def test_regressor():
    X = [[0]] * 4  # ignored
    y = [1, 2, 1, 1]

    reg = DummyRegressor()
    reg.fit(X, y)
    assert_array_equal(reg.predict(X), [5. / 4] * len(X))

def mean_model(features, solutions, verbose=0):
    columns = solutions.columns
    clf = DummyRegressor()
    print('Training Model... ')
    clf.fit(features, solutions)
    print('Done Training')
    return (clf, columns)

def test_quantile_strategy_multioutput_regressor():

    random_state = np.random.RandomState(seed=1)

    X_learn = random_state.randn(10, 10)
    y_learn = random_state.randn(10, 5)

    median = np.median(y_learn, axis=0).reshape((1, -1))
    quantile_values = np.percentile(y_learn, axis=0, q=80).reshape((1, -1))

    X_test = random_state.randn(20, 10)
    y_test = random_state.randn(20, 5)

    # Correctness oracle
    est = DummyRegressor(strategy="quantile", quantile=0.5)
    est.fit(X_learn, y_learn)
    y_pred_learn = est.predict(X_learn)
    y_pred_test = est.predict(X_test)

    _check_equality_regressor(
        median, y_learn, y_pred_learn, y_test, y_pred_test)
    _check_behavior_2d(est)

    # Correctness oracle
    est = DummyRegressor(strategy="quantile", quantile=0.8)
    est.fit(X_learn, y_learn)
    y_pred_learn = est.predict(X_learn)
    y_pred_test = est.predict(X_test)

    _check_equality_regressor(
        quantile_values, y_learn, y_pred_learn, y_test, y_pred_test)
    _check_behavior_2d(est)

def test_y_mean_attribute_regressor():
    X = [[0]] * 5
    y = [1, 2, 4, 6, 8]
    # when strategy = 'mean'
    est = DummyRegressor(strategy='mean')
    est.fit(X, y)
    assert_equal(est.y_mean_, np.mean(y))

def train_classifier():
	X_train = tfv.transform(video_captions_train)
	X_test  = tfv.transform(video_captions_test)
	
	dummy = DummyRegressor(strategy="median")
	dummy.fit(X_train, Y_train)
	Y_pred_med = dummy.predict(X_test)

def test_dummy_regressor_on_nan_value():
    X = [[np.NaN]]
    y = [1]
    y_expected = [1]
    clf = DummyRegressor()
    clf.fit(X, y)
    y_pred = clf.predict(X)
    assert_array_equal(y_pred, y_expected)

def test_dummy_regressor_on_3D_array():
    X = np.array([[['foo']], [['bar']], [['baz']]])
    y = np.array([2, 2, 2])
    y_expected = np.array([2, 2, 2])
    cls = DummyRegressor()
    cls.fit(X, y)
    y_pred = cls.predict(X)
    assert_array_equal(y_pred, y_expected)

class Regressor(BaseEstimator):
    def __init__(self):
        self.clf = DummyRegressor()

    def fit(self, X, y):
        self.clf.fit(X, y)

    def predict(self, X):
        return self.clf.predict(X)

def test_scorer_sample_weight():
    # Test that scorers support sample_weight or raise sensible errors

    # Unlike the metrics invariance test, in the scorer case it's harder
    # to ensure that, on the classifier output, weighted and unweighted
    # scores really should be unequal.
    X, y = make_classification(random_state=0)
    _, y_ml = make_multilabel_classification(n_samples=X.shape[0], random_state=0)
    split = train_test_split(X, y, y_ml, random_state=0)
    X_train, X_test, y_train, y_test, y_ml_train, y_ml_test = split

    sample_weight = np.ones_like(y_test)
    sample_weight[:10] = 0

    # get sensible estimators for each metric
    sensible_regr = DummyRegressor(strategy="median")
    sensible_regr.fit(X_train, y_train)
    sensible_clf = DecisionTreeClassifier(random_state=0)
    sensible_clf.fit(X_train, y_train)
    sensible_ml_clf = DecisionTreeClassifier(random_state=0)
    sensible_ml_clf.fit(X_train, y_ml_train)
    estimator = dict(
        [(name, sensible_regr) for name in REGRESSION_SCORERS]
        + [(name, sensible_clf) for name in CLF_SCORERS]
        + [(name, sensible_ml_clf) for name in MULTILABEL_ONLY_SCORERS]
    )

    for name, scorer in SCORERS.items():
        if name in MULTILABEL_ONLY_SCORERS:
            target = y_ml_test
        else:
            target = y_test
        try:
            weighted = scorer(estimator[name], X_test, target, sample_weight=sample_weight)
            ignored = scorer(estimator[name], X_test[10:], target[10:])
            unweighted = scorer(estimator[name], X_test, target)
            assert_not_equal(
                weighted,
                unweighted,
                msg="scorer {0} behaves identically when "
                "called with sample weights: {1} vs "
                "{2}".format(name, weighted, unweighted),
            )
            assert_almost_equal(
                weighted,
                ignored,
                err_msg="scorer {0} behaves differently when "
                "ignoring samples and setting sample_weight to"
                " 0: {1} vs {2}".format(name, weighted, ignored),
            )

        except TypeError as e:
            assert_true(
                "sample_weight" in str(e),
                "scorer {0} raises unhelpful exception when called " "with sample weights: {1}".format(name, str(e)),
            )

def test_median_strategy_regressor():

    random_state = np.random.RandomState(seed=1)

