Python numpy.partition() Examples

def test_argequivalent(self):
        """ Test it translates from arg<func> to <func> """
        from numpy.random import rand
        a = rand(3, 4, 5)

        funcs = [
            (np.sort, np.argsort, dict()),
            (_add_keepdims(np.min), _add_keepdims(np.argmin), dict()),
            (_add_keepdims(np.max), _add_keepdims(np.argmax), dict()),
            (np.partition, np.argpartition, dict(kth=2)),
        ]

        for func, argfunc, kwargs in funcs:
            for axis in list(range(a.ndim)) + [None]:
                a_func = func(a, axis=axis, **kwargs)
                ai_func = argfunc(a, axis=axis, **kwargs)
                assert_equal(a_func, take_along_axis(a, ai_func, axis=axis)) 

def _get_scores(self):
        dataset = self.dataset
        self.model.train(dataset)
        unlabeled_entry_ids, X_pool = dataset.get_unlabeled_entries()

        if isinstance(self.model, ProbabilisticModel):
            dvalue = self.model.predict_proba(X_pool)
        elif isinstance(self.model, ContinuousModel):
            dvalue = self.model.predict_real(X_pool)

        if self.method == 'lc':  # least confident
            score = -np.max(dvalue, axis=1)

        elif self.method == 'sm':  # smallest margin
            if np.shape(dvalue)[1] > 2:
                # Find 2 largest decision values
                dvalue = -(np.partition(-dvalue, 2, axis=1)[:, :2])
            score = -np.abs(dvalue[:, 0] - dvalue[:, 1])

        elif self.method == 'entropy':
            score = np.sum(-dvalue * np.log(dvalue), axis=1)
        return zip(unlabeled_entry_ids, score) 

def test_partition_cdtype(self):
        d = array([('Galahad', 1.7, 38), ('Arthur', 1.8, 41),
                   ('Lancelot', 1.9, 38)],
                  dtype=[('name', '|S10'), ('height', '<f8'), ('age', '<i4')])

        tgt = np.sort(d, order=['age', 'height'])
        assert_array_equal(np.partition(d, range(d.size),
                                        order=['age', 'height']),
                           tgt)
        assert_array_equal(d[np.argpartition(d, range(d.size),
                                             order=['age', 'height'])],
                           tgt)
        for k in range(d.size):
            assert_equal(np.partition(d, k, order=['age', 'height'])[k],
                        tgt[k])
            assert_equal(d[np.argpartition(d, k, order=['age', 'height'])][k],
                         tgt[k])

        d = array(['Galahad', 'Arthur', 'zebra', 'Lancelot'])
        tgt = np.sort(d)
        assert_array_equal(np.partition(d, range(d.size)), tgt)
        for k in range(d.size):
            assert_equal(np.partition(d, k)[k], tgt[k])
            assert_equal(d[np.argpartition(d, k)][k], tgt[k]) 

def test_argequivalent(self):
        """ Test it translates from arg<func> to <func> """
        from numpy.random import rand
        a = rand(3, 4, 5)

        funcs = [
            (np.sort, np.argsort, dict()),
            (_add_keepdims(np.min), _add_keepdims(np.argmin), dict()),
            (_add_keepdims(np.max), _add_keepdims(np.argmax), dict()),
            (np.partition, np.argpartition, dict(kth=2)),
        ]

        for func, argfunc, kwargs in funcs:
            for axis in list(range(a.ndim)) + [None]:
                a_func = func(a, axis=axis, **kwargs)
                ai_func = argfunc(a, axis=axis, **kwargs)
                assert_equal(a_func, take_along_axis(a, ai_func, axis=axis)) 

def test_argequivalent(self):
        """ Test it translates from arg<func> to <func> """
        from numpy.random import rand
        a = rand(3, 4, 5)

        funcs = [
            (np.sort, np.argsort, dict()),
            (_add_keepdims(np.min), _add_keepdims(np.argmin), dict()),
            (_add_keepdims(np.max), _add_keepdims(np.argmax), dict()),
            (np.partition, np.argpartition, dict(kth=2)),
        ]

