python类GaussianNB()的实例源码

def sub_NB(train_x, train_y, test_x, test_y):
    """ ???????? """
    classifier = GaussianNB()
    classifier.fit(train_x, train_y)
    pred = classifier.predict_proba(test_x)
    predict_pro = []
    for pro in pred:
        predict_pro.append(pro[1])
    return np.array(predict_pro)

def _init_model(self):
        return GaussianNB()

def generate_base_classification():
    from sklearn.svm import LinearSVC, NuSVC, SVC
    from sklearn.tree import ExtraTreeClassifier, DecisionTreeClassifier
    from sklearn.ensemble import RandomForestClassifier
    from sklearn.gaussian_process import GaussianProcessClassifier
    from sklearn.linear_model import LogisticRegression, PassiveAggressiveClassifier, RidgeClassifier, SGDClassifier
    from sklearn.neighbors import KNeighborsClassifier
    from sklearn.naive_bayes import MultinomialNB, GaussianNB, BernoulliNB
    models = [
        #(LinearSVC, params('C', 'loss')),
#         (NuSVC, params('nu', 'kernel', 'degree')),
        #(SVC, params('C', 'kernel')),
        #(ExtraTreeClassifier, params('criterion', 'min_samples_split', 'min_samples_leaf')),
        (DecisionTreeClassifier, params('criterion', 'min_samples_split', 'min_samples_leaf')),
        (RandomForestClassifier, params('criterion', 'min_samples_split', 'min_samples_leaf', 'n_estimators')),
        #(GaussianProcessClassifier, None),
        (LogisticRegression, params('C', 'penalty')),
        #(PassiveAggressiveClassifier, params('C', 'loss')),
        #(RidgeClassifier, params('alpha')),
        # we do in-place modification of what the method params return in order to add
        # more loss functions that weren't defined in the method
        #(SGDClassifier, params('loss', 'penalty', 'alpha')['loss'].extend(['log', 'modified_huber'])),
        (KNeighborsClassifier, params('n_neighbors', 'leaf_size', 'p').update({
            'algorithm': ['auto', 'brute', 'kd_tree', 'ball_tree']
        })),
        (MultinomialNB, params('alpha')),
        #(GaussianNB, None),
        #(BernoulliNB, params('alpha'))
    ]

    return models

def __init__(self):
        SingleClassifier.SingleClassifier.__init__(self)
        #weak classifier
        self.clf=GaussianNB()

def __init__(self):
        self.learner = GaussianNB()

def get_naive_bayes(self):
        """get naive bayes algorithm"""
        return GaussianNB()

def define_clfs_params(self):
        '''
        Defines all relevant parameters and classes for classfier objects.
        Edit these if you wish to change parameters.
        '''
        # These are the classifiers
        self.clfs = {
            'RF': RandomForestClassifier(n_estimators = 50, n_jobs = -1),
            'ET': ExtraTreesClassifier(n_estimators = 10, n_jobs = -1, criterion = 'entropy'),
            'AB': AdaBoostClassifier(DecisionTreeClassifier(max_depth = [1, 5, 10, 15]), algorithm = "SAMME", n_estimators = 200),
            'LR': LogisticRegression(penalty = 'l1', C = 1e5),
            'SVM': svm.SVC(kernel = 'linear', probability = True, random_state = 0),
            'GB': GradientBoostingClassifier(learning_rate = 0.05, subsample = 0.5, max_depth = 6, n_estimators = 10),
            'NB': GaussianNB(),
            'DT': DecisionTreeClassifier(),
            'SGD': SGDClassifier(loss = 'log', penalty = 'l2'),
            'KNN': KNeighborsClassifier(n_neighbors = 3)
            }
        # These are the parameters which will be run through
        self.params = {
             'RF':{'n_estimators': [1,10,100,1000], 'max_depth': [10, 15,20,30,40,50,60,70,100], 'max_features': ['sqrt','log2'],'min_samples_split': [2,5,10], 'random_state': [1]},
             'LR': {'penalty': ['l1','l2'], 'C': [0.00001,0.0001,0.001,0.01,0.1,1,10], 'random_state': [1]},
             'SGD': {'loss': ['log'], 'penalty': ['l2','l1','elasticnet'], 'random_state': [1]},
             'ET': {'n_estimators': [1,10,100,1000], 'criterion' : ['gini', 'entropy'], 'max_depth': [1,3,5,10,15], 'max_features': ['sqrt','log2'],'min_samples_split': [2,5,10], 'random_state': [1]},
             'AB': {'algorithm': ['SAMME', 'SAMME.R'], 'n_estimators': [1,10,100,1000], 'random_state': [1]},
             'GB': {'n_estimators': [1,10,100,1000], 'learning_rate' : [0.001,0.01,0.05,0.1,0.5],'subsample' : [0.1,0.5,1.0], 'max_depth': [1,3,5,10,20,50,100], 'random_state': [1]},
             'NB': {},
             'DT': {'criterion': ['gini', 'entropy'], 'max_depth': [1,2,15,20,30,40,50], 'max_features': ['sqrt','log2'],'min_samples_split': [2,5,10], 'random_state': [1]},
             'SVM' :{'C' :[0.00001,0.0001,0.001,0.01,0.1,1,10],'kernel':['linear'], 'random_state': [1]},
             'KNN' :{'n_neighbors': [1,5,10,25,50,100],'weights': ['uniform','distance'],'algorithm': ['auto','ball_tree','kd_tree']}
             }