    X = [[0]] * 5  # ignored
    y = random_state.randn(5)

    reg = DummyRegressor(strategy="median")
    reg.fit(X, y)
    assert_array_equal(reg.predict(X), [np.median(y)] * len(X))

def test_dummy_regressor_return_std():
    X = [[0]] * 3  # ignored
    y = np.array([2, 2, 2])
    y_std_expected = np.array([0, 0, 0])
    cls = DummyRegressor()
    cls.fit(X, y)
    y_pred_list = cls.predict(X, return_std=True)
    # there should be two elements when return_std is True
    assert_equal(len(y_pred_list), 2)
    # the second element should be all zeros
    assert_array_equal(y_pred_list[1], y_std_expected)

def simplest(cube, y, cv):
    """ just use the mean to impute the missing values
    """
    from sklearn.dummy import DummyRegressor
    clf = DummyRegressor()
    X = cube.reshape(cube.shape[0], cube.shape[1] * cube.shape[2])
    sse = np.zeros(y.shape[1])
    for train, test in cv:
        y_train, y_test = y[train], y[test]
        y_predict = clf.fit(X[train], y[train]).predict(X[test])
        sse += np.mean((y_predict - y_test) ** 2, 0)
    return sse

def _make_estimators(X_train, y_train, y_ml_train):
    # Make estimators that make sense to test various scoring methods
    sensible_regr = DummyRegressor(strategy='median')
    sensible_regr.fit(X_train, y_train)
    sensible_clf = DecisionTreeClassifier(random_state=0)
    sensible_clf.fit(X_train, y_train)
    sensible_ml_clf = DecisionTreeClassifier(random_state=0)
    sensible_ml_clf.fit(X_train, y_ml_train)
    return dict(
        [(name, sensible_regr) for name in REGRESSION_SCORERS] +
        [(name, sensible_clf) for name in CLF_SCORERS] +
        [(name, sensible_ml_clf) for name in MULTILABEL_ONLY_SCORERS]
    )

def test_multioutput_regressor():

    X_learn = np.random.randn(10, 10)
    y_learn = np.random.randn(10, 5)

    mean = np.mean(y_learn, axis=0).reshape((1, -1))

    X_test = np.random.randn(20, 10)
    y_test = np.random.randn(20, 5)

    # Correctness oracle
    est = DummyRegressor()
    est.fit(X_learn, y_learn)
    y_pred_learn = est.predict(X_learn)
    y_pred_test = est.predict(X_test)

    assert_array_equal(np.tile(mean, (y_learn.shape[0], 1)), y_pred_learn)
    assert_array_equal(np.tile(mean, (y_test.shape[0], 1)), y_pred_test)
    _check_behavior_2d(est)

def test_mean_strategy_multioutput_regressor():

    random_state = np.random.RandomState(seed=1)

    X_learn = random_state.randn(10, 10)
    y_learn = random_state.randn(10, 5)

    mean = np.mean(y_learn, axis=0).reshape((1, -1))

    X_test = random_state.randn(20, 10)
    y_test = random_state.randn(20, 5)

    # Correctness oracle
    est = DummyRegressor()
    est.fit(X_learn, y_learn)
    y_pred_learn = est.predict(X_learn)
    y_pred_test = est.predict(X_test)

    _check_equality_regressor(mean, y_learn, y_pred_learn, y_test, y_pred_test)
    _check_behavior_2d(est)

def test_regressor_prediction_independent_of_X(strategy):
    y = [0, 2, 1, 1]
    X1 = [[0]] * 4
    reg1 = DummyRegressor(strategy=strategy, constant=0, quantile=0.7)
    reg1.fit(X1, y)
    predictions1 = reg1.predict(X1)

    X2 = [[1]] * 4
    reg2 = DummyRegressor(strategy=strategy, constant=0, quantile=0.7)
    reg2.fit(X2, y)
    predictions2 = reg2.predict(X2)

    assert_array_equal(predictions1, predictions2)

def test_scorer_sample_weight():
    """Test that scorers support sample_weight or raise sensible errors"""

    # Unlike the metrics invariance test, in the scorer case it's harder
    # to ensure that, on the classifier output, weighted and unweighted
    # scores really should be unequal.
    X, y = make_classification(random_state=0)
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
    sample_weight = np.ones_like(y_test)
    sample_weight[:10] = 0

