Python sklearn.linear_model.LinearRegression() Examples

def trainModel(trainData, features, labels):
    """
    利用训练数据，估计模型参数

    参数
    ----
    trainData : DataFrame，训练数据集，包含特征和标签

    features : 特征名列表

    labels : 标签名列表

    返回
    ----
    model : LinearRegression, 训练好的线性模型
    """
    # 创建一个线性回归模型
    model = linear_model.LinearRegression()
    # 训练模型，估计模型参数
    model.fit(trainData[features], trainData[labels])
    return model 

def test_lin_reg(self):
        # python -m unittest tests_regression.Tests_Regression.test_lin_reg
        from sklearn import linear_model
        from discomll.regression import linear_regression

        x_train, y_train, x_test, y_test = datasets.ex3()
        train_data, test_data = datasets.ex3_discomll()

        lin_reg = linear_model.LinearRegression()  # Create linear regression object
        lin_reg.fit(x_train, y_train)  # Train the model using the training sets
        thetas1 = [lin_reg.intercept_] + lin_reg.coef_[1:].tolist()
        prediction1 = lin_reg.predict(x_test)

        thetas_url = linear_regression.fit(train_data)
        thetas2 = [v for k, v in result_iterator(thetas_url["linreg_fitmodel"])]
        results = linear_regression.predict(test_data, thetas_url)
        prediction2 = [v[0] for k, v in result_iterator(results)]

        self.assertTrue(np.allclose(thetas1, thetas2))
        self.assertTrue(np.allclose(prediction1, prediction2)) 

def test_same_results(self):
        from sklearn import datasets
        from sklearn.model_selection import train_test_split
        from sklearn import linear_model

        dataset = datasets.load_iris()
        X_train, X_test, y_train, y_test = train_test_split(dataset.data, dataset.target, test_size=0.2)

        clf = LinearRegression(data_norm=12, epsilon=float("inf"),
                               bounds_X=([4.3, 2.0, 1.0, 0.1], [7.9, 4.4, 6.9, 2.5]), bounds_y=(0, 2))
        clf.fit(X_train, y_train)

        predict1 = clf.predict(X_test)

        clf = linear_model.LinearRegression(normalize=False)
        clf.fit(X_train, y_train)

        predict2 = clf.predict(X_test)

        self.assertTrue(np.allclose(predict1, predict2)) 

def test_accountant(self):
        from diffprivlib.accountant import BudgetAccountant

        acc = BudgetAccountant()
        X = np.linspace(-1, 1, 1000)
        y = X.copy()
        X = X[:, np.newaxis]

        clf = LinearRegression(epsilon=2, data_norm=1, fit_intercept=False, accountant=acc)
        clf.fit(X, y)
        self.assertEqual((2, 0), acc.total())

        with BudgetAccountant(3, 0) as acc2:
            clf = LinearRegression(epsilon=2, data_norm=1, fit_intercept=False)
            clf.fit(X, y)
            self.assertEqual((2, 0), acc2.total())

            with self.assertRaises(BudgetError):
                clf.fit(X, y) 

def test_parameter_estimation_resampling_low_memory(self):
        X = np.random.uniform(0, 4, 1000)
        y = X + np.random.normal(0, 1, 1000)
        m = BayesianBootstrapBagging(LinearRegression(), 10000, 1000, low_mem=True)
        m.fit(X.reshape(-1, 1), y)
        coef_samples = [b.coef_ for b in m.base_models_]
        intercept_samples = [b.intercept_ for b in m.base_models_]
        self.assertAlmostEqual(np.mean(coef_samples), 1, delta=0.3)
        l, r = central_credible_interval(coef_samples, alpha=0.05)
        self.assertLess(l, 1)
        self.assertGreater(r, 1)
        l, r = highest_density_interval(coef_samples, alpha=0.05)
        self.assertLess(l, 1)
        self.assertGreater(r, 1)
        self.assertAlmostEqual(np.mean(intercept_samples), 0, delta=0.3)
        l, r = central_credible_interval(intercept_samples, alpha=0.05)
        self.assertLess(l, 0)
        self.assertGreater(r, 0)
        self.assertAlmostEqual(np.mean(intercept_samples), 0, delta=0.3)
        l, r = highest_density_interval(intercept_samples, alpha=0.05)
        self.assertLess(l, 0)
        self.assertGreater(r, 0) 

