Python sklearn.metrics.mean_squared_error() Examples

def Train(data, modelcount, censhu, yanzhgdata):
    model = xgb.XGBRegressor(max_depth=censhu, learning_rate=0.1, n_estimators=modelcount, silent=True, objective='reg:gamma')

    model.fit(data[:, :-1], data[:, -1])
    # 给出训练数据的预测值
    train_out = model.predict(data[:, :-1])
    # 计算MSE
    train_mse = mse(data[:, -1], train_out)

    # 给出验证数据的预测值
    add_yan = model.predict(yanzhgdata[:, :-1])
    # 计算MSE
    add_mse = mse(yanzhgdata[:, -1], add_yan)
    print(train_mse, add_mse)
    return train_mse, add_mse

# 最终确定组合的函数 

def test_regression_small():
    X, y = make_regression(n_samples=2000,
                           n_features=10,
                           n_informative=5,
                           noise=30.0,
                           random_state=0)
    X = pd.DataFrame(X)
    y = pd.Series(y)
    cls = MALSS('regression').fit(X, y, 'test_regression_small')
    cls.generate_module_sample()

    from sklearn.metrics import mean_squared_error
    pred = cls.predict(X)
    print(mean_squared_error(y, pred))

    assert len(cls.algorithms) == 4
    assert cls.algorithms[0].best_score is not None 

def test_regression_medium():
    X, y = make_regression(n_samples=20000,
                           n_features=10,
                           n_informative=5,
                           noise=30.0,
                           random_state=0)
    X = pd.DataFrame(X)
    y = pd.Series(y)
    cls = MALSS('regression').fit(X, y, 'test_regression_medium')
    cls.generate_module_sample()

    from sklearn.metrics import mean_squared_error
    pred = cls.predict(X)
    print(mean_squared_error(y, pred))

    assert len(cls.algorithms) == 2
    assert cls.algorithms[0].best_score is not None 

def test_regression_big():
    X, y = make_regression(n_samples=200000,
                           n_features=10,
                           n_informative=5,
                           noise=30.0,
                           random_state=0)
    X = pd.DataFrame(X)
    y = pd.Series(y)
    cls = MALSS('regression').fit(X, y, 'test_regression_big')
    cls.generate_module_sample()

    from sklearn.metrics import mean_squared_error
    pred = cls.predict(X)
    print(mean_squared_error(y, pred))

    assert len(cls.algorithms) == 1
    assert cls.algorithms[0].best_score is not None 

def calculate_regression_metrics(trained_sklearn_estimator, x_test, y_test):
    """
    Given a trained estimator, calculate metrics.

    Args:
        trained_sklearn_estimator (sklearn.base.BaseEstimator): a scikit-learn estimator that has been `.fit()`
        y_test (numpy.ndarray): A 1d numpy array of the y_test set (predictions)
        x_test (numpy.ndarray): A 2d numpy array of the x_test set (features)

    Returns:
        dict: A dictionary of metrics objects
    """
    # Get predictions
    predictions = trained_sklearn_estimator.predict(x_test)

    # Calculate individual metrics
    mean_squared_error = skmetrics.mean_squared_error(y_test, predictions)
    mean_absolute_error = skmetrics.mean_absolute_error(y_test, predictions)

    result = {'mean_squared_error': mean_squared_error, 'mean_absolute_error': mean_absolute_error}

    return result 

def score_regression(y, y_hat, report=True):
    """
    Create regression score
    :param y:
    :param y_hat:
    :return:
    """
    r2 = r2_score(y, y_hat)
    rmse = sqrt(mean_squared_error(y, y_hat))
    mae = mean_absolute_error(y, y_hat)

    report_string = "---Regression Score--- \n"
    report_string += "R2 = " + str(r2) + "\n"
    report_string += "RMSE = " + str(rmse) + "\n"
    report_string += "MAE = " + str(mae) + "\n"

    if report:
        print(report_string)

    return mae, report_string 

def mean_squared_error_scorer(
    golds: ndarray,
    probs: ndarray,
    preds: Optional[ndarray],
    uids: Optional[List[str]] = None,
) -> Dict[str, float]:
    """Mean squared error regression loss.

    Args:
      golds: Ground truth values.
      probs: Predicted probabilities.
      preds: Predicted values.
      uids: Unique ids, defaults to None.

