Python metrics.mean_squared_error方法代码示例

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import mean_squared_error [as 别名]
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 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import mean_squared_error [as 别名]
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 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import mean_squared_error [as 别名]
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 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import mean_squared_error [as 别名]
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 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import mean_squared_error [as 别名]
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 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import mean_squared_error [as 别名]
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 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import mean_squared_error [as 别名]
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 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import mean_squared_error [as 别名]
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))} 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import mean_squared_error [as 别名]
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 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import mean_squared_error [as 别名]
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 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import mean_squared_error [as 别名]
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 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import mean_squared_error [as 别名]
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) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import mean_squared_error [as 别名]
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) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import mean_squared_error [as 别名]
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] 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import mean_squared_error [as 别名]
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