def test_parameter_estimation_resampling(self):
        X = np.random.uniform(0, 4, 1000)
        y = X + np.random.normal(0, 1, 1000)
        m = BayesianBootstrapBagging(LinearRegression(), 10000, 1000, low_mem=False)
        m.fit(X.reshape(-1, 1), y)
        coef_samples = [b.coef_ for b in m.base_models_]
        intercept_samples = [b.intercept_ for b in m.base_models_]
        self.assertAlmostEqual(np.mean(coef_samples), 1, delta=0.3)
        l, r = central_credible_interval(coef_samples, alpha=0.05)
        self.assertLess(l, 1)
        self.assertGreater(r, 1)
        l, r = highest_density_interval(coef_samples, alpha=0.05)
        self.assertLess(l, 1)
        self.assertGreater(r, 1)
        self.assertAlmostEqual(np.mean(intercept_samples), 0, delta=0.3)
        l, r = central_credible_interval(intercept_samples, alpha=0.05)
        self.assertLess(l, 0)
        self.assertGreater(r, 0)
        self.assertAlmostEqual(np.mean(intercept_samples), 0, delta=0.3)
        l, r = highest_density_interval(intercept_samples, alpha=0.05)
        self.assertLess(l, 0)
        self.assertGreater(r, 0) 

def test_parameter_estimation_bayes_low_memory(self):
        X = np.random.uniform(0, 4, 1000)
        y = X + np.random.normal(0, 1, 1000)
        m = BayesianBootstrapBagging(LinearRegression(), 10000, low_mem=True)
        m.fit(X.reshape(-1, 1), y)
        coef_samples = [b.coef_ for b in m.base_models_]
        intercept_samples = [b.intercept_ for b in m.base_models_]
        self.assertAlmostEqual(np.mean(coef_samples), 1, delta=0.3)
        l, r = central_credible_interval(coef_samples, alpha=0.05)
        self.assertLess(l, 1)
        self.assertGreater(r, 1)
        l, r = highest_density_interval(coef_samples, alpha=0.05)
        self.assertLess(l, 1)
        self.assertGreater(r, 1)
        self.assertAlmostEqual(np.mean(intercept_samples), 0, delta=0.3)
        l, r = central_credible_interval(intercept_samples, alpha=0.05)
        self.assertLess(l, 0)
        self.assertGreater(r, 0)
        self.assertAlmostEqual(np.mean(intercept_samples), 0, delta=0.3)
        l, r = highest_density_interval(intercept_samples, alpha=0.05)
        self.assertLess(l, 0)
        self.assertGreater(r, 0) 

def test_refit_nochange_reg(sim_nochange):
    """ Test refit ``keep_regularized=False`` (i.e., not ignoring coef == 0)
    """
    from sklearn.linear_model import LinearRegression as OLS
    estimator = OLS()

    refit = refit_record(sim_nochange, 'ols', estimator,
                         keep_regularized=False)
    assert 'ols_coef' in refit.dtype.names
    assert 'ols_rmse' in refit.dtype.names

    coef = np.array([[-3.83016528e+03, -3.83016528e+03],
                     [5.24635240e-03, 5.24635240e-03]])
    rmse = np.array([0.96794599, 0.96794599])
    np.testing.assert_allclose(refit[0]['ols_coef'], coef)
    np.testing.assert_allclose(refit[0]['ols_rmse'], rmse) 

def prepare_fit_model_for_factors(model_type, x_train, y_train):
    """
    Given a model type, train and test data
    
    Args:
        model_type (str): 'classification' or 'regression'
        x_train:
        y_train:

    Returns:
        (sklearn.base.BaseEstimator): A fit model.
    """

    if model_type == 'classification':
        algorithm = LogisticRegression()
    elif model_type == 'regression':
        algorithm = LinearRegression()
    else:
        algorithm = None

    if algorithm is not None:
        algorithm.fit(x_train, y_train)

    return algorithm 

def retrieve_from_scan(self, df_scan):
        from sklearn.linear_model import LinearRegression

        bpm_x = [self.bpm2x_name(bpm) for bpm in self.bpm_names]
        bpm_y = [self.bpm2y_name(bpm) for bpm in self.bpm_names]
        bpm_names_xy = bpm_x + bpm_y

        x = df_scan.loc[:, self.cor_names].values
        y = df_scan.loc[:, bpm_names_xy].values

        reg = LinearRegression().fit(x, y)
        #x_test = np.eye(np.shape(x)[1])
        rm = reg.coef_
        #df_rm = pd.DataFrame(rm.T, columns=self.cor_names, index=bpm_x+bpm_y)
        self.df = self.data2df(matrix=rm, bpm_names=self.bpm_names, cor_names=self.cor_names)
        return self.df 

def test_stacking():
    model = Regressor(estimator=LinearRegression, parameters={}, dataset=RealDataset)
    ds = model.stack(10)

    assert ds.X_train.shape[0] == model.dataset.X_train.shape[0]
    assert ds.X_test.shape[0] == model.dataset.X_test.shape[0]
    assert ds.y_train.shape[0] == model.dataset.y_train.shape[0]

    model = Regressor(estimator=LinearRegression, parameters={}, dataset=RealDataset)
    ds = model.stack(10, full_test=False)
    assert np.isnan(ds.X_train).sum() == 0
    assert ds.X_train.shape[0] == model.dataset.X_train.shape[0]
    assert ds.X_test.shape[0] == model.dataset.X_test.shape[0]
    assert ds.y_train.shape[0] == model.dataset.y_train.shape[0]

    model = Regressor(estimator=LinearRegression, parameters={}, dataset=RealDataset)
    model.dataset.load()
    ds = model.stack(10, full_test=False)
    # Check cache
    assert np.isnan(ds.X_train).sum() == 0
    assert ds.X_train.shape[0] == model.dataset.X_train.shape[0]
    assert ds.X_test.shape[0] == model.dataset.X_test.shape[0]
    assert ds.y_train.shape[0] == model.dataset.y_train.shape[0] 

def test_fixed_effect_contrast_nonzero_effect():
    X, y = make_regression(n_features=5, n_samples=20, random_state=0)
    y = y[:, None]
    labels, results = run_glm(y, X, 'ols')
    coef = LinearRegression(fit_intercept=False).fit(X, y).coef_
    for i in range(X.shape[1]):
        contrast = np.zeros(X.shape[1])
        contrast[i] = 1.
        fixed_effect = _compute_fixed_effect_contrast([labels],
                                                      [results],
                                                      [contrast],
                                                      )
        assert_almost_equal(fixed_effect.effect_size(), coef.ravel()[i])
        fixed_effect = _compute_fixed_effect_contrast(
            [labels] * 3, [results] * 3, [contrast] * 3)
        assert_almost_equal(fixed_effect.effect_size(), coef.ravel()[i]) 

def CalculateVIF2(self, df):
        # initialize dictionaries
        vif_dict, tolerance_dict = {}, {}

        # form input data for each exogenous variable
        for exog in df.columns:
            not_exog = [i for i in df.columns if i != exog]
            X, y = df[not_exog], df[exog]

            # extract r-squared from the fit
            r_squared = LinearRegression().fit(X, y).score(X, y)

            # calculate VIF
            vif = 1/(1 - r_squared)
            vif_dict[exog] = vif

            # calculate tolerance
            tolerance = 1 - r_squared
            tolerance_dict[exog] = tolerance

        # return VIF DataFrame
        df_vif = pd.DataFrame({'VIF': vif_dict, 'Tolerance': tolerance_dict})

        return df_vif 

def test_diff_detector_cross_validate(return_estimator: bool):
    """
    DiffBasedAnomalyDetector.cross_validate implementation should be the
    same as sklearn.model_selection.cross_validate if called the same.

