def test_multioutput_regression():
    y_true = np.array([[1, 0, 0, 1], [0, 1, 1, 1], [1, 1, 0, 1]])
    y_pred = np.array([[0, 0, 0, 1], [1, 0, 1, 1], [0, 0, 0, 1]])

    error = mean_squared_error(y_true, y_pred)
    assert_almost_equal(error, (1. / 3 + 2. / 3 + 2. / 3) / 4.)

    error = mean_squared_log_error(y_true, y_pred)
    assert_almost_equal(error, 0.200, decimal=2)

    # mean_absolute_error and mean_squared_error are equal because
    # it is a binary problem.
    error = mean_absolute_error(y_true, y_pred)
    assert_almost_equal(error, (1. / 3 + 2. / 3 + 2. / 3) / 4.)

    error = r2_score(y_true, y_pred, multioutput='variance_weighted')
    assert_almost_equal(error, 1. - 5. / 2)
    error = r2_score(y_true, y_pred, multioutput='uniform_average')
    assert_almost_equal(error, -.875) 

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_mean_squared_log_error(self):

        try:
            from sklearn.metrics import mean_squared_log_error as skmsle
        except:
            unittest.TestCase.skipTest(self, "sklearn is not found in the libraries")

        skmsle_score1 = skmsle(self.local_reg1.target, self.local_reg1.p_target)
        dlpymsle_score1 = mean_squared_log_error('target', 'p_target', castable=self.reg_table1)

        self.assertAlmostEqual(skmsle_score1, dlpymsle_score1)

        skmsle_score2 = skmsle(self.local_reg1.target, self.local_reg2.p_target)
        dlpymsle_score2 = mean_squared_log_error(self.reg_table1.target, self.reg_table2.p_target,
                                                 id_vars='id1')
        dlpymsle_score2_1 = mean_squared_log_error(self.reg_table1.target, self.reg_table2.p_target)

        self.assertAlmostEqual(skmsle_score2, dlpymsle_score2) 

def test_multioutput_regression():
    y_true = np.array([[1, 0, 0, 1], [0, 1, 1, 1], [1, 1, 0, 1]])
    y_pred = np.array([[0, 0, 0, 1], [1, 0, 1, 1], [0, 0, 0, 1]])

    error = mean_squared_error(y_true, y_pred)
    assert_almost_equal(error, (1. / 3 + 2. / 3 + 2. / 3) / 4.)

    error = mean_squared_log_error(y_true, y_pred)
    assert_almost_equal(error, 0.200, decimal=2)

    # mean_absolute_error and mean_squared_error are equal because
    # it is a binary problem.
    error = mean_absolute_error(y_true, y_pred)
    assert_almost_equal(error, (1. / 3 + 2. / 3 + 2. / 3) / 4.)

    error = r2_score(y_true, y_pred, multioutput='variance_weighted')
    assert_almost_equal(error, 1. - 5. / 2)
    error = r2_score(y_true, y_pred, multioutput='uniform_average')
    assert_almost_equal(error, -.875) 

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_regression_metrics(n_samples=50):
    y_true = np.arange(n_samples)
    y_pred = y_true + 1

    assert_almost_equal(mean_squared_error(y_true, y_pred), 1.)
    assert_almost_equal(mean_squared_log_error(y_true, y_pred),
                        mean_squared_error(np.log(1 + y_true),
                                           np.log(1 + y_pred)))
    assert_almost_equal(mean_absolute_error(y_true, y_pred), 1.)
    assert_almost_equal(median_absolute_error(y_true, y_pred), 1.)
    assert_almost_equal(max_error(y_true, y_pred), 1.)
    assert_almost_equal(r2_score(y_true, y_pred),  0.995, 2)
    assert_almost_equal(explained_variance_score(y_true, y_pred), 1.) 

