Python model_selection.cross_val_score函数代码示例

def main():
    from sklearn import preprocessing
    from sklearn.datasets import fetch_mldata
    from sklearn.model_selection import cross_val_score

    db_name = 'iris'
    hid_num = 1000
    data_set = fetch_mldata(db_name)
    data_set.data = preprocessing.scale(data_set.data)

    print(db_name)
    print('ECOBELM', hid_num)
    e = ECOBELM(hid_num, c=2**5)
    ave = 0
    for i in range(10):
        scores = cross_val_score(
            e, data_set.data, data_set.target, cv=5, scoring='accuracy')
        ave += scores.mean()
    ave /= 10
    print("Accuracy: %0.2f " % (ave))

    print('ELM', hid_num)
    e = ELM(hid_num)
    ave = 0
    for i in range(10):
        scores = cross_val_score(
            e, data_set.data, data_set.target, cv=5, scoring='accuracy')
        ave += scores.mean()
    ave /= 10
    print("Accuracy: %0.2f " % (ave))

def neural_net(features,target,test_size_percent=0.2,cv_split=3,n_iter=100,learning_rate=0.01):
    '''Features -> Pandas Dataframe with attributes as columns
        target -> Pandas Dataframe with target column for prediction
        Test_size_percent -> Percentage of data point to be used for testing'''
    scale=preprocessing.MinMaxScaler()
    X_array = scale.fit_transform(features)
    y_array = scale.fit_transform(target)
    mlp = Regressor(layers=[Layer("Rectifier",units=5), # Hidden Layer1
                            Layer("Rectifier",units=3)  # Hidden Layer2
                            ,Layer("Linear")],     # Output Layer
                        n_iter = n_iter, learning_rate=0.01)
    X_train, X_test, y_train, y_test = train_test_split(X_array, y_array.T.squeeze(), test_size=test_size_percent, random_state=4)
    mlp.fit(X_train,y_train)
    test_prediction = mlp.predict(X_test)
    tscv = TimeSeriesSplit(cv_split)
    
    training_score = cross_val_score(mlp,X_train,y_train,cv=tscv.n_splits) 
    testing_score = cross_val_score(mlp,X_test,y_test,cv=tscv.n_splits)
    print"Cross-val Training score:", training_score.mean()
#    print"Cross-val Testing score:", testing_score.mean()
    training_predictions = cross_val_predict(mlp,X_train,y_train,cv=tscv.n_splits)
    testing_predictions = cross_val_predict(mlp,X_test,y_test,cv=tscv.n_splits)
    
    training_accuracy = metrics.r2_score(y_train,training_predictions) 
#    test_accuracy_model = metrics.r2_score(y_test,test_prediction_model)
    test_accuracy = metrics.r2_score(y_test,testing_predictions)
    
#    print"Cross-val predicted accuracy:", training_accuracy
    print"Test-predictions accuracy:",test_accuracy

    plot_model(target,y_train,y_test,training_predictions,testing_predictions)
    return mlp

    def three_models_combined(self, intrusion_features, avoidance_features, hypertension_features):

        self.df = self.df[~self.df['intrusion_cutoff'].isna()]
        self.df = self.df[~self.df['avoidance_cutoff'].isna()]
        self.df = self.df[~self.df['hypertention_cutoff'].isna()]
        print("self.df.shape", self.df.shape)
        X = self.df
        Y = self.df[self.target]# strict
        all_Y = [self.target, "intrusion_cutoff", "avoidance_cutoff", "hypertention_cutoff"]


        X_train, X_test, y_train, y_test = train_test_split(X, self.df[all_Y], test_size=0.25, random_state = 8526566, stratify=Y)