        for func, argfunc, kwargs in funcs:
            for axis in list(range(a.ndim)) + [None]:
                a_func = func(a, axis=axis, **kwargs)
                ai_func = argfunc(a, axis=axis, **kwargs)
                assert_equal(a_func, take_along_axis(a, ai_func, axis=axis)) 

def test_argequivalent(self):
        """ Test it translates from arg<func> to <func> """
        from numpy.random import rand
        a = rand(3, 4, 5)

        funcs = [
            (np.sort, np.argsort, dict()),
            (_add_keepdims(np.min), _add_keepdims(np.argmin), dict()),
            (_add_keepdims(np.max), _add_keepdims(np.argmax), dict()),
            (np.partition, np.argpartition, dict(kth=2)),
        ]

        for func, argfunc, kwargs in funcs:
            for axis in list(range(a.ndim)) + [None]:
                a_func = func(a, axis=axis, **kwargs)
                ai_func = argfunc(a, axis=axis, **kwargs)
                assert_equal(a_func, take_along_axis(a, ai_func, axis=axis)) 

def argpartition(a, kth, axis=-1):
    """Returns the indices that would partially sort an array.

    Args:
        a (cupy.ndarray): Array to be sorted.
        kth (int or sequence of ints): Element index to partition by. If
            supplied with a sequence of k-th it will partition all elements
            indexed by k-th of them into their sorted position at once.
        axis (int or None): Axis along which to sort. Default is -1, which
            means sort along the last axis. If None is supplied, the array is
            flattened before sorting.

    Returns:
        cupy.ndarray: Array of the same type and shape as ``a``.

    .. note::
        For its implementation reason, `cupy.argpartition` fully sorts the
        given array as `cupy.argsort` does. It also does not support ``kind``
        and ``order`` parameters that ``numpy.argpartition`` supports.

    .. seealso:: :func:`numpy.argpartition`

    """
    return a.argpartition(kth, axis=axis) 

def test_argequivalent(self):
        """ Test it translates from arg<func> to <func> """
        from numpy.random import rand
        a = rand(3, 4, 5)

        funcs = [
            (np.sort, np.argsort, dict()),
            (_add_keepdims(np.min), _add_keepdims(np.argmin), dict()),
            (_add_keepdims(np.max), _add_keepdims(np.argmax), dict()),
            (np.partition, np.argpartition, dict(kth=2)),
        ]

        for func, argfunc, kwargs in funcs:
            for axis in list(range(a.ndim)) + [None]:
                a_func = func(a, axis=axis, **kwargs)
                ai_func = argfunc(a, axis=axis, **kwargs)
                assert_equal(a_func, take_along_axis(a, ai_func, axis=axis)) 

def merge_outputs(self, detections):
        results = {}
        for i in range(1, self.num_classes + 1):
            results[i] = np.concatenate([detection[i] for detection in detections], axis=0).astype(np.float32)
            if len(self.scales) > 1 or self.opt.nms:
                soft_nms(results[i], Nt=0.5, method=2)

        scores = np.hstack([results[i][:,4] for i in range(1, self.num_classes + 1)])

        if len(scores) > self.max_per_image:
            kth = len(scores) - self.max_per_image
            thresh = np.partition(scores, kth)[kth]
            for i in range(1, self.num_classes + 1):
                keep_inds = (results[i][:, 4] >= thresh)
                results[i] = results[i][keep_inds]
        return results 

def _proba_margin(proba: np.ndarray) -> np.ndarray:
    """
    Calculates the margin of the prediction probabilities.

    Args:
        proba: Prediction probabilities.

    Returns:
        Margin of the prediction probabilities.
    """

    if proba.shape[1] == 1:
        return np.zeros(shape=len(proba))

    part = np.partition(-proba, 1, axis=1)
    margin = - part[:, 0] + part[:, 1]

    return margin 

def classifier_margin(classifier: BaseEstimator, X: modALinput, **predict_proba_kwargs) -> np.ndarray:
    """
    Classification margin uncertainty of the classifier for the provided samples. This uncertainty measure takes the
    first and second most likely predictions and takes the difference of their probabilities, which is the margin.