    Returns:
      Mean squared error regression loss.
    """
    return {"mean_squared_error": float(mean_squared_error(golds, probs))} 

def Train(data, treecount, tezh, yanzhgdata):
    model = RF(n_estimators=treecount, max_features=tezh)
    model.fit(data[:, :-1], data[:, -1])
    # 给出训练数据的预测值
    train_out = model.predict(data[:, :-1])
    # 计算MSE
    train_mse = mse(data[:, -1], train_out)

    # 给出验证数据的预测值
    add_yan = model.predict(yanzhgdata[:, :-1])
    # 计算MSE
    add_mse = mse(yanzhgdata[:, -1], add_yan)
    print(train_mse, add_mse)
    return train_mse, add_mse

# 最终确定组合的函数 

def Train(data, modelcount, censhu, yanzhgdata):
    model = AdaBoostRegressor(DecisionTreeRegressor(max_depth=censhu),
                              n_estimators=modelcount, learning_rate=0.8)

    model.fit(data[:, :-1], data[:, -1])
    # 给出训练数据的预测值
    train_out = model.predict(data[:, :-1])
    # 计算MSE
    train_mse = mse(data[:, -1], train_out)

    # 给出验证数据的预测值
    add_yan = model.predict(yanzhgdata[:, :-1])
    # 计算MSE
    add_mse = mse(yanzhgdata[:, -1], add_yan)
    print(train_mse, add_mse)
    return train_mse, add_mse

# 最终确定组合的函数 

def Train(data, modelcount, censhu, yanzhgdata):
    model = lgbm.LGBMRegressor(boosting_type='gbdt', objective='regression', num_leaves=1200,
                                learning_rate=0.17, n_estimators=modelcount, max_depth=censhu,
                                metric='rmse', bagging_fraction=0.8, feature_fraction=0.8, reg_lambda=0.9)

    model.fit(data[:, :-1], data[:, -1])
    # 给出训练数据的预测值
    train_out = model.predict(data[:, :-1])
    # 计算MSE
    train_mse = mse(data[:, -1], train_out)

    # 给出验证数据的预测值
    add_yan = model.predict(yanzhgdata[:, :-1])
    # 计算MSE
    add_mse = mse(yanzhgdata[:, -1], add_yan)
    print(train_mse, add_mse)
    return train_mse, add_mse

# 最终确定组合的函数 

def test_metrics_wrapper():
    # make the features in y be in different scales
    y = np.array([[1, 1], [2, 2], [3, 3], [4, 4], [5, 5]]) * [1, 100]

    # With no scaler provided it is relevant which of the two series gets an 80% error
    metric_func_noscaler = model_utils.metric_wrapper(mean_squared_error)

    mse_feature_one_wrong = metric_func_noscaler(y, y * [0.8, 1])
    mse_feature_two_wrong = metric_func_noscaler(y, y * [1, 0.8])

    assert not np.isclose(mse_feature_one_wrong, mse_feature_two_wrong)

    # With a scaler provided it is not relevant which of the two series gets an 80%
    # error
    scaler = MinMaxScaler().fit(y)
    metric_func_scaler = model_utils.metric_wrapper(mean_squared_error, scaler=scaler)

    mse_feature_one_wrong = metric_func_scaler(y, y * [0.8, 1])
    mse_feature_two_wrong = metric_func_scaler(y, y * [1, 0.8])

    assert np.isclose(mse_feature_one_wrong, mse_feature_two_wrong) 

def test_get_metrics_dict_scaler(scaler, mock):
    mock_model = mock
    metrics_list = [sklearn.metrics.mean_squared_error]
    # make the features in y be in different scales
    y = pd.DataFrame(
        np.array([[1, 1], [2, 2], [3, 3], [4, 4], [5, 5]]) * [1, 100],
        columns=["Tag 1", "Tag 2"],
    )
    metrics_dict = ModelBuilder.build_metrics_dict(metrics_list, y, scaler=scaler)
    metric_func = metrics_dict["mean-squared-error"]

    mock_model.predict = lambda _y: _y * [0.8, 1]
    mse_feature_one_wrong = metric_func(mock_model, y, y)
    mock_model.predict = lambda _y: _y * [1, 0.8]
    mse_feature_two_wrong = metric_func(mock_model, y, y)

    if scaler:
        assert np.isclose(mse_feature_one_wrong, mse_feature_two_wrong)
    else:
        assert not np.isclose(mse_feature_one_wrong, mse_feature_two_wrong) 

def test_metrics_from_list():
    """
    Check getting functions from a list of metric names
    """
    default = ModelBuilder.metrics_from_list()
    assert default == [
        metrics.explained_variance_score,
        metrics.r2_score,
        metrics.mean_squared_error,
        metrics.mean_absolute_error,
    ]