        # intrusion
        X_intrusion = X_train[intrusion_features].values
        y_intrusion = y_train["intrusion_cutoff"].apply(lambda x: int(x))
        pipe_intrusion = Pipeline(steps=[
            ('rfe', BorderlineSMOTE()),
            ('classifier', XGBClassifier(n_estimators=100, reg_alpha=1))])
        scores = cross_val_score(pipe_intrusion, X_intrusion, y_intrusion, scoring='precision', cv=StratifiedKFold(5))
        print(f"intrusion {sum(scores)/5}")
        pipe_intrusion.fit(X_intrusion, y_intrusion)

        # avoidance
        X_avoidance = X_train[avoidance_features].values
        y_avoidance = y_train["avoidance_cutoff"].apply(lambda x: int(x))
        pipe_avoidance = Pipeline(steps=[
            ('classifier', XGBClassifier(n_estimators=100, scale_pos_weight=3, reg_alpha=1))])
        scores = cross_val_score(pipe_avoidance, X_avoidance, y_avoidance, scoring='precision', cv=StratifiedKFold(5))
        print(f"avoidance {sum(scores)/5}")
        pipe_avoidance.fit(X_avoidance, y_avoidance)


        # hypertension
        X_hypertension = X_train[hypertension_features].values
        y_hypertention = y_train["hypertention_cutoff"].apply(lambda x: int(x))
        pipe_hypertension = Pipeline(steps=[
            ('classifier', BalancedBaggingClassifier(n_estimators=100))])
        scores = cross_val_score(pipe_hypertension, X_hypertension, y_hypertention, scoring='precision', cv=StratifiedKFold(5))
        print(f"hypertension {sum(scores)/5}")
        pipe_hypertension.fit(X_hypertension, y_hypertention)

        ## combine three classifiers
        X_test_hypertension = X_test[hypertension_features].values
        X_test_avoidance = X_test[avoidance_features].values
        X_test_intrusion = X_test[intrusion_features].values

        y_pred_hypertension = pipe_hypertension.predict(X_test_hypertension)
        y_pred_avoidance = pipe_avoidance.predict(X_test_avoidance)
        y_pred_intrusion = pipe_intrusion.predict(X_test_intrusion)
        y_pred = (y_pred_hypertension * y_pred_avoidance * y_pred_intrusion)

        y_target = y_test["PCL_Strict3"].apply(lambda x: int(x))

        acc = accuracy_score(y_target, y_pred)
        f1 = f1_score(y_target, y_pred)
        recall = recall_score(y_target, y_pred)
        precision = precision_score(y_target, y_pred)
        print("test scores")
        print(f"acc-{acc}, f1- {f1}, recall-{recall}, precision - {precision}")

def test_score_memmap():
    # Ensure a scalar score of memmap type is accepted
    iris = load_iris()
    X, y = iris.data, iris.target
    clf = MockClassifier()
    tf = tempfile.NamedTemporaryFile(mode='wb', delete=False)
    tf.write(b'Hello world!!!!!')
    tf.close()
    scores = np.memmap(tf.name, dtype=np.float64)
    score = np.memmap(tf.name, shape=(), mode='r', dtype=np.float64)
    try:
        cross_val_score(clf, X, y, scoring=lambda est, X, y: score)
        # non-scalar should still fail
        assert_raises(ValueError, cross_val_score, clf, X, y,
                      scoring=lambda est, X, y: scores)
    finally:
        # Best effort to release the mmap file handles before deleting the
        # backing file under Windows
        scores, score = None, None
        for _ in range(3):
            try:
                os.unlink(tf.name)
                break
            except WindowsError:
                sleep(1.)

    def _cross_validation(self, sentences, labels, intent_features, spacy_nlp, max_ngrams):
        """choose the best number of ngrams to include in bow.

