Python multiclass.OneVsOneClassifier类代码示例

def gen_svc(train_model):
    '''Given a training model, generates the SVM (and DictVectorizer) for it

    Args: 
        train_model: a training model object. should have 2 attributes:
        feature_lists, a map from POS tag to a dictionary of features
        (the ones used in the ith decision), and action_lists, a map from
        POS tag to the action (Shift, Left, Right) chosen for the ith decision
    Returns: dictionary mapping POS tag to a vectorizer, SVM tuple
    Raises: None
    '''
    models = {}
    for pos_tag in train_model.feature_lists:
        vec = DictVectorizer()
        feature_mat = vec.fit_transform(train_model.feature_lists[pos_tag])
        trained_svc = OneVsOneClassifier(LinearSVC())
        try:
            trained_svc.fit(feature_mat, np.array(train_model.action_lists[pos_tag]))
        except ValueError:
            # occasionally we get the same action for everything with a
            # particular POS, which raises an error. so in that case we just
            # use a custom class that always predicts the same action
            trained_svc = AlwaysPredict(train_model.feature_lists[pos_tag][0])
        models[pos_tag] = (vec, trained_svc)
    return models

def svm_training(train_X,train_Y,kernel):
	if kernel == False:
		clf = OneVsOneClassifier(svm.LinearSVC(random_state=0))
	else:
		clf = OneVsOneClassifier(svm.SVC(kernel='rbf'))
	clf.fit(train_X,train_Y)
	return clf

def svm_classification(genres, features_type):
	training_set_features = tf.read_features_from_files("../../music/training", genres, features_type)
	testing_set_features = tf.read_features_from_files("../../music/testing", genres, features_type)

	X = []
	y = []
	for feature in training_set_features:
		(mean, cov_mat, genre_name) = feature
		X.append(mean.tolist())
		y.append(tf.get_genre_ID(genre_name))

	training_data = np.array(X)
	training_class = np.array(y)

	X = []
	y = []
	for feature in testing_set_features:
		(mean, cov_mat, genre_name) = feature
		X.append(mean.tolist())
		y.append(tf.get_genre_ID(genre_name))

	testing_data = np.array(X)
	testing_class = np.array(y)


	clf = OneVsOneClassifier(SVC(kernel='linear'))
	result_class = np.array(clf.fit(training_data, training_class).predict(testing_data))

	rt.print_accuracy(list(testing_class), list(result_class), genres, features_type, "svm")
	rt.write_accuracy_to_file("../../music/", list(testing_class), list(result_class), genres, features_type, "svm")

def train_classifier(clf,X_train,y_train,X_test,y_test):
	clf = OneVsOneClassifier(clf)
	clf.fit(X_train, y_train)
	train_time = time() - t0
	print("train time: %0.3fs" % train_time)
	t0 = time()
	return clf

def test_ovo_ties():
    # test that ties are broken using the decision function, not defaulting to
    # the smallest label
    X = np.array([[1, 2], [2, 1], [-2, 1], [-2, -1]])
    y = np.array([2, 0, 1, 2])
    multi_clf = OneVsOneClassifier(Perceptron())
    ovo_prediction = multi_clf.fit(X, y).predict(X)

    # recalculate votes to make sure we have a tie
    predictions = np.vstack([clf.predict(X) for clf in multi_clf.estimators_])
    scores = np.vstack([clf.decision_function(X)
                        for clf in multi_clf.estimators_])
    # classifiers are in order 0-1, 0-2, 1-2
    # aggregate votes:
    votes = np.zeros((4, 3))
    votes[np.arange(4), predictions[0]] += 1
    votes[np.arange(4), 2 * predictions[1]] += 1
    votes[np.arange(4), 1 + predictions[2]] += 1
    # for the first point, there is one vote per class
    assert_array_equal(votes[0, :], 1)
    # for the rest, there is no tie and the prediction is the argmax
    assert_array_equal(np.argmax(votes[1:], axis=1), ovo_prediction[1:])
    # for the tie, the prediction is the class with the highest score
    assert_equal(ovo_prediction[0], 0)
    # in the zero-one classifier, the score for 0 is greater than the score for
    # one.
    assert_greater(scores[0][0], scores[0][1])
    # score for one is greater than score for zero
    assert_greater(scores[2, 0] - scores[0, 0], scores[0, 0] + scores[1, 0])
    # score for one is greater than score for two
    assert_greater(scores[2, 0] - scores[0, 0], -scores[1, 0] - scores[2, 0])

def test_ovo_fit_on_list():
    # Test that OneVsOne fitting works with a list of targets and yields the
    # same output as predict from an array
    ovo = OneVsOneClassifier(LinearSVC(random_state=0))
    prediction_from_array = ovo.fit(iris.data, iris.target).predict(iris.data)
    prediction_from_list = ovo.fit(iris.data,
                                   list(iris.target)).predict(iris.data)
    assert_array_equal(prediction_from_array, prediction_from_list)

def test_ovo_string_y():
    # Test that the OvO doesn't mess up the encoding of string labels
    X = np.eye(4)
    y = np.array(['a', 'b', 'c', 'd'])

    ovo = OneVsOneClassifier(LinearSVC())
    ovo.fit(X, y)
    assert_array_equal(y, ovo.predict(X))

