python AI-Machine Learning-Program3

Posted 2021-05-09

from sklearn.svm import SVC
import numpy as np
from sklearn.metrics import accuracy_score
from sklearn.svm import SVC
from sklearn.naive_bayes import BernoulliNB
from sklearn.naive_bayes import GaussianNB
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from matplotlib.colors import ListedColormap
import matplotlib.pyplot as plt
from sklearn.cross_validation import cross_val_score
from sklearn.linear_model import LogisticRegression


from sklearn.base import BaseEstimator
from sklearn.base import ClassifierMixin
from sklearn.preprocessing import LabelEncoder
from sklearn.externals import six
from sklearn.base import clone
from sklearn.pipeline import _name_estimators
from sklearn.pipeline import Pipeline
import operator


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)"
                             % self.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 six.iteritems(self.named_classifiers):
                for key, value in six.iteritems(step.get_params(deep=True)):
                    out['%s__%s' % (name, key)] = value
            return out


# In[7]:

data = np.loadtxt('TraData.csv', delimiter=',')

X = data[:, :-1]
y = data[:, -1]

from sklearn.cross_validation import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)

from sklearn.preprocessing import StandardScaler

sc = StandardScaler()

sc.fit(X_train)

X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)

clf1 = LogisticRegression(penalty='l2', C=100, random_state=0)
clf2 = DecisionTreeClassifier(criterion='entropy', max_depth=7, random_state=0)
clf3 = KNeighborsClassifier(n_neighbors=3, p=1, metric='minkowski')
clf4 = SVC(kernel='linear', C=2.0, random_state=0)
clf5 = BernoulliNB()
clf6 = RandomForestClassifier(criterion='entropy', n_estimators=299, random_state=1, n_jobs=2)

clf_labels = ['Logistic Regression', 'Decision Tree', 'KNN', 'Linear SVM', 'Naive Bayes', 'Random Forest']

print('[*] 10-fold cross validation\n')

pipe1 = Pipeline([['sc', StandardScaler()], ['clf', clf1]])
pipe3 = Pipeline([['sc', StandardScaler()], ['clf', clf3]])
pipe4 = Pipeline([['sc', StandardScaler()], ['clf', clf4]])
pipe5 = Pipeline([['sc', StandardScaler()], ['clf', clf5]])

for clf, label in zip([pipe1, clf2, pipe3, pipe4, pipe5, clf6], 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))