    Args:
        classifier: The classifier for which the prediction margin is to be measured.
        X: The samples for which the prediction margin of classification is to be measured.
        **predict_proba_kwargs: Keyword arguments to be passed for the :meth:`predict_proba` of the classifier.

    Returns:
        Margin uncertainty, which is the difference of the probabilities of first and second most likely predictions.
    """
    try:
        classwise_uncertainty = classifier.predict_proba(X, **predict_proba_kwargs)
    except NotFittedError:
        return np.zeros(shape=(X.shape[0], ))

    if classwise_uncertainty.shape[1] == 1:
        return np.zeros(shape=(classwise_uncertainty.shape[0],))

    part = np.partition(-classwise_uncertainty, 1, axis=1)
    margin = - part[:, 0] + part[:, 1]

    return margin 

def test_partition_cdtype(self):
        d = array([('Galahad', 1.7, 38), ('Arthur', 1.8, 41),
                   ('Lancelot', 1.9, 38)],
                  dtype=[('name', '|S10'), ('height', '<f8'), ('age', '<i4')])

        tgt = np.sort(d, order=['age', 'height'])
        assert_array_equal(np.partition(d, range(d.size),
                                        order=['age', 'height']),
                           tgt)
        assert_array_equal(d[np.argpartition(d, range(d.size),
                                             order=['age', 'height'])],
                           tgt)
        for k in range(d.size):
            assert_equal(np.partition(d, k, order=['age', 'height'])[k],
                        tgt[k])
            assert_equal(d[np.argpartition(d, k, order=['age', 'height'])][k],
                         tgt[k])

        d = array(['Galahad', 'Arthur', 'zebra', 'Lancelot'])
        tgt = np.sort(d)
        assert_array_equal(np.partition(d, range(d.size)), tgt)
        for k in range(d.size):
            assert_equal(np.partition(d, k)[k], tgt[k])
            assert_equal(d[np.argpartition(d, k)][k], tgt[k]) 

def merge_outputs(self, detections):
    results = {}
    for j in range(1, self.num_classes + 1):
      results[j] = np.concatenate(
        [detection[j] for detection in detections], axis=0).astype(np.float32)
      if len(self.scales) > 1 or self.opt.nms:
         soft_nms(results[j], Nt=0.5, method=2)
    scores = np.hstack(
      [results[j][:, 4] for j in range(1, self.num_classes + 1)])
    if len(scores) > self.max_per_image:
      kth = len(scores) - self.max_per_image
      thresh = np.partition(scores, kth)[kth]
      for j in range(1, self.num_classes + 1):
        keep_inds = (results[j][:, 4] >= thresh)
        results[j] = results[j][keep_inds]
    return results 

def merge_outputs(self, detections):
    results = {}
    for j in range(1, self.num_classes + 1):
      results[j] = np.concatenate(
        [detection[j] for detection in detections], axis=0).astype(np.float32)
      if len(self.scales) > 1 or self.opt.nms:
         soft_nms(results[j], Nt=0.5, method=2)
    scores = np.hstack(
      [results[j][:, 4] for j in range(1, self.num_classes + 1)])
    if len(scores) > self.max_per_image:
      kth = len(scores) - self.max_per_image
      thresh = np.partition(scores, kth)[kth]
      for j in range(1, self.num_classes + 1):
        keep_inds = (results[j][:, 4] >= thresh)
        results[j] = results[j][keep_inds]
    return results 

def merge_outputs(detections, num_classes):
#     print(detections)
    results = {}
    max_per_image = 100
    for j in range(1, num_classes + 1):
        results[j] = np.concatenate(
            [detection[j] for detection in detections], axis=0).astype(np.float32)
#         if len(self.scales) > 1 or self.opt.nms:
        results[j] = soft_nms(results[j], Nt=0.5, method=2, threshold=0.01)
#         print(results)
    scores = np.hstack([results[j][:, 4] for j in range(1, num_classes + 1)])

    if len(scores) > max_per_image:
        kth = len(scores) - max_per_image
        thresh = np.partition(scores, kth)[kth]
        for j in range(1, num_classes + 1):
            keep_inds = (results[j][:, 4] >= thresh)
            results[j] = results[j][keep_inds]
#     print("after merge out\n", results)
    return results2coco_boxes(results, num_classes) 