    And it always will update `return_estimator` to True, as it requires
    the intermediate models to calculate the thresholds
    """
    X = np.random.random((100, 10))
    y = np.random.random((100, 1))

    model = DiffBasedAnomalyDetector(base_estimator=LinearRegression())

    cv = TimeSeriesSplit(n_splits=3)
    cv_results_da = model.cross_validate(
        X=X, y=y, cv=cv, return_estimator=return_estimator
    )
    cv_results_sk = cross_validate(model, X=X, y=y, cv=cv, return_estimator=True)

    assert cv_results_da.keys() == cv_results_sk.keys() 

def test_diff_detector_require_thresholds(require_threshold: bool):
    """
    Should fail if requiring thresholds, but not calling cross_validate
    """
    X = pd.DataFrame(np.random.random((100, 5)))
    y = pd.DataFrame(np.random.random((100, 2)))

    model = DiffBasedAnomalyDetector(
        base_estimator=MultiOutputRegressor(LinearRegression()),
        require_thresholds=require_threshold,
    )

    model.fit(X, y)

    if require_threshold:
        # FAIL: Forgot to call .cross_validate to calculate thresholds.
        with pytest.raises(AttributeError):
            model.anomaly(X, y)

        model.cross_validate(X=X, y=y)
        model.anomaly(X, y)
    else:
        # thresholds not required
        model.anomaly(X, y) 

def test_experiment_sklearn_regressor(tmpdir_name):
    X, y = make_regression_df(n_samples=1024, n_num_features=10, n_cat_features=0,
                              random_state=0, id_column='user_id')

    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=0)

    params = {
        'fit_intercept': True
    }

    result = run_experiment(params, X_train, y_train, X_test, tmpdir_name, with_auto_prep=False,
                            algorithm_type=LinearRegression)

    assert len(np.unique(result.oof_prediction)) > 5  # making sure prediction is not binarized
    assert len(np.unique(result.test_prediction)) > 5
    assert mean_squared_error(y_train, result.oof_prediction) == result.metrics[-1]

    _check_file_exists(tmpdir_name) 

def linearRegression():
    print(u"加载数据...\n")
    data = loadtxtAndcsv_data("data.txt",",",np.float64)  #读取数据
    X = np.array(data[:,0:-1],dtype=np.float64)      # X对应0到倒数第2列                  
    y = np.array(data[:,-1],dtype=np.float64)        # y对应最后一列  
        
    # 归一化操作
    scaler = StandardScaler()   
    scaler.fit(X)
    x_train = scaler.transform(X)
    x_test = scaler.transform(np.array([1650,3]))
    
    # 线性模型拟合
    model = linear_model.LinearRegression()
    model.fit(x_train, y)
    
    #预测结果
    result = model.predict(x_test)
    print(model.coef_)       # Coefficient of the features 决策函数中的特征系数
    print(model.intercept_)  # 又名bias偏置,若设置为False，则为0
    print(result)            # 预测结果


# 加载txt和csv文件 

def test_single_feature():
    estimator = linear_model.LinearRegression()
    estimator.coef_ = np.array([1])
    estimator.intercept_ = np.array([3])

    assembler = assemblers.SklearnLinearModelAssembler(estimator)
    actual = assembler.assemble()

    expected = ast.BinNumExpr(
        ast.NumVal(3),
        ast.BinNumExpr(
            ast.FeatureRef(0),
            ast.NumVal(1),
            ast.BinNumOpType.MUL),
        ast.BinNumOpType.ADD)

    assert utils.cmp_exprs(actual, expected) 