    specifics = ModelBuilder.metrics_from_list(
        ["sklearn.metrics.adjusted_mutual_info_score", "sklearn.metrics.r2_score"]
    )
    assert specifics == [metrics.adjusted_mutual_info_score, metrics.r2_score] 

def test_averaging_opt_minimize():
    X, y = make_regression_df(n_samples=1024)
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)

    oof, test = _make_1st_stage_preds(X_train, y_train, X_test)

    best_single_model = min(mean_squared_error(y_train, oof[0]),
                            mean_squared_error(y_train, oof[1]),
                            mean_squared_error(y_train, oof[2]))

    result = averaging_opt(test, oof, y_train, mean_squared_error, higher_is_better=False)

    assert result.score <= best_single_model

    result_simple_avg = averaging(test, oof, y_train, eval_func=mean_squared_error)

    assert result.score <= result_simple_avg.score 

def test_experiment_lgb_regressor(tmpdir_name):
    X, y = make_regression_df(n_samples=1024, n_num_features=10, n_cat_features=2,
                              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 = {
        'objective': 'regression',
        'max_depth': 8
    }

    result = run_experiment(params, X_train, y_train, X_test, tmpdir_name)

    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 test_boston():
    # Check consistency on dataset boston house prices.

    for (name, Tree), criterion in product(REG_TREES.items(), REG_CRITERIONS):
        reg = Tree(criterion=criterion, random_state=0)
        reg.fit(boston.data, boston.target)
        score = mean_squared_error(boston.target, reg.predict(boston.data))
        assert_less(score, 1,
                    "Failed with {0}, criterion = {1} and score = {2}"
                    "".format(name, criterion, score))

        # using fewer features reduces the learning ability of this tree,
        # but reduces training time.
        reg = Tree(criterion=criterion, max_features=6, random_state=0)
        reg.fit(boston.data, boston.target)
        score = mean_squared_error(boston.target, reg.predict(boston.data))
        assert_less(score, 2,
                    "Failed with {0}, criterion = {1} and score = {2}"
                    "".format(name, criterion, score)) 

def test_regression_metrics_at_limits():
    assert_almost_equal(mean_squared_error([0.], [0.]), 0.00, 2)
    assert_almost_equal(mean_squared_log_error([0.], [0.]), 0.00, 2)
    assert_almost_equal(mean_absolute_error([0.], [0.]), 0.00, 2)
    assert_almost_equal(median_absolute_error([0.], [0.]), 0.00, 2)
    assert_almost_equal(max_error([0.], [0.]), 0.00, 2)
    assert_almost_equal(explained_variance_score([0.], [0.]), 1.00, 2)
    assert_almost_equal(r2_score([0., 1], [0., 1]), 1.00, 2)
    assert_raises_regex(ValueError, "Mean Squared Logarithmic Error cannot be "
                        "used when targets contain negative values.",
                        mean_squared_log_error, [-1.], [-1.])
    assert_raises_regex(ValueError, "Mean Squared Logarithmic Error cannot be "
                        "used when targets contain negative values.",
                        mean_squared_log_error, [1., 2., 3.], [1., -2., 3.])
    assert_raises_regex(ValueError, "Mean Squared Logarithmic Error cannot be "
                        "used when targets contain negative values.",
                        mean_squared_log_error, [1., -2., 3.], [1., 2., 3.]) 

def test_regression_custom_weights():
    y_true = [[1, 2], [2.5, -1], [4.5, 3], [5, 7]]
    y_pred = [[1, 1], [2, -1], [5, 4], [5, 6.5]]

    msew = mean_squared_error(y_true, y_pred, multioutput=[0.4, 0.6])
    maew = mean_absolute_error(y_true, y_pred, multioutput=[0.4, 0.6])
    rw = r2_score(y_true, y_pred, multioutput=[0.4, 0.6])
    evsw = explained_variance_score(y_true, y_pred, multioutput=[0.4, 0.6])

    assert_almost_equal(msew, 0.39, decimal=2)
    assert_almost_equal(maew, 0.475, decimal=3)
    assert_almost_equal(rw, 0.94, decimal=2)
    assert_almost_equal(evsw, 0.94, decimal=2)