        Given an intent classification problem and a set of ordered ngrams (ordered in terms
        of importance by pick_applicable_ngrams) we choose the best number of ngrams to include
        in our bow vecs by cross validation."""

        from sklearn import preprocessing
        from sklearn.linear_model import LogisticRegression
        from sklearn.model_selection import cross_val_score
        import numpy as np

        clf2 = LogisticRegression(class_weight='balanced')
        intent_encoder = preprocessing.LabelEncoder()
        intent_encoder.fit(labels)
        y = intent_encoder.transform(labels)
        cv_splits = min(10, np.min(np.bincount(y))) if y.size > 0 else 0
        if cv_splits >= 3:
            logger.debug("Started ngram cross-validation to find best number of ngrams to use...")
            num_ngrams = np.unique(list(map(int, np.floor(np.linspace(1, max_ngrams, 8)))))
            no_ngrams_X = self._create_bow_vecs(intent_features, sentences, spacy_nlp, max_ngrams=0)
            no_ngrams_score = np.mean(cross_val_score(clf2, no_ngrams_X, y, cv=cv_splits))
            scores = []
            for n in num_ngrams:
                X = self._create_bow_vecs(intent_features, sentences, spacy_nlp, max_ngrams=n)
                score = np.mean(cross_val_score(clf2, X, y, cv=cv_splits))
                scores.append(score)
                logger.debug("Evaluating usage of {} ngrams. Score: {}".format(n, score))
            n_top = num_ngrams[np.argmax(scores)]
            logger.debug("Score without ngrams: {}".format(no_ngrams_score))
            logger.info("Best score with {} ngrams: {}".format(n_top, np.max(scores)))
            return n_top
        else:
            warnings.warn("Can't cross-validate ngram featurizer. There aren't enough examples per intent (at least 3)")
            return max_ngrams

def main():
    # 1 查看训练集和测试集的数据特征
    train_data = pandas.read_csv('data/train.csv')
    test_data = pandas.read_csv('data/test.csv')
    print(train_data.info())
    print(test_data.info())
    # 2 人工选取预测有效的特征
    selected_features = ['Pclass', 'Sex', 'Age', 'Embarked', 'SibSp', 'Parch', 'Fare']
    x_train = train_data[selected_features]
    x_test = test_data[selected_features]

    y_train = train_data['Survived']

    # 3 补充缺失值
    # 得知Embared特征惨在缺失值，需要补完
    print(x_train['Embarked'].value_counts())
    print(x_test['Embarked'].value_counts())

    # 对于类别型特征，使用出现频率最高的特征来填充，可以作为减少引入误差的方法之一
    x_train['Embarked'].fillna('S', inplace=True)
    x_test['Embarked'].fillna('S', inplace=True)

    x_train['Age'].fillna(x_train['Age'].mean(), inplace=True)
    x_test['Age'].fillna(x_test['Age'].mean(), inplace=True)

    x_test['Fare'].fillna(x_test['Fare'].mean(), inplace=True)
    print(x_train.info())
    print(x_test.info())

    # 4 采用DictVectorizer对特征向量化
    dict_vectorizer = DictVectorizer(sparse=False)
    x_train = dict_vectorizer.fit_transform(x_train.to_dict(orient='record'))
    print(dict_vectorizer.feature_names_)
    x_test = dict_vectorizer.transform(x_test.to_dict(orient='record'))

    # 5 训练模型
    forest_classifier = RandomForestClassifier()
    xgb_classifier = XGBClassifier()

    # 使用5折交叉验证的方式进行性能评估
    forest_mean_score = cross_val_score(forest_classifier, x_train, y_train, cv=5).mean()
    print(forest_mean_score)
    xgb_mean_score = cross_val_score(xgb_classifier, x_train, y_train, cv=5).mean()
    print(xgb_mean_score)

    # 6 使用并行网格搜索的方式选择更好的超参组合
    params = {
        'max_depth': range(2, 8), 'n_estimators': range(100, 1200, 200),
        'learning_rate': [0.05, 0.1, 0.25, 0.5, 1.0]
    }
    xgbc_best = XGBClassifier()
    grid_search_cv = GridSearchCV(xgbc_best, params, n_jobs=-1, cv=5)
    grid_search_cv.fit(x_train, y_train)
    print(grid_search_cv.best_score_)
    print(grid_search_cv.best_params_)