def merge_outputs(detections, num_classes):
#     print(detections)
    results = {}
    max_per_image = 100
    for j in range(1, num_classes + 1):
        results[j] = np.concatenate(
            [detection[j] for detection in detections], axis=0).astype(np.float32)
#         if len(self.scales) > 1 or self.opt.nms:
        results[j] = soft_nms(results[j], Nt=0.5, method=2, threshold=0.01)
#         print(results)
    scores = np.hstack([results[j][:, 4] for j in range(1, num_classes + 1)])

    if len(scores) > max_per_image:
        kth = len(scores) - max_per_image
        thresh = np.partition(scores, kth)[kth]
        for j in range(1, num_classes + 1):
            keep_inds = (results[j][:, 4] >= thresh)
            results[j] = results[j][keep_inds]
#     print("after merge out\n", results)
    return results2coco_boxes(results, num_classes) 

def merge_outputs(detections, num_classes):
#     print(detections)
    results = {}
    max_per_image = 100
    for j in range(1, num_classes + 1):
        results[j] = np.concatenate(
            [detection[j] for detection in detections], axis=0).astype(np.float32)
#         if len(self.scales) > 1 or self.opt.nms:
        results[j] = soft_nms(results[j], Nt=0.5, method=2, threshold=0.01)
#         print(results)
    scores = np.hstack([results[j][:, 4] for j in range(1, num_classes + 1)])

    if len(scores) > max_per_image:
        kth = len(scores) - max_per_image
        thresh = np.partition(scores, kth)[kth]
        for j in range(1, num_classes + 1):
            keep_inds = (results[j][:, 4] >= thresh)
            results[j] = results[j][keep_inds]
#     print("after merge out\n", results)
    return results2coco_boxes(results, num_classes) 

def merge_outputs(detections, num_classes):
#     print(detections)
    results = {}
    max_per_image = 100
    for j in range(1, num_classes + 1):
        results[j] = np.concatenate(
            [detection[j] for detection in detections], axis=0).astype(np.float32)
#         if len(self.scales) > 1 or self.opt.nms:
        results[j] = soft_nms(results[j], Nt=0.5, method=2, threshold=0.01)
#         print(results)
    scores = np.hstack([results[j][:, 4] for j in range(1, num_classes + 1)])

    if len(scores) > max_per_image:
        kth = len(scores) - max_per_image
        thresh = np.partition(scores, kth)[kth]
        for j in range(1, num_classes + 1):
            keep_inds = (results[j][:, 4] >= thresh)
            results[j] = results[j][keep_inds]
#     print("after merge out\n", results)
    return results2coco_boxes(results, num_classes) 

def merge_outputs(detections):
#     print(detections)
    results = {}
    max_per_image = 100
    for j in range(1,  num_classes + 1):
        results[j] = np.concatenate(
            [detection[j] for detection in detections], axis=0).astype(np.float32)
#         if len(self.scales) > 1 or self.opt.nms:
        results[j] = soft_nms(results[j], Nt=0.5, method=2, threshold=0.001)
#         print(results)
    scores = np.hstack(
      [results[j][:, 4] for j in range(1, num_classes + 1)])
    if len(scores) > max_per_image:
        kth = len(scores) - max_per_image
        thresh = np.partition(scores, kth)[kth]
        for j in range(1, num_classes + 1):
            keep_inds = (results[j][:, 4] >= thresh)
            results[j] = results[j][keep_inds]
#     print("after merge out\n", results)
    return results2coco_boxes(results) 

def test_argequivalent(self):
        """ Test it translates from arg<func> to <func> """
        from numpy.random import rand
        a = rand(3, 4, 5)

        funcs = [
            (np.sort, np.argsort, dict()),
            (_add_keepdims(np.min), _add_keepdims(np.argmin), dict()),
            (_add_keepdims(np.max), _add_keepdims(np.argmax), dict()),
            (np.partition, np.argpartition, dict(kth=2)),
        ]