def test_two_features():
    estimator = linear_model.LinearRegression()
    estimator.coef_ = np.array([1, 2])
    estimator.intercept_ = np.array([3])

    assembler = assemblers.SklearnLinearModelAssembler(estimator)
    actual = assembler.assemble()

    expected = ast.BinNumExpr(
        ast.BinNumExpr(
            ast.NumVal(3),
            ast.BinNumExpr(
                ast.FeatureRef(0),
                ast.NumVal(1),
                ast.BinNumOpType.MUL),
            ast.BinNumOpType.ADD),
        ast.BinNumExpr(
            ast.FeatureRef(1),
            ast.NumVal(2),
            ast.BinNumOpType.MUL),
        ast.BinNumOpType.ADD)

    assert utils.cmp_exprs(actual, expected) 

def test_gradient_boosting_with_init_pipeline():
    # Check that the init estimator can be a pipeline (see issue #13466)

    X, y = make_regression(random_state=0)
    init = make_pipeline(LinearRegression())
    gb = GradientBoostingRegressor(init=init)
    gb.fit(X, y)  # pipeline without sample_weight works fine

    with pytest.raises(
            ValueError,
            match='The initial estimator Pipeline does not support sample '
                  'weights'):
        gb.fit(X, y, sample_weight=np.ones(X.shape[0]))

    # Passing sample_weight to a pipeline raises a ValueError. This test makes
    # sure we make the distinction between ValueError raised by a pipeline that
    # was passed sample_weight, and a ValueError raised by a regular estimator
    # whose input checking failed.
    with pytest.raises(
            ValueError,
            match='nu <= 0 or nu > 1'):
        # Note that NuSVR properly supports sample_weight
        init = NuSVR(gamma='auto', nu=1.5)
        gb = GradientBoostingRegressor(init=init)
        gb.fit(X, y, sample_weight=np.ones(X.shape[0])) 

def test_transform_target_regressor_error():
    X, y = friedman
    # provide a transformer and functions at the same time
    regr = TransformedTargetRegressor(regressor=LinearRegression(),
                                      transformer=StandardScaler(),
                                      func=np.exp, inverse_func=np.log)
    assert_raises_regex(ValueError, "'transformer' and functions"
                        " 'func'/'inverse_func' cannot both be set.",
                        regr.fit, X, y)
    # fit with sample_weight with a regressor which does not support it
    sample_weight = np.ones((y.shape[0],))
    regr = TransformedTargetRegressor(regressor=Lasso(),
                                      transformer=StandardScaler())
    assert_raises_regex(TypeError, r"fit\(\) got an unexpected keyword "
                        "argument 'sample_weight'", regr.fit, X, y,
                        sample_weight=sample_weight)
    # func is given but inverse_func is not
    regr = TransformedTargetRegressor(func=np.exp)
    assert_raises_regex(ValueError, "When 'func' is provided, 'inverse_func'"
                        " must also be provided", regr.fit, X, y) 

def test_transform_target_regressor_2d_transformer_multioutput():
    # Check consistency with transformer accepting only 2D array and a 2D y
    # array.
    X = friedman[0]
    y = np.vstack((friedman[1], friedman[1] ** 2 + 1)).T
    transformer = StandardScaler()
    regr = TransformedTargetRegressor(regressor=LinearRegression(),
                                      transformer=transformer)
    y_pred = regr.fit(X, y).predict(X)
    assert y.shape == y_pred.shape
    # consistency forward transform
    y_tran = regr.transformer_.transform(y)
    _check_standard_scaled(y, y_tran)
    assert y.shape == y_pred.shape
    # consistency inverse transform
    assert_allclose(y, regr.transformer_.inverse_transform(
        y_tran).squeeze())
    # consistency of the regressor
    lr = LinearRegression()
    transformer2 = clone(transformer)
    lr.fit(X, transformer2.fit_transform(y))
    y_lr_pred = lr.predict(X)
    assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred))
    assert_allclose(regr.regressor_.coef_, lr.coef_) 

def test_pipeline_raise_set_params_error():
    # Test pipeline raises set params error message for nested models.
    pipe = Pipeline([('cls', LinearRegression())])