def runner(i):
    sem.acquire()
    print("learn begin %s" % i)
    clf = ensemble.BaggingClassifier(naive_bayes.GaussianNB())
    clf = clf.fit(traindata, trainlabel[i])
    svms.append((i, clf))
    result[i] = clf.predict_proba(testdata)
    dbresult[i] = clf.predict_proba(dbdata)
    #print("label %s done\n%s"
    # % (i, metrics.classification_report(testlabel[i], result[i])))
    #print metrics.confusion_matrix(testlabel[i], result)
    sem.release()

def runner(i):
    sem.acquire()
    print("learn begin %s" % i)
    clf = ensemble.AdaBoostClassifier(naive_bayes.GaussianNB())
    clf = clf.fit(traindata, trainlabel[i])
    svms.append((i, clf))
    result[i] = clf.predict_proba(testdata)
    dbresult[i] = clf.predict_proba(dbdata)
    #print("label %s done\n%s"
    # % (i, metrics.classification_report(testlabel[i], result[i])))
    #print metrics.confusion_matrix(testlabel[i], result)
    sem.release()

def runner(i):
    sem.acquire()
    print("learn begin %s" % i)
    clf = naive_bayes.GaussianNB()
    clf = clf.fit(traindata, trainlabel[i])
    svms.append((i, clf))
    result[i] = clf.predict(testdata)
    dbresult[i] = clf.predict(dbdata)
    print("label %s done\n%s"
     % (i, metrics.classification_report(testlabel[i], result[i])))
    #print metrics.confusion_matrix(testlabel[i], result)
    sem.release()

def test_gaussiannb():
    iris = load_iris()
    clf = GaussianNB()
    clf.fit(iris.data, iris.target)
    y_pred = clf.predict(iris.data)
    print(y_pred)
    clf_ = SKGaussianNB()
    clf_.fit(iris.data, iris.target)
    print(clf_.predict(iris.data))


    print(iris.target)

def __init__(self, genres, data, type='knn', name='', clf_kwargs=None):
        self.logger = get_logger('classifier')
        self.display_name = name

        self.genres = genres
        self.m_genres = { genre:i for i, genre in enumerate(genres) }
        self.randstate = np.random.RandomState()
        self.scaler = StandardScaler()

        clf_kwargs = { } if not clf_kwargs else clf_kwargs
        if type in ['svm', 'mlp']:
            clf_kwargs['random_state'] = self.randstate

        if type == 'knn':
            self.proto_clf = KNeighborsClassifier(**clf_kwargs)
        elif type == 'svm':
            self.proto_clf = SVC(**clf_kwargs)
        elif type == 'dtree':
            self.proto_clf = DecisionTreeClassifier(**clf_kwargs)
        elif type == 'gnb':
            self.proto_clf = GaussianNB(**clf_kwargs)
        elif type == 'perc':
            self.proto_clf = Perceptron(**clf_kwargs)
        elif type == 'mlp':
            self.proto_clf = MLPClassifier(**clf_kwargs)
        elif type == 'ada':
            self.proto_clf = AdaBoostClassifier(**clf_kwargs)
        else:
            raise LookupError('Classifier type "{}" is invalid'.format(type))

        self._convert_data(data)

        self.logger.info('Classifier: {} (params={})'.format(
            self.proto_clf.__class__.__name__,
            clf_kwargs
        ))

def getModels():
    result = []
    result.append("LinearRegression")
    result.append("BayesianRidge")
    result.append("ARDRegression")
    result.append("ElasticNet")
    result.append("HuberRegressor")
    result.append("Lasso")
    result.append("LassoLars")
    result.append("Rigid")
    result.append("SGDRegressor")
    result.append("SVR")
    result.append("MLPClassifier")
    result.append("KNeighborsClassifier")
    result.append("SVC")
    result.append("GaussianProcessClassifier")
    result.append("DecisionTreeClassifier")
    result.append("RandomForestClassifier")
    result.append("AdaBoostClassifier")
    result.append("GaussianNB")
    result.append("LogisticRegression")
    result.append("QuadraticDiscriminantAnalysis")
    return result