    # get sensible estimators for each metric
    sensible_regr = DummyRegressor(strategy='median')
    sensible_regr.fit(X_train, y_train)
    sensible_clf = DecisionTreeClassifier()
    sensible_clf.fit(X_train, y_train)
    estimator = dict([(name, sensible_regr)
                      for name in REGRESSION_SCORERS] +
                     [(name, sensible_clf)
                      for name in CLF_SCORERS])

    for name, scorer in SCORERS.items():
        try:
            weighted = scorer(estimator[name], X_test, y_test,
                              sample_weight=sample_weight)
            ignored = scorer(estimator[name], X_test[10:], y_test[10:])
            unweighted = scorer(estimator[name], X_test, y_test)
            assert_not_equal(weighted, unweighted,
                             "scorer {0} behaves identically when called with "
                             "sample weights: {1} vs {2}".format(name,
                                                                 weighted,
                                                                 unweighted))
            assert_equal(weighted, ignored,
                         "scorer {0} behaves differently when ignoring "
                         "samples and setting sample_weight to 0: "
                         "{1} vs {2}".format(name, weighted, ignored))

        except TypeError as e:
            assert_true("sample_weight" in str(e),
                        "scorer {0} raises unhelpful exception when called "
                        "with sample weights: {1}".format(name, str(e)))

def _minimize_simbo_general(fun,
                            x0,  # only used to get number of features
                            args=(),
                            callback=None,
                            batch_size=100,
                            population_size=10000,
                            maxiter=10000,
                            scorer=None, # if no scorer given, scores are constant
                            selector=None, # only relevant is sampler is given
                            sampler=None):
    n_iter = int(maxiter / batch_size)
    assert n_iter > 0

    dummy_generator = generative_models.DummyGenerator(len(x0))

    if scorer is None:
        scorer = DummyRegressor()
    if sampler is None:
        sampler = dummy_generator

    if isinstance(selector, float) and 0 < selector < 1:
        selector = percentile_selector(selector)

    for i in range(n_iter):
        if i == 0:
            batch = dummy_generator.sample(batch_size)
        else:
            population = sampler.sample(population_size)
            scores = scorer.predict(population)
            batch_w_score = heapq.nsmallest(batch_size, zip(scores, population),
                                            key=lambda x: x[0])
            batch = [v for score, v in batch_w_score]
        results = optimize_utils.score_multi(fun, batch, args, callback)
        selected = selector(results, batch) if selector is not None else batch
        scorer.fit(batch, results)
        sampler.fit(selected)

    best_fval, best_x = max(zip(results, batch), key=lambda x: x[0])
    nfev = batch_size * n_iter
    return optimize_utils.to_result(x=best_x, fun=best_fval,
                                    niter=n_iter, nfev=nfev)

def test_constant_strategy_multioutput_regressor():

    random_state = np.random.RandomState(seed=1)

    X_learn = random_state.randn(10, 10)
    y_learn = random_state.randn(10, 5)

    # test with 2d array
    constants = random_state.randn(5)

    X_test = random_state.randn(20, 10)
    y_test = random_state.randn(20, 5)

    # Correctness oracle
    est = DummyRegressor(strategy="constant", constant=constants)
    est.fit(X_learn, y_learn)
    y_pred_learn = est.predict(X_learn)
    y_pred_test = est.predict(X_test)

    _check_equality_regressor(constants, y_learn, y_pred_learn, y_test, y_pred_test)
    _check_behavior_2d_for_constant(est)

def test_weights_regressor():
    """Check weighted average regression prediction on boston dataset."""
    reg1 = DummyRegressor(strategy='mean')
    reg2 = DummyRegressor(strategy='median')
    reg3 = DummyRegressor(strategy='quantile', quantile=.2)
    ereg = VotingRegressor([('mean', reg1), ('median', reg2),
                            ('quantile', reg3)], weights=[1, 2, 10])

    X_r_train, X_r_test, y_r_train, y_r_test = \
        train_test_split(X_r, y_r, test_size=.25)

    reg1_pred = reg1.fit(X_r_train, y_r_train).predict(X_r_test)
    reg2_pred = reg2.fit(X_r_train, y_r_train).predict(X_r_test)
    reg3_pred = reg3.fit(X_r_train, y_r_train).predict(X_r_test)
    ereg_pred = ereg.fit(X_r_train, y_r_train).predict(X_r_test)

    avg = np.average(np.asarray([reg1_pred, reg2_pred, reg3_pred]), axis=0,
                     weights=[1, 2, 10])
    assert_almost_equal(ereg_pred, avg, decimal=2)

    ereg_weights_none = VotingRegressor([('mean', reg1), ('median', reg2),
                                         ('quantile', reg3)], weights=None)
    ereg_weights_equal = VotingRegressor([('mean', reg1), ('median', reg2),
                                          ('quantile', reg3)],
                                         weights=[1, 1, 1])
    ereg_weights_none.fit(X_r_train, y_r_train)
    ereg_weights_equal.fit(X_r_train, y_r_train)
    ereg_none_pred = ereg_weights_none.predict(X_r_test)
    ereg_equal_pred = ereg_weights_equal.predict(X_r_test)
    assert_almost_equal(ereg_none_pred, ereg_equal_pred, decimal=2)