def score(self,
              actual: np.array,
              predicted: np.array,
              sample_weight: typing.Optional[np.array] = None,
              labels: typing.Optional[np.array] = None,
              **kwargs) -> float:
        if not ((actual >= 0).all() and (predicted >= 0).all()):
            return 1e36
        return mean_squared_log_error(actual, predicted) 

def gini_msle(truth, predictions):
    score = mean_squared_log_error(truth, predictions)
    return score 

def gini_msle(truth, predictions):
    score = np.sqrt(mean_squared_log_error(truth, predictions))
    return score 

def get_rmsle(y_true, y_pred):
    return np.sqrt(mean_squared_log_error(np.expm1(y_true), np.expm1(y_pred))) 

def main():
    vectorizer = make_union(
        on_field('name', Tfidf(max_features=100000, token_pattern='\w+')),
        on_field('text', Tfidf(max_features=100000, token_pattern='\w+', ngram_range=(1, 2))),
        on_field(['shipping', 'item_condition_id'],
                 FunctionTransformer(to_records, validate=False), DictVectorizer()),
        n_jobs=4)
    y_scaler = StandardScaler()
    with timer('process train'):
        train = pd.read_table('../input/train.tsv')
        train = train[train['price'] > 0].reset_index(drop=True)
        cv = KFold(n_splits=20, shuffle=True, random_state=42)
        train_ids, valid_ids = next(cv.split(train))
        train, valid = train.iloc[train_ids], train.iloc[valid_ids]
        y_train = y_scaler.fit_transform(np.log1p(train['price'].values.reshape(-1, 1)))
        X_train = vectorizer.fit_transform(preprocess(train)).astype(np.float32)
        print(f'X_train: {X_train.shape} of {X_train.dtype}')
        del train
    with timer('process valid'):
        X_valid = vectorizer.transform(preprocess(valid)).astype(np.float32)
    with ThreadPool(processes=4) as pool:
        Xb_train, Xb_valid = [x.astype(np.bool).astype(np.float32) for x in [X_train, X_valid]]
        xs = [[Xb_train, Xb_valid], [X_train, X_valid]] * 2
        y_pred = np.mean(pool.map(partial(fit_predict, y_train=y_train), xs), axis=0)
    y_pred = np.expm1(y_scaler.inverse_transform(y_pred.reshape(-1, 1))[:, 0])
    print('Valid RMSLE: {:.4f}'.format(np.sqrt(mean_squared_log_error(valid['price'], y_pred)))) 

def test_regression_metrics(n_samples=50):
    y_true = np.arange(n_samples)
    y_pred = y_true + 1

    assert_almost_equal(mean_squared_error(y_true, y_pred), 1.)
    assert_almost_equal(mean_squared_log_error(y_true, y_pred),
                        mean_squared_error(np.log(1 + y_true),
                                           np.log(1 + y_pred)))
    assert_almost_equal(mean_absolute_error(y_true, y_pred), 1.)
    assert_almost_equal(median_absolute_error(y_true, y_pred), 1.)
    assert_almost_equal(r2_score(y_true, y_pred),  0.995, 2)
    assert_almost_equal(explained_variance_score(y_true, y_pred), 1.) 

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(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.]) 

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

    mse = mean_squared_error(y_true, y_pred, multioutput='raw_values')
    mae = mean_absolute_error(y_true, y_pred, multioutput='raw_values')
    r = r2_score(y_true, y_pred, multioutput='raw_values')
    evs = explained_variance_score(y_true, y_pred, multioutput='raw_values')

    assert_array_almost_equal(mse, [0.125, 0.5625], decimal=2)
    assert_array_almost_equal(mae, [0.25, 0.625], decimal=2)
    assert_array_almost_equal(r, [0.95, 0.93], decimal=2)
    assert_array_almost_equal(evs, [0.95, 0.93], decimal=2)

    # mean_absolute_error and mean_squared_error are equal because
    # it is a binary problem.
    y_true = [[0, 0]]*4
    y_pred = [[1, 1]]*4
    mse = mean_squared_error(y_true, y_pred, multioutput='raw_values')
    mae = mean_absolute_error(y_true, y_pred, multioutput='raw_values')
    r = r2_score(y_true, y_pred, multioutput='raw_values')
    assert_array_almost_equal(mse, [1., 1.], decimal=2)
    assert_array_almost_equal(mae, [1., 1.], decimal=2)
    assert_array_almost_equal(r, [0., 0.], decimal=2)

    r = r2_score([[0, -1], [0, 1]], [[2, 2], [1, 1]], multioutput='raw_values')
    assert_array_almost_equal(r, [0, -3.5], decimal=2)
    assert_equal(np.mean(r), r2_score([[0, -1], [0, 1]], [[2, 2], [1, 1]],
                 multioutput='uniform_average'))
    evs = explained_variance_score([[0, -1], [0, 1]], [[2, 2], [1, 1]],
                                   multioutput='raw_values')
    assert_array_almost_equal(evs, [0, -1.25], decimal=2)