    # expected error message
    error_msg = ('Invalid parameter %s for estimator %s. '
                 'Check the list of available parameters '
                 'with `estimator.get_params().keys()`.')

    assert_raise_message(ValueError,
                         error_msg % ('fake', pipe),
                         pipe.set_params,
                         fake='nope')

    # nested model check
    assert_raise_message(ValueError,
                         error_msg % ("fake", pipe),
                         pipe.set_params,
                         fake__estimator='nope') 

def evaluateModel(model, testData, features, labels):
    """
    计算线性模型的均方差和决定系数

    参数
    ----
    model : LinearRegression, 训练完成的线性模型

    testData : DataFrame，测试数据

    features : list[str]，特征名列表

    labels : list[str]，标签名列表

    返回
    ----
    error : np.float64，均方差

    score : np.float64，决定系数
    """
    # 均方差(The mean squared error)，均方差越小越好
    error = np.mean(
        (model.predict(testData[features]) - testData[labels]) ** 2)
    # 决定系数(Coefficient of determination)，决定系数越接近1越好
    score = model.score(testData[features], testData[labels])
    return error, score 

def test_not_none(self):
        self.assertIsNotNone(LinearRegression) 

def test_no_params(self):
        clf = LinearRegression()

        X = np.array(
            [0.50, 0.75, 1.00, 1.25, 1.50, 1.75, 1.75, 2.00, 2.25, 2.50, 2.75, 3.00, 3.25, 3.50, 4.00, 4.25, 4.50, 4.75,
             5.00, 5.50])
        y = np.array([0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1])
        X = X[:, np.newaxis]

        with self.assertWarns(PrivacyLeakWarning):
            clf.fit(X, y) 

def test_sample_weight_warning(self):
        clf = LinearRegression(data_norm=5.5, bounds_X=(0, 5), bounds_y=(0, 1))

        X = np.array(
            [0.50, 0.75, 1.00, 1.25, 1.50, 1.75, 1.75, 2.00, 2.25, 2.50, 2.75, 3.00, 3.25, 3.50, 4.00, 4.25, 4.50, 4.75,
             5.00, 5.50])
        y = np.array([0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1])
        X = X[:, np.newaxis]

        with self.assertWarns(DiffprivlibCompatibilityWarning):
            clf.fit(X, y, sample_weight=np.ones_like(y)) 

def test_no_range_y(self):
        clf = LinearRegression(data_norm=5.5, bounds_X=(0, 5))

        X = np.array(
            [0.50, 0.75, 1.00, 1.25, 1.50, 1.75, 1.75, 2.00, 2.25, 2.50, 2.75, 3.00, 3.25, 3.50, 4.00, 4.25, 4.50, 4.75,
             5.00, 5.50])
        y = np.array([0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1])
        X = X[:, np.newaxis]

        with self.assertWarns(PrivacyLeakWarning):
            clf.fit(X, y) 

def test_large_norm(self):
        X = np.array(
            [0.50, 0.75, 1.00, 1.25, 1.50, 1.75, 1.75, 2.00, 2.25, 2.50, 2.75, 3.00, 3.25, 3.50, 4.00, 4.25, 4.50, 4.75,
             5.00, 5.50])
        y = np.array([0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1])
        X = X[:, np.newaxis]

        clf = LinearRegression(data_norm=1.0, fit_intercept=False)

        self.assertIsNotNone(clf.fit(X, y)) 

def test_simple(self):
        X = np.linspace(-1, 1, 1000)
        y = X.copy()
        X = X[:, np.newaxis]

        clf = LinearRegression(epsilon=2, data_norm=1, fit_intercept=False)
        clf.fit(X, y)

        self.assertIsNotNone(clf)
        self.assertAlmostEqual(clf.predict(np.array([0.5]).reshape(-1, 1))[0], 0.5, places=3)