Python BaggingRegressor.score方法代码示例

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import score [as 别名]
def test_bootstrap_samples():
    """Test that bootstraping samples generate non-perfect base estimators."""
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    base_estimator = DecisionTreeRegressor().fit(X_train, y_train)

    # without bootstrap, all trees are perfect on the training set
    ensemble = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                max_samples=1.0,
                                bootstrap=False,
                                random_state=rng).fit(X_train, y_train)

    assert_equal(base_estimator.score(X_train, y_train),
                 ensemble.score(X_train, y_train))

    # with bootstrap, trees are no longer perfect on the training set
    ensemble = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                max_samples=1.0,
                                bootstrap=True,
                                random_state=rng).fit(X_train, y_train)

    assert_greater(base_estimator.score(X_train, y_train),
                   ensemble.score(X_train, y_train))

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import score [as 别名]
def test_oob_score_regression():
    # Check that oob prediction is a good estimation of the generalization
    # error.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    clf = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                           n_estimators=50,
                           bootstrap=True,
                           oob_score=True,
                           random_state=rng).fit(X_train, y_train)

    test_score = clf.score(X_test, y_test)

    assert_less(abs(test_score - clf.oob_score_), 0.1)

    # Test with few estimators
    assert_warns(UserWarning,
                 BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                  n_estimators=1,
                                  bootstrap=True,
                                  oob_score=True,
                                  random_state=rng).fit,
                 X_train,
                 y_train)

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import score [as 别名]
def test_bootstrap_samples():
    # Test that bootstrapping samples generate non-perfect base estimators.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    base_estimator = DecisionTreeRegressor().fit(X_train, y_train)

    # without bootstrap, all trees are perfect on the training set
    ensemble = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                max_samples=1.0,
                                bootstrap=False,
                                random_state=rng).fit(X_train, y_train)

    assert_equal(base_estimator.score(X_train, y_train),
                 ensemble.score(X_train, y_train))

    # with bootstrap, trees are no longer perfect on the training set
    ensemble = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                max_samples=1.0,
                                bootstrap=True,
                                random_state=rng).fit(X_train, y_train)

    assert_greater(base_estimator.score(X_train, y_train),
                   ensemble.score(X_train, y_train))

    # check that each sampling correspond to a complete bootstrap resample.
    # the size of each bootstrap should be the same as the input data but
    # the data should be different (checked using the hash of the data).
    ensemble = BaggingRegressor(base_estimator=DummySizeEstimator(),
                                bootstrap=True).fit(X_train, y_train)
    training_hash = []
    for estimator in ensemble.estimators_:
        assert estimator.training_size_ == X_train.shape[0]
        training_hash.append(estimator.training_hash_)
    assert len(set(training_hash)) == len(training_hash)

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import score [as 别名]
    print '******************************************'
    print name
    print '******************************************'
    
    if name=='Boston' or name=='Diabetes': # Regression problem
    
        rfr = RandomForestRegressor(**params)
        rfr.fit(X, y)
        print 'Score RandomForestRegressor = %s' % (rfr.score(X, y))
        scores_rfr = cross_val_score(rfr, X, y ,cv=5)
        print 'Cross Val Score RandomForestRegressor = %s' % (np.mean(scores_rfr))
        
        br = BaggingRegressor(base_estimator=DecisionTreeRegressor(max_depth=max_depth), n_estimators=n_estimators)
        br.fit(X, y)
        print 'Score BaggingRegressor = %s' % (br.score(X, y))
        scores_br = cross_val_score(br, X, y, cv=5)
        print 'Cross Val Scores of BR = %s' %(np.mean(scores_br))
        
    if name=='Iris' or name=='Digits': # Classificaiton problem
    
        rfc = RandomForestClassifier(**params)
        rfc.fit(X, y)
        print 'Score RandomForestClassifier = %s' % (rfc.score(X, y))
        scores_rfc = cross_val_score(rfc, X, y ,cv=5)
        print 'Corss Val Scores of RandomForestClassifier = %s' %(np.mean(scores_rfc))

        bc = BaggingClassifier(base_estimator=DecisionTreeClassifier(max_depth=max_depth), n_estimators=n_estimators)
        bc.fit(X, y)        
        print 'Score BaggingClassifier == %s' % (bc.score(X, y))
        scores_bc = cross_val_score(bc, X, y, cv=5)

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import score [as 别名]
def bagging(df1, features, pred_var, df2):
    lr = BaggingRegressor()
    lr.fit(df1[features], df1[pred_var])
    print 'BaggingClassifier Score: ', lr.score(df2[features], df2[pred_var])

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import score [as 别名]
        print '******************************************'
        
        if name=='Boston': # Regression problem
        
            rfr = RandomForestRegressor(**params)
            rfr.fit(X, y)
            scores_rfr = cross_val_score(rfr, X, y ,cv=5)

            br = BaggingRegressor(base_estimator=DecisionTreeRegressor(max_depth=max_depth), n_estimators=n_estimators)
            br.fit(X, y)
            scores_br = cross_val_score(br, X, y, cv=5)
            
            boston[i,1] = rfr.score(X, y)
            boston[i,2] = np.mean(scores_rfr)
            boston[i,3] = np.std(scores_rfr)
            boston[i,4] = br.score(X, y)
            boston[i,5] = np.mean(np.mean(scores_br))
            boston[i,6] = np.std(scores_br)

            print 'Score RandomForestRegressor = %s' % ( boston[i,1])
            print 'Cross Val : mean = %s' % (boston[i,2])
            print 'Cross Val : std = %s' % (boston[i,3])
            print 'Score BaggingRegressor = %s' % (boston[i,4])
            print 'Cross Val : mean = %s' %(boston[i,5])
            print 'Cross Val : std = %s' %(boston[i,6])
            
        if name=='Diabetes': # Regression problem
        
            rfr = RandomForestRegressor(**params)
            rfr.fit(X, y)
            scores_rfr = cross_val_score(rfr, X, y ,cv=5)