    # Handling msle separately as it does not accept negative inputs.
    y_true = np.array([[0.5, 1], [1, 2], [7, 6]])
    y_pred = np.array([[0.5, 2], [1, 2.5], [8, 8]])
    msle = mean_squared_log_error(y_true, y_pred, multioutput=[0.3, 0.7])
    msle2 = mean_squared_error(np.log(1 + y_true), np.log(1 + y_pred),
                               multioutput=[0.3, 0.7])
    assert_almost_equal(msle, msle2, decimal=2) 

def test_base_chain_crossval_fit_and_predict():
    # Fit chain with cross_val_predict and verify predict
    # performance
    X, Y = generate_multilabel_dataset_with_correlations()

    for chain in [ClassifierChain(LogisticRegression()),
                  RegressorChain(Ridge())]:
        chain.fit(X, Y)
        chain_cv = clone(chain).set_params(cv=3)
        chain_cv.fit(X, Y)
        Y_pred_cv = chain_cv.predict(X)
        Y_pred = chain.predict(X)

        assert Y_pred_cv.shape == Y_pred.shape
        assert not np.all(Y_pred == Y_pred_cv)
        if isinstance(chain, ClassifierChain):
            assert jaccard_score(Y, Y_pred_cv, average='samples') > .4
        else:
            assert mean_squared_error(Y, Y_pred_cv) < .25 

def __init__(self, transportAlgorithm="MappingTransport",
                 scaler=False, params=None, feedback=True):
        try:
            from sklearn.metrics import mean_squared_error
            from itertools import product
            from sklearn.metrics import (
                f1_score, cohen_kappa_score, accuracy_score)
        except BaseException:
            raise ImportError('Please install itertools and scikit-learn')

        self.transportAlgorithm = transportAlgorithm
        self.feedback = feedback

        self.params_ = params

        if scaler:
            from sklearn.preprocessing import MinMaxScaler
            self.scaler = MinMaxScaler(feature_range=(-1, 1))
            self.scalerTarget = MinMaxScaler(feature_range=(-1, 1))
        else:
            self.scaler = scaler 

def mse_cv(self, cv):
        """
        This method performs cross-validation over mean squared error.
        
        Parameters
        ----------
        * cv : integer
          The number of cross validation folds to perform

        Returns
        -------
        Returns a scores of the k-fold mean squared error.
        """
        mse = metrics.make_scorer(metrics.mean_squared_error)
        result = cross_validate(self.reg, self.X,
                                self.y, cv=cv,
                                scoring=(mse))
        return self.get_test_score(result) 

def rmse(a, b):
    return sqrt(mean_squared_error(a, b)) 

def rmse(a, b):
    return sqrt(mean_squared_error(a, b)) 

def rmse(a, b):
    return sqrt(mean_squared_error(a, b)) 

def rmse(a, b):
    return sqrt(mean_squared_error(a, b)) 

def rmse(y_pred, y_true):
    y_pred = y_pred.reshape(-1)
    y_true = y_true.reshape(-1)
    #print(y_true.shape)
    return np.sqrt(mean_squared_error(y_pred, y_true)) 

def rmse(y, p):
    """Root Mean Squared Error (RMSE).

    Args:
        y (numpy.array): target
        p (numpy.array): prediction

    Returns:
        e (numpy.float64): RMSE
    """

    # check and get number of samples
    assert y.shape == p.shape

    return np.sqrt(mse(y, p)) 

def plot(results, ax):
    df = results[["size", "time"]]

    df.plot.scatter(x='size', y='time', c='LightBlue', ax=ax, marker=".")

    # linear regression
    x = df["size"].values.reshape((-1, 1))
    y = df["time"].values
    linear = LinearRegression().fit(x, y)
    y_pred = linear.predict(x)

    mqe = mean_squared_error(y, y_pred)
    r2 = r2_score(y, y_pred)

    ax.plot(x, y_pred, color='DarkBlue', linewidth=2)

    ax.set_title(
        "Linear regression between size and time "
        f"\n$mse={mqe:.3f}$ - $R^2={r2:.3f}$")
    ax.set_xlabel("Size")
    ax.set_ylabel("Seconds")

    return ax


# =============================================================================
# CLI MAIN
# ============================================================================= 

def rmse(y_true, y_pred):
    assert y_true.shape == y_pred.shape
    return np.sqrt(mean_squared_error(y_true, y_pred)) 

def mse(preds, dtrain):
    """Compute mean squared error.

    For more information see: https://scikit-learn.org/stable/modules/generated/sklearn.metrics.mean_squared_error.html
    :param preds: Prediction values
    :param dtrain: Training data with labels
    :return: Metric name, mean squared error
    """
    labels = dtrain.get_label()
    return 'mse', mean_squared_error(labels, preds)