    # 7 预测结果并写入文件
    predict_result = grid_search_cv.predict(x_test)
    submission_data = pandas.DataFrame({'PassengerId': test_data['PassengerId'], 'Survived': predict_result})
    submission_data.to_csv('data/submission/titanic_submission.csv', index=False)

def test_cross_val_score_fit_params():
    clf = MockClassifier()
    n_samples = X.shape[0]
    n_classes = len(np.unique(y))

    W_sparse = coo_matrix((np.array([1]), (np.array([1]), np.array([0]))),
                          shape=(10, 1))
    P_sparse = coo_matrix(np.eye(5))

    DUMMY_INT = 42
    DUMMY_STR = '42'
    DUMMY_OBJ = object()

    def assert_fit_params(clf):
        # Function to test that the values are passed correctly to the
        # classifier arguments for non-array type

        assert_equal(clf.dummy_int, DUMMY_INT)
        assert_equal(clf.dummy_str, DUMMY_STR)
        assert_equal(clf.dummy_obj, DUMMY_OBJ)

    fit_params = {'sample_weight': np.ones(n_samples),
                  'class_prior': np.ones(n_classes) / n_classes,
                  'sparse_sample_weight': W_sparse,
                  'sparse_param': P_sparse,
                  'dummy_int': DUMMY_INT,
                  'dummy_str': DUMMY_STR,
                  'dummy_obj': DUMMY_OBJ,
                  'callback': assert_fit_params}
    cross_val_score(clf, X, y, fit_params=fit_params)

def Random_forest(features,target,test_size_percent=0.2,cv_split=3):
    X_array = features.as_matrix()
    y_array = target.as_matrix()        
    model_rdf = RandomForestRegressor()
    X_train, X_test, y_train, y_test = train_test_split(X_array, y_array.T.squeeze(), test_size=test_size_percent, random_state=4)
    model_rdf.fit(X_train,y_train)
    test_prediction = model_rdf.predict(X_test)
    tscv = TimeSeriesSplit(cv_split)
    
    training_score = cross_val_score(model_rdf,X_train,y_train,cv=tscv.n_splits) 
    testing_score = cross_val_score(model_rdf,X_test,y_test,cv=tscv.n_splits)
    print"Cross-val Training score:", training_score.mean()
#    print"Cross-val Testing score:", testing_score.mean()
    training_predictions = cross_val_predict(model_rdf,X_train,y_train,cv=tscv.n_splits)
    testing_predictions = cross_val_predict(model_rdf,X_test,y_test,cv=tscv.n_splits)
    
    training_accuracy = metrics.r2_score(y_train,training_predictions) 
#    test_accuracy_model = metrics.r2_score(y_test,test_prediction_model)
    test_accuracy = metrics.r2_score(y_test,testing_predictions)
    
#    print"Cross-val predicted accuracy:", training_accuracy
    print"Test-predictions accuracy:",test_accuracy

    plot_model(target,y_train,y_test,training_predictions,testing_predictions)
    return model_rdf

def svm_regressor(features,target,test_size_percent=0.2,cv_split=5):
    
    scale=preprocessing.MinMaxScaler()
    X_array = scale.fit_transform(features)
    y_array = scale.fit_transform(target)  
    X_train, X_test, y_train, y_test = train_test_split(X_array, y_array.T.squeeze(), test_size=test_size_percent, random_state=4)
    svr = SVR(kernel='rbf',C=10,gamma=1)
    svr.fit(X_train,y_train.ravel())
    test_prediction = svr.predict(X_test)
    tscv = TimeSeriesSplit(cv_split)
    
    training_score = cross_val_score(svr,X_train,y_train,cv=tscv.n_splits) 
    testing_score = cross_val_score(svr,X_test,y_test,cv=tscv.n_splits)
    print"Cross-val Training score:", training_score.mean()
#    print"Cross-val Testing score:", testing_score.mean()
    training_predictions = cross_val_predict(svr,X_train,y_train,cv=tscv.n_splits)
    testing_predictions = cross_val_predict(svr,X_test,y_test,cv=tscv.n_splits)
    
    training_accuracy = metrics.r2_score(y_train,training_predictions) 
#    test_accuracy_model = metrics.r2_score(y_test,test_prediction_model)
    test_accuracy = metrics.r2_score(y_test,testing_predictions)
    