    # Checking for the condition in which both numerator and denominator is
    # zero.
    y_true = [[1, 3], [-1, 2]]
    y_pred = [[1, 4], [-1, 1]]
    r2 = r2_score(y_true, y_pred, multioutput='raw_values')
    assert_array_almost_equal(r2, [1., -3.], decimal=2)
    assert_equal(np.mean(r2), r2_score(y_true, y_pred,
                 multioutput='uniform_average'))
    evs = explained_variance_score(y_true, y_pred, multioutput='raw_values')
    assert_array_almost_equal(evs, [1., -3.], decimal=2)
    assert_equal(np.mean(evs), explained_variance_score(y_true, y_pred))

    # 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='raw_values')
    msle2 = mean_squared_error(np.log(1 + y_true), np.log(1 + y_pred),
                               multioutput='raw_values')
    assert_array_almost_equal(msle, msle2, decimal=2) 

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

    mse = mean_squared_error(y_true, y_pred, multioutput='raw_values')
    mae = mean_absolute_error(y_true, y_pred, multioutput='raw_values')
    r = r2_score(y_true, y_pred, multioutput='raw_values')
    evs = explained_variance_score(y_true, y_pred, multioutput='raw_values')

    assert_array_almost_equal(mse, [0.125, 0.5625], decimal=2)
    assert_array_almost_equal(mae, [0.25, 0.625], decimal=2)
    assert_array_almost_equal(r, [0.95, 0.93], decimal=2)
    assert_array_almost_equal(evs, [0.95, 0.93], decimal=2)

    # mean_absolute_error and mean_squared_error are equal because
    # it is a binary problem.
    y_true = [[0, 0]]*4
    y_pred = [[1, 1]]*4
    mse = mean_squared_error(y_true, y_pred, multioutput='raw_values')
    mae = mean_absolute_error(y_true, y_pred, multioutput='raw_values')
    r = r2_score(y_true, y_pred, multioutput='raw_values')
    assert_array_almost_equal(mse, [1., 1.], decimal=2)
    assert_array_almost_equal(mae, [1., 1.], decimal=2)
    assert_array_almost_equal(r, [0., 0.], decimal=2)

    r = r2_score([[0, -1], [0, 1]], [[2, 2], [1, 1]], multioutput='raw_values')
    assert_array_almost_equal(r, [0, -3.5], decimal=2)
    assert_equal(np.mean(r), r2_score([[0, -1], [0, 1]], [[2, 2], [1, 1]],
                 multioutput='uniform_average'))
    evs = explained_variance_score([[0, -1], [0, 1]], [[2, 2], [1, 1]],
                                   multioutput='raw_values')
    assert_array_almost_equal(evs, [0, -1.25], decimal=2)

    # Checking for the condition in which both numerator and denominator is
    # zero.
    y_true = [[1, 3], [-1, 2]]
    y_pred = [[1, 4], [-1, 1]]
    r2 = r2_score(y_true, y_pred, multioutput='raw_values')
    assert_array_almost_equal(r2, [1., -3.], decimal=2)
    assert_equal(np.mean(r2), r2_score(y_true, y_pred,
                 multioutput='uniform_average'))
    evs = explained_variance_score(y_true, y_pred, multioutput='raw_values')
    assert_array_almost_equal(evs, [1., -3.], decimal=2)
    assert_equal(np.mean(evs), explained_variance_score(y_true, y_pred))

    # 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='raw_values')
    msle2 = mean_squared_error(np.log(1 + y_true), np.log(1 + y_pred),
                               multioutput='raw_values')
    assert_array_almost_equal(msle, msle2, decimal=2)