def test_AdaBoostClassifier_base_classifier(*data):
    '''
    test Adaboost classifier with different number of classifier, and category of classifier
    :param data: train_data, test_data, train_value, test_value
    :return:  None
    '''
    from sklearn.naive_bayes import GaussianNB
    X_train,X_test,y_train,y_test=data
    fig=plt.figure()
    ax=fig.add_subplot(2,1,1)

    clf=ensemble.AdaBoostClassifier(learning_rate=0.1)
    clf.fit(X_train,y_train)
    ## graph
    estimators_num=len(clf.estimators_)
    X=range(1,estimators_num+1)
    ax.plot(list(X),list(clf.staged_score(X_train,y_train)),label="Traing score")
    ax.plot(list(X),list(clf.staged_score(X_test,y_test)),label="Testing score")
    ax.set_xlabel("estimator num")
    ax.set_ylabel("score")
    ax.legend(loc="lower right")
    ax.set_ylim(0,1)
    ax.set_title("AdaBoostClassifier with Decision Tree")

    ax=fig.add_subplot(2,1,2)
    clf=ensemble.AdaBoostClassifier(learning_rate=0.1,base_estimator=GaussianNB())
    clf.fit(X_train,y_train)
    ## graph
    estimators_num=len(clf.estimators_)
    X=range(1,estimators_num+1)
    ax.plot(list(X),list(clf.staged_score(X_train,y_train)),label="Traing score")
    ax.plot(list(X),list(clf.staged_score(X_test,y_test)),label="Testing score")
    ax.set_xlabel("estimator num")
    ax.set_ylabel("score")
    ax.legend(loc="lower right")
    ax.set_ylim(0,1)
    ax.set_title("AdaBoostClassifier with Gaussian Naive Bayes")
    plt.show()

def script_run():
    # ??keyword
    kw_list = build_key_word("train.txt")
    # ????
    fp = open("new_word.txt", encoding="utf-8", mode="w")
    for word in kw_list:
        fp.write(word + "\n")
    fp.close()
   # kw_list = load_key_words("word.txt")
    feature, label = get_feature("train.txt", kw_list)
    gnb = GaussianNB()
    gnb = gnb.fit(feature, label)
    joblib.dump(gnb, 'model/gnb.model')
    print("????")
    # print(feature,label)

def GaussianNBLocalModel(localTrainFeature, localTestFeature, localTrainLabel, config):
    print 'train...'
    model = GaussianNB()
    model.fit(X = localTrainFeature.toarray(), y = localTrainLabel)
    print 'predict...'
    if config['prob'] == False:
        return model.predict(localTestFeature.toarray())
    else:
        return model.predict_log_proba(localTestFeature.toarray())

#-- Gaussian Navie Bayes online predict model frame

def sk_demo_1():
    X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]])
    Y = np.array([1, 1, 1, 2, 2, 2])
    clf = GaussianNB()
    clf.fit(X, Y)
    test_item = np.array([[-0.8, -1]])
    print clf.predict(test_item)
    # [1]
    print clf.get_params()

def sk_nb_diabetes():
    x_train, x_test, y_train, y_test = load_diabetes_data()
    clf = GaussianNB()

def test_majority_label_iris():
    """Check classification by majority label on dataset iris."""
    clf1 = LogisticRegression(random_state=123)
    clf2 = RandomForestClassifier(random_state=123)
    clf3 = GaussianNB()
    eclf = VotingClassifier(estimators=[
                ('lr', clf1), ('rf', clf2), ('gnb', clf3)],
                voting='hard')
    scores = cross_val_score(eclf, X, y, cv=5, scoring='accuracy')
    assert_almost_equal(scores.mean(), 0.95, decimal=2)

def test_weights_iris():
    """Check classification by average probabilities on dataset iris."""
    clf1 = LogisticRegression(random_state=123)
    clf2 = RandomForestClassifier(random_state=123)
    clf3 = GaussianNB()
    eclf = VotingClassifier(estimators=[
                            ('lr', clf1), ('rf', clf2), ('gnb', clf3)],
                            voting='soft',
                            weights=[1, 2, 10])
    scores = cross_val_score(eclf, X, y, cv=5, scoring='accuracy')
    assert_almost_equal(scores.mean(), 0.93, decimal=2)