#    print"Cross-val predicted accuracy:", training_accuracy
    print"Test-predictions accuracy:",test_accuracy
    return svr

def linear_regression(features,target,test_size_percent=0.2,cv_split=5):
    ''' Features -> Pandas Dataframe with attributes as columns
        target -> Pandas Dataframe with target column for prediction
        Test_size_percent -> Percentage of data point to be used for testing'''
    X_array = features.as_matrix()
    y_array = target.as_matrix()    
    ols = linear_model.LinearRegression()
    X_train, X_test, y_train, y_test = train_test_split(X_array, y_array.T.squeeze(), test_size=test_size_percent, random_state=4)
#    model = ols.fit(X_train, y_train)
    ols.fit(X_train, y_train)
#    test_prediction_model = ols.predict(X_test)
    tscv = TimeSeriesSplit(cv_split)
    
    training_score = cross_val_score(ols,X_train,y_train,cv=tscv.n_splits) 
    testing_score = cross_val_score(ols,X_test,y_test,cv=tscv.n_splits)
    print"Cross-val Training score:", training_score.mean()
#    print"Cross-val Testing score:", testing_score.mean()
    training_predictions = cross_val_predict(ols,X_train,y_train,cv=tscv.n_splits)
    testing_predictions = cross_val_predict(ols,X_test,y_test,cv=tscv.n_splits)
    
    training_accuracy = metrics.r2_score(y_train,training_predictions) 
#    test_accuracy_model = metrics.r2_score(y_test,test_prediction_model)
    test_accuracy = metrics.r2_score(y_test,testing_predictions)
    
#    print"Cross-val predicted accuracy:", training_accuracy
    print"Test-predictions accuracy:",test_accuracy

    plot_model(target,y_train,y_test,training_predictions,testing_predictions)
    return ols

    def fit(self, X_train, y_train):
        # intrusion
        X_intrusion = X_train[self.features].values
        y_intrusion = X_train["intrusion_cutoff"].apply(lambda x: int(x))
        self.pipe_intrusion = Pipeline(steps=[
           ('rfe',  RFE(XGBClassifier(n_estimators=self.n_estimators, reg_alpha=1, scale_pos_weight=3), self.rfe)),
            ('classifier', XGBClassifier(n_estimators=self.n_estimators, reg_alpha=1, scale_pos_weight=3))])
        self.pipe_intrusion.fit(X_intrusion, y_intrusion)
        scores = cross_val_score(self.pipe_intrusion, X_intrusion, y_intrusion, scoring='precision', cv=StratifiedKFold(5))
        print(f"intrusion {sum(scores)/5}")
        self.pipe_intrusion.fit(X_intrusion, y_intrusion)

        # avoidance
        X_avoidance = X_train[self.features].values
        y_avoidance = X_train["avoidance_cutoff"].apply(lambda x: int(x))
        self.pipe_avoidance = Pipeline(steps=[
            ('rfe', RFE(XGBClassifier(n_estimators=self.n_estimators, reg_alpha=1, scale_pos_weight=6), self.rfe)),
            ('classifier', XGBClassifier(n_estimators=self.n_estimators, reg_alpha=1, scale_pos_weight=6))])
        self.pipe_avoidance.fit(X_avoidance, y_avoidance)
        scores = cross_val_score(self.pipe_avoidance, X_avoidance, y_avoidance, scoring='precision', cv=StratifiedKFold(5))
        print(f"avoidance {sum(scores)/5}")
        self.pipe_avoidance.fit(X_avoidance, y_avoidance)