        for func, argfunc, kwargs in funcs:
            for axis in list(range(a.ndim)) + [None]:
                a_func = func(a, axis=axis, **kwargs)
                ai_func = argfunc(a, axis=axis, **kwargs)
                assert_equal(a_func, take_along_axis(a, ai_func, axis=axis)) 

def test_argequivalent(self):
        """ Test it translates from arg<func> to <func> """
        from numpy.random import rand
        a = rand(3, 4, 5)

        funcs = [
            (np.sort, np.argsort, dict()),
            (_add_keepdims(np.min), _add_keepdims(np.argmin), dict()),
            (_add_keepdims(np.max), _add_keepdims(np.argmax), dict()),
            (np.partition, np.argpartition, dict(kth=2)),
        ]

        for func, argfunc, kwargs in funcs:
            for axis in list(range(a.ndim)) + [None]:
                a_func = func(a, axis=axis, **kwargs)
                ai_func = argfunc(a, axis=axis, **kwargs)
                assert_equal(a_func, take_along_axis(a, ai_func, axis=axis)) 

def test_argequivalent(self):
        """ Test it translates from arg<func> to <func> """
        from numpy.random import rand
        a = rand(3, 4, 5)

        funcs = [
            (np.sort, np.argsort, dict()),
            (_add_keepdims(np.min), _add_keepdims(np.argmin), dict()),
            (_add_keepdims(np.max), _add_keepdims(np.argmax), dict()),
            (np.partition, np.argpartition, dict(kth=2)),
        ]

        for func, argfunc, kwargs in funcs:
            for axis in list(range(a.ndim)) + [None]:
                a_func = func(a, axis=axis, **kwargs)
                ai_func = argfunc(a, axis=axis, **kwargs)
                assert_equal(a_func, take_along_axis(a, ai_func, axis=axis)) 

def merge_outputs(self, detections):
    results = {}
    for j in range(1, self.num_classes + 1):
      results[j] = np.concatenate(
        [detection[j] for detection in detections], axis=0).astype(np.float32)
      if len(self.scales) > 1 or self.opt.nms:
         soft_nms(results[j], Nt=0.5, method=2)
    scores = np.hstack(
      [results[j][:, 4] for j in range(1, self.num_classes + 1)])
    if len(scores) > self.max_per_image:
      kth = len(scores) - self.max_per_image
      thresh = np.partition(scores, kth)[kth]
      for j in range(1, self.num_classes + 1):
        keep_inds = (results[j][:, 4] >= thresh)
        results[j] = results[j][keep_inds]
    return results 

def find_threshold(self, np_predict, np_target):
        # downsample 1/8
        factor = self.factor
        predict = nd.zoom(np_predict, (1.0, 1.0, 1.0/factor, 1.0/factor), order=1)
        target = nd.zoom(np_target, (1.0, 1.0/factor, 1.0/factor), order=0)

        n, c, h, w = predict.shape
        min_kept = self.min_kept // (factor*factor) #int(self.min_kept_ratio * n * h * w)

        input_label = target.ravel().astype(np.int32)
        input_prob = np.rollaxis(predict, 1).reshape((c, -1))

        valid_flag = input_label != self.ignore_label
        valid_inds = np.where(valid_flag)[0]
        label = input_label[valid_flag]
        num_valid = valid_flag.sum()
        if min_kept >= num_valid:
            threshold = 1.0
        elif num_valid > 0:
            prob = input_prob[:,valid_flag]
            pred = prob[label, np.arange(len(label), dtype=np.int32)]
            threshold = self.thresh
            if min_kept > 0:
                k_th = min(len(pred), min_kept)-1
                new_array = np.partition(pred, k_th)
                new_threshold = new_array[k_th]
                if new_threshold > self.thresh:
                    threshold = new_threshold
        return threshold 

def test_partition_matrix_none():
    # gh-4301
    # 2018-04-29: moved here from core.tests.test_multiarray
    a = np.matrix([[2, 1, 0]])
    actual = np.partition(a, 1, axis=None)
    expected = np.matrix([[0, 1, 2]])
    assert_equal(actual, expected)
    assert_(type(expected) is np.matrix) 

