scores=grid.cv_results_['mean_test_score']
scores =    grid.cv_results_['std_test_score']

for i in range(len(params)):
    print("%0.6f+/-%0.6f %r"
            % (mean_scores[i], scores[i] / 2, sorted(params[i].items())))
print('\nBest parameters: %s' % sorted(grid.best_params_.items()))
print('Best Accuracy: %.6f' % grid.best_score_)

print ('\n########################### No Errors ####################################')