def gen_svc(train_model):
    '''Given a training model, generates the SVM (and DictVectorizer) for it'''
    vec = DictVectorizer()
    feature_mat = vec.fit_transform(train_model.feature_list)
    # for some reason just SVC() seems to always suggest "Shift"
    trained_svc = OneVsOneClassifier(LinearSVC())
    trained_svc.fit(feature_mat, np.array(train_model.action_list))
    return vec, trained_svc

def test_ovo_string_y():
    "Test that the OvO doesn't screw the encoding of string labels"
    X = np.eye(4)
    y = np.array(['a', 'b', 'c', 'd'])

    svc = LinearSVC()
    ovo = OneVsOneClassifier(svc)
    ovo.fit(X, y)
    assert_array_equal(y, ovo.predict(X))

 def __init__(self, estimator, n_jobs=-1, n_neighbors=18, radius=1.0,
              algorithm='auto', leaf_size=30, metric='minkowski',
              p=2, threshold=0.2, metric_params=None):
     OneVsOneClassifier.__init__(self, estimator, n_jobs)
     self.nbrs = NearestNeighbors(n_neighbors=n_neighbors, radius=radius, algorithm=algorithm,
                                  leaf_size=leaf_size, metric=metric, p=p,
                                  metric_params=metric_params, n_jobs=n_jobs)
     self.n_neighbors = n_neighbors
     self.threshold = threshold
     self._fit_y = None

def test_ovo_fit_predict():
    # A classifier which implements decision_function.
    ovo = OneVsOneClassifier(LinearSVC())
    pred = ovo.fit(iris.data, iris.target).predict(iris.data)
    assert_equal(len(ovo.estimators_), n_classes * (n_classes - 1) / 2)

    # A classifier which implements predict_proba.
    ovo = OneVsOneClassifier(MultinomialNB())
    pred = ovo.fit(iris.data, iris.target).predict(iris.data)
    assert_equal(len(ovo.estimators_), n_classes * (n_classes - 1) / 2)

def OneVsOne(inputs_train, inputs_valid, target_train, target_valid):
	name = "Multiclass One Vs One"
	clf = OneVsOneClassifier(LinearSVC(random_state=0))
	clf.fit(inputs_train, np.ravel(target_train))
	prediction = clf.predict(inputs_valid)
	correct = np.count_nonzero(np.ravel(target_valid) == prediction)
	total = target_valid.shape[0]
	correctRate = (float(correct)/total)*100

	return name, correctRate

def test_ovo_ties2():
    # test that ties can not only be won by the first two labels
    X = np.array([[1, 2], [2, 1], [-2, 1], [-2, -1]])
    y_ref = np.array([2, 0, 1, 2])

    # cycle through labels so that each label wins once
    for i in range(3):
        y = (y_ref + i) % 3
        multi_clf = OneVsOneClassifier(Perceptron())
        ovo_prediction = multi_clf.fit(X, y).predict(X)
        assert_equal(ovo_prediction[0], i % 3)

    def fit(self, X, y):
        """Fit Gaussian process classification model

        Parameters
        ----------
        X : array-like, shape = (n_samples, n_features)
            Training data

        y : array-like, shape = (n_samples,)
            Target values, must be binary

        Returns
        -------
        self : returns an instance of self.
        """
        X, y = check_X_y(X, y, multi_output=False)

        self.base_estimator_ = _BinaryGaussianProcessClassifierLaplace(
            self.kernel, self.optimizer, self.n_restarts_optimizer,
            self.max_iter_predict, self.warm_start, self.copy_X_train,
            self.random_state)

        self.classes_ = np.unique(y)
        self.n_classes_ = self.classes_.size
        if self.n_classes_ == 1:
            raise ValueError("GaussianProcessClassifier requires 2 or more "
                             "distinct classes; got %d class (only class %s "
                             "is present)"
                             % (self.n_classes_, self.classes_[0]))
        if self.n_classes_ > 2:
            if self.multi_class == "one_vs_rest":
                self.base_estimator_ = \
                    OneVsRestClassifier(self.base_estimator_,
                                        n_jobs=self.n_jobs)
            elif self.multi_class == "one_vs_one":
                self.base_estimator_ = \
                    OneVsOneClassifier(self.base_estimator_,
                                       n_jobs=self.n_jobs)
            else:
                raise ValueError("Unknown multi-class mode %s"
                                 % self.multi_class)

        self.base_estimator_.fit(X, y)

        if self.n_classes_ > 2:
            self.log_marginal_likelihood_value_ = np.mean(
                [estimator.log_marginal_likelihood()
                 for estimator in self.base_estimator_.estimators_])
        else:
            self.log_marginal_likelihood_value_ = \
                self.base_estimator_.log_marginal_likelihood()

        return self

def svm(X,Y):
    X_train = np.array([x for i, x in enumerate(X) if i % 7 != 0], dtype = np.uint8)
    y_train = np.array([z for i, z in enumerate(Y) if i % 7 != 0], dtype = np.uint8)
    X_test  = np.array([x for i, x in enumerate(X) if i % 10 == 0], dtype = np.uint8)
    y_test  = np.array([z for i, z in enumerate(Y) if i % 10 == 0], dtype = np.uint8)

    clf = OneVsOneClassifier(LinearSVC(random_state=0))
    clf.fit(X_train, y_train)
    y_predicted = rf.predict(X_test)

    results = [prediction == truth for prediction, truth in zip(y_predicted, y_test)]
    accuracy = float(results.count(True)) / float(len(results))
    print accuracy