        # hypertension
        X_hypertension = X_train[self.features].values
        y_hypertention = X_train["hypertention_cutoff"].apply(lambda x: int(x))
        self.pipe_hypertension = Pipeline(steps=[
            ('rfe', RFE(XGBClassifier(n_estimators=self.n_estimators, reg_alpha=1, scale_pos_weight=4), self.rfe)),
            ('classifier', XGBClassifier(n_estimators=self.n_estimators, reg_alpha=1, scale_pos_weight=4))])
        self.pipe_hypertension.fit(X_hypertension, y_hypertention)
        scores = cross_val_score(self.pipe_hypertension, X_hypertension, y_hypertention, scoring='precision', cv=StratifiedKFold(5))
        print(f"hypertension {sum(scores)/5}")
        self.pipe_hypertension.fit(X_hypertension, y_hypertention)

        # regression
        X_regression = X_train[self.features].values
        y_regression = X_train["PCL3"]
        self.pipe_regression = Pipeline(steps=[
            ('classifier', Ridge())])
        self.pipe_regression.fit(X_regression, y_regression)

        # target
        y_pred_hypertension = self.pipe_hypertension.predict(X_hypertension)
        y_pred_avoidance = self.pipe_avoidance.predict(X_avoidance)
        y_pred_intrusion = self.pipe_intrusion.predict(X_intrusion)
        y_pred_regression = self.pipe_regression.predict(X_regression) >= self.cutoff

        y_pred = (y_pred_hypertension & y_pred_avoidance & y_pred_intrusion & y_pred_regression & y_pred_regression)
        y_target = y_train

        acc = accuracy_score(y_target, y_pred)
        f1 = f1_score(y_target, y_pred)
        recall = recall_score(y_target, y_pred)
        precision = precision_score(y_target, y_pred)
        print("test scores")
        print(f"acc-{acc}, f1- {f1}, recall-{recall}, precision - {precision}")

def tune_spam(X_train,y_train,alpha_list):
    val_accuracy=[]
    for alpha in alpha_list:
        model = SVC(C=alpha)
        val_accuracy.extend([np.mean(cross_val_score(model, X_train, y_train, cv=5, scoring='accuracy'))])
        print [np.mean(cross_val_score(model, X_train, y_train, cv=5, scoring='accuracy'))]
    max_index =  val_accuracy.index(max( val_accuracy))
    print "CV_val_error:", val_accuracy
    print "Best C:",alpha_list[max_index]
    return alpha_list[max_index]

def test_cross_val_score_allow_nans():
    # Check that cross_val_score allows input data with NaNs
    X = np.arange(200, dtype=np.float64).reshape(10, -1)
    X[2, :] = np.nan
    y = np.repeat([0, 1], X.shape[0] / 2)
    p = Pipeline([
        ('imputer', Imputer(strategy='mean', missing_values='NaN')),
        ('classifier', MockClassifier()),
    ])
    cross_val_score(p, X, y, cv=5)

def test_k_fold_cv():
    """Test OneHotEncoder with categorical_features='auto'."""
    boston = load_boston()
    clf = make_pipeline(
        OneHotEncoder(
            categorical_features='auto',
            sparse=False,
            minimum_fraction=0.05
        ),
        LinearRegression()
    )

    cross_val_score(clf, boston.data, boston.target, cv=KFold(n_splits=10, shuffle=True))

def test_precomputed_cross_validation():
    # Ensure array is split correctly
    rng = np.random.RandomState(0)
    X = rng.rand(20, 2)
    D = pairwise_distances(X, metric='euclidean')
    y = rng.randint(3, size=20)
    for Est in (neighbors.KNeighborsClassifier,
                neighbors.RadiusNeighborsClassifier,
                neighbors.KNeighborsRegressor,
                neighbors.RadiusNeighborsRegressor):
        metric_score = cross_val_score(Est(), X, y)
        precomp_score = cross_val_score(Est(metric='precomputed'), D, y)
        assert_array_equal(metric_score, precomp_score)