Python sklearn.utils.extmath.weighted_mode() Examples

def _get_redop(red_op, weights=None, axis=None):
    if red_op in ['mean', 'average']:
        if weights is None:
            def fred(x, w): return np.mean(x, axis=axis)
        else:
            def fred(x, w): return np.average(x, weights=w, axis=axis)
    elif red_op == 'median':
        def fred(x, w): return np.median(x, axis=axis)
    elif red_op == 'mode':
        if weights is None:
            def fred(x, w): return mode(x, axis=axis)[0].ravel()
        else:
            def fred(x, w): return weighted_mode(x, w, axis=axis)
    elif red_op == 'sum':
        def fred(x, w): return np.sum(x if w is None else w * x, axis=axis)
    elif red_op == 'max':
        def fred(x, w): return np.max(x, axis=axis)
    elif red_op == 'min':
        def fred(x, w): return np.min(x, axis=axis)
    else:
        raise ValueError("Unknown reduction operation '{0}'".format(red_op))
    return fred 

def test_random_weights():
    # set this up so that each row should have a weighted mode of 6,
    # with a score that is easily reproduced
    mode_result = 6

    rng = np.random.RandomState(0)
    x = rng.randint(mode_result, size=(100, 10))
    w = rng.random_sample(x.shape)

    x[:, :5] = mode_result
    w[:, :5] += 1

    mode, score = weighted_mode(x, w, axis=1)

    assert_array_equal(mode, mode_result)
    assert_array_almost_equal(score.ravel(), w[:, :5].sum(1)) 

def test_random_weights():
    # set this up so that each row should have a weighted mode of 6,
    # with a score that is easily reproduced
    mode_result = 6

    rng = np.random.RandomState(0)
    x = rng.randint(mode_result, size=(100, 10))
    w = rng.random_sample(x.shape)

    x[:, :5] = mode_result
    w[:, :5] += 1

    mode, score = weighted_mode(x, w, axis=1)

    assert_array_equal(mode, mode_result)
    assert_array_almost_equal(score.ravel(), w[:, :5].sum(1)) 

def test_uniform_weights():
    # with uniform weights, results should be identical to stats.mode
    rng = np.random.RandomState(0)
    x = rng.randint(10, size=(10, 5))
    weights = np.ones(x.shape)

    for axis in (None, 0, 1):
        mode, score = stats.mode(x, axis)
        mode2, score2 = weighted_mode(x, weights, axis)

        assert_array_equal(mode, mode2)
        assert_array_equal(score, score2) 

def _distance_weighting(neighbor_vals, neighbor_dist):
        neighbor_weights = 1 / neighbor_dist
        X = weighted_mode(neighbor_vals, neighbor_weights, axis=1)
        return X 

def _custom_weighting(self, neighbor_vals, neighbor_dist):
        neighbor_weights = self.weights(neighbor_dist)
        new_X = weighted_mode(neighbor_vals, neighbor_weights, axis=1)
        return new_X 

def test_uniform_weights():
    # with uniform weights, results should be identical to stats.mode
    rng = np.random.RandomState(0)
    x = rng.randint(10, size=(10, 5))
    weights = np.ones(x.shape)

    for axis in (None, 0, 1):
        mode, score = stats.mode(x, axis)
        mode2, score2 = weighted_mode(x, weights, axis)

        assert_array_equal(mode, mode2)
        assert_array_equal(score, score2) 

def majority_vote(scores, n_classes=2, weights=None):
    """Combination method to merge the scores from multiple estimators
    by majority vote.

    Parameters
    ----------
    scores : numpy array of shape (n_samples, n_estimators)
        Score matrix from multiple estimators on the same samples.

    n_classes : int, optional (default=2)
        The number of classes in scores matrix

    weights : numpy array of shape (1, n_estimators)
        If specified, using weighted majority weight.

    Returns
    -------
    combined_scores : numpy array of shape (n_samples, )
        The combined scores.

    """

    scores = check_array(scores)

    # assert only discrete scores are combined with majority vote
    check_classification_targets(scores)

    n_samples, n_estimators = scores.shape[0], scores.shape[1]

    vote_results = np.zeros([n_samples, ])

    if weights is not None:
        assert_equal(scores.shape[1], weights.shape[1])

    # equal weights if not set
    else:
        weights = np.ones([1, n_estimators])

    for i in range(n_samples):
        vote_results[i] = weighted_mode(scores[i, :], weights)[0][0]

    return vote_results.ravel() 

def predict(self, X):
        """Predict the class labels for the provided data

        Parameters
        ----------
        X : sktime-format pandas dataframe or array-like, shape (n_query,
        n_features), \
                or (n_query, n_indexed) if metric == 'precomputed'
            Test samples.

        Returns
        -------
        y : array of shape [n_samples] or [n_samples, n_outputs]
            Class labels for each data sample.
        """
        self.check_is_fitted()
        temp = check_array.__wrapped__.__code__
        check_array.__wrapped__.__code__ = _check_array_ts.__code__
        neigh_dist, neigh_ind = self.kneighbors(X)
        classes_ = self.classes_
        _y = self._y
        if not self.outputs_2d_:
            _y = self._y.reshape((-1, 1))
            classes_ = [self.classes_]

        n_outputs = len(classes_)
        n_samples = X.shape[0]
        weights = _get_weights(neigh_dist, self.weights)

        y_pred = np.empty((n_samples, n_outputs), dtype=classes_[0].dtype)
        for k, classes_k in enumerate(classes_):
            if weights is None:
                mode, _ = stats.mode(_y[neigh_ind, k], axis=1)
            else:
                mode, _ = weighted_mode(_y[neigh_ind, k], weights, axis=1)

            mode = np.asarray(mode.ravel(), dtype=np.intp)
            y_pred[:, k] = classes_k.take(mode)

        if not self.outputs_2d_:
            y_pred = y_pred.ravel()

        check_array.__wrapped__.__code__ = temp
        return y_pred