def testPartitionIndicesExecution(self):
        # only 1 chunk when axis = -1
        raw = np.random.rand(100, 10)
        x = tensor(raw, chunk_size=10)

        kth = [2, 5, 9]
        r = partition(x, kth, return_index=True)

        pr, pi = self.executor.execute_tensors(r)
        np.testing.assert_array_equal(pr, np.take_along_axis(raw, pi, axis=-1))
        np.testing.assert_array_equal(np.sort(raw)[:, kth], pr[:, kth])

        x = tensor(raw, chunk_size=(22, 4))

        r = partition(x, kth, return_index=True)

        pr, pi = self.executor.execute_tensors(r)
        np.testing.assert_array_equal(pr, np.take_along_axis(raw, pi, axis=-1))
        np.testing.assert_array_equal(np.sort(raw)[:, kth], pr[:, kth])

        raw = np.random.rand(100)

        x = tensor(raw, chunk_size=23)

        r = partition(x, kth, axis=0, return_index=True)

        pr, pi = self.executor.execute_tensors(r)
        np.testing.assert_array_equal(pr, np.take_along_axis(raw, pi, axis=-1))
        np.testing.assert_array_equal(np.sort(raw)[kth], pr[kth]) 

def find_threshold(self, np_predict, np_target):
        # downsample 1/8
        factor = self.factor
        predict = nd.zoom(np_predict, (1.0, 1.0, 1.0/factor, 1.0/factor), order=1)
        target = nd.zoom(np_target, (1.0, 1.0/factor, 1.0/factor), order=0)

        n, c, h, w = predict.shape
        min_kept = self.min_kept // (factor*factor) #int(self.min_kept_ratio * n * h * w)

        input_label = target.ravel().astype(np.int32)
        input_prob = np.rollaxis(predict, 1).reshape((c, -1))

        valid_flag = input_label != self.ignore_label
        valid_inds = np.where(valid_flag)[0]
        label = input_label[valid_flag]
        num_valid = valid_flag.sum()
        if min_kept >= num_valid:
            threshold = 1.0
        elif num_valid > 0:
            prob = input_prob[:,valid_flag]
            pred = prob[label, np.arange(len(label), dtype=np.int32)]
            threshold = self.thresh
            if min_kept > 0:
                k_th = min(len(pred), min_kept)-1
                new_array = np.partition(pred, k_th)
                new_threshold = new_array[k_th]
                if new_threshold > self.thresh:
                    threshold = new_threshold
        return threshold 

def test_partition_matrix_none():
    # gh-4301
    # 2018-04-29: moved here from core.tests.test_multiarray
    a = np.matrix([[2, 1, 0]])
    actual = np.partition(a, 1, axis=None)
    expected = np.matrix([[0, 1, 2]])
    assert_equal(actual, expected)
    assert_(type(expected) is np.matrix) 

def top_proportions_sparse_csr(data, indptr, n):
    values = np.zeros((indptr.size - 1, n), dtype=np.float64)
    for i in numba.prange(indptr.size - 1):
        start, end = indptr[i], indptr[i + 1]
        vec = np.zeros(n, dtype=np.float64)
        if end - start <= n:
            vec[:end - start] = data[start:end]
            total = vec.sum()
        else:
            vec[:] = -(np.partition(-data[start:end], n - 1)[:n])
            total = (data[start:end]).sum()  # Is this not just vec.sum()?
        vec[::-1].sort()
        values[i, :] = vec.cumsum() / total
    return values 

def top_segment_proportions_dense(
    mtx: Union[np.array, spmatrix], ns: Collection[int]
) -> np.ndarray:
    # Currently ns is considered to be 1 indexed
    ns = np.sort(ns)
    sums = mtx.sum(axis=1)
    partitioned = np.apply_along_axis(np.partition, 1, mtx, mtx.shape[1] - ns)[:, ::-1][:, :ns[-1]]
    values = np.zeros((mtx.shape[0], len(ns)))
    acc = np.zeros((mtx.shape[0]))
    prev = 0
    for j, n in enumerate(ns):
        acc += partitioned[:, prev:n].sum(axis=1)
        values[:, j] = acc
        prev = n
    return values / sums[:, None]