/sklearn/utils/multiclass.py

# Author: Arnaud Joly, Joel Nothman, Hamzeh Alsalhi
#
# License: BSD 3 clause
"""
Multi-class / multi-label utility function
==========================================

"""
from __future__ import division
from collections import Sequence
from itertools import chain

from scipy.sparse import issparse
from scipy.sparse.base import spmatrix
from scipy.sparse import dok_matrix
from scipy.sparse import lil_matrix

import numpy as np

from ..externals.six import string_types
from .validation import check_array
from ..utils.fixes import bincount
from ..utils.fixes import array_equal


def _unique_multiclass(y):
    if hasattr(y, '__array__'):
        return np.unique(np.asarray(y))
    else:
        return set(y)


def _unique_indicator(y):
    return np.arange(check_array(y, ['csr', 'csc', 'coo']).shape[1])


_FN_UNIQUE_LABELS = {
    'binary': _unique_multiclass,
    'multiclass': _unique_multiclass,
    'multilabel-indicator': _unique_indicator,
}


def unique_labels(*ys):
    """Extract an ordered array of unique labels

    We don't allow:
        - mix of multilabel and multiclass (single label) targets
        - mix of label indicator matrix and anything else,
          because there are no explicit labels)
        - mix of label indicator matrices of different sizes
        - mix of string and integer labels

    At the moment, we also don't allow "multiclass-multioutput" input type.

    Parameters
    ----------
    *ys : array-likes,

    Returns
    -------
    out : numpy array of shape [n_unique_labels]
        An ordered array of unique labels.

    Examples
    --------
    >>> from sklearn.utils.multiclass import unique_labels
    >>> unique_labels([3, 5, 5, 5, 7, 7])
    array([3, 5, 7])
    >>> unique_labels([1, 2, 3, 4], [2, 2, 3, 4])
    array([1, 2, 3, 4])
    >>> unique_labels([1, 2, 10], [5, 11])
    array([ 1,  2,  5, 10, 11])
    """
    if not ys:
        raise ValueError('No argument has been passed.')
    # Check that we don't mix label format

    ys_types = set(type_of_target(x) for x in ys)
    if ys_types == set(["binary", "multiclass"]):
        ys_types = set(["multiclass"])

    if len(ys_types) > 1:
        raise ValueError("Mix type of y not allowed, got types %s" % ys_types)

    label_type = ys_types.pop()

    # Check consistency for the indicator format
    if (label_type == "multilabel-indicator" and
            len(set(check_array(y, ['csr', 'csc', 'coo']).shape[1]
                    for y in ys)) > 1):
        raise ValueError("Multi-label binary indicator input with "
                         "different numbers of labels")

    # Get the unique set of labels
    _unique_labels = _FN_UNIQUE_LABELS.get(label_type, None)
    if not _unique_labels:
        raise ValueError("Unknown label type: %s" % repr(ys))

    ys_labels = set(chain.from_iterable(_unique_labels(y) for y in ys))

    # Check that we don't mix string type with number type
    if (len(set(isinstance(label, string_types) for label in ys_labels)) > 1):
        raise ValueError("Mix of label input types (string and number)")

    return np.array(sorted(ys_labels))


def _is_integral_float(y):
    return y.dtype.kind == 'f' and np.all(y.astype(int) == y)


def is_multilabel(y):
    """ Check if ``y`` is in a multilabel format.

    Parameters
    ----------
    y : numpy array of shape [n_samples]
        Target values.

    Returns
    -------
    out : bool,
        Return ``True``, if ``y`` is in a multilabel format, else ```False``.

    Examples
    --------
    >>> import numpy as np
    >>> from sklearn.utils.multiclass import is_multilabel
    >>> is_multilabel([0, 1, 0, 1])
    False
    >>> is_multilabel([[1], [0, 2], []])
    False
    >>> is_multilabel(np.array([[1, 0], [0, 0]]))
    True
    >>> is_multilabel(np.array([[1], [0], [0]]))
    False
    >>> is_multilabel(np.array([[1, 0, 0]]))
    True
    """
    if hasattr(y, '__array__'):
        y = np.asarray(y)
    if not (hasattr(y, "shape") and y.ndim == 2 and y.shape[1] > 1):
        return False

    if issparse(y):
        if isinstance(y, (dok_matrix, lil_matrix)):
            y = y.tocsr()
        return (len(y.data) == 0 or np.unique(y.data).size == 1 and
                (y.dtype.kind in 'biu' or  # bool, int, uint
                 _is_integral_float(np.unique(y.data))))
    else:
        labels = np.unique(y)

        return len(labels) < 3 and (y.dtype.kind in 'biu' or  # bool, int, uint
                                    _is_integral_float(labels))

def check_classification_targets(y):
    """Ensure that target y is of a non-regression type.

    Only the following target types (as defined in type_of_target) are allowed:
        'binary', 'multiclass', 'multiclass-multioutput', 
        'multilabel-indicator', 'multilabel-sequences'

    Parameters
    ----------
    y : array-like
    """
    y_type = type_of_target(y)
    if y_type not in ['binary', 'multiclass', 'multiclass-multioutput', 
            'multilabel-indicator', 'multilabel-sequences']:
        raise ValueError("Unknown label type: %r" % y_type)



def type_of_target(y):
    """Determine the type of data indicated by target `y`

    Parameters
    ----------
    y : array-like

    Returns
    -------
    target_type : string
        One of:
        * 'continuous': `y` is an array-like of floats that are not all
          integers, and is 1d or a column vector.
        * 'continuous-multioutput': `y` is a 2d array of floats that are
          not all integers, and both dimensions are of size > 1.
        * 'binary': `y` contains <= 2 discrete values and is 1d or a column
          vector.
        * 'multiclass': `y` contains more than two discrete values, is not a
          sequence of sequences, and is 1d or a column vector.
        * 'multiclass-multioutput': `y` is a 2d array that contains more
          than two discrete values, is not a sequence of sequences, and both
          dimensions are of size > 1.
        * 'multilabel-indicator': `y` is a label indicator matrix, an array
          of two dimensions with at least two columns, and at most 2 unique
          values.
        * 'unknown': `y` is array-like but none of the above, such as a 3d
          array, sequence of sequences, or an array of non-sequence objects.

    Examples
    --------
    >>> import numpy as np
    >>> type_of_target([0.1, 0.6])
    'continuous'
    >>> type_of_target([1, -1, -1, 1])
    'binary'
    >>> type_of_target(['a', 'b', 'a'])
    'binary'
    >>> type_of_target([1.0, 2.0])
    'binary'
    >>> type_of_target([1, 0, 2])
    'multiclass'
    >>> type_of_target([1.0, 0.0, 3.0])
    'multiclass'
    >>> type_of_target(['a', 'b', 'c'])
    'multiclass'
    >>> type_of_target(np.array([[1, 2], [3, 1]]))
    'multiclass-multioutput'
    >>> type_of_target([[1, 2]])
    'multiclass-multioutput'
    >>> type_of_target(np.array([[1.5, 2.0], [3.0, 1.6]]))
    'continuous-multioutput'
    >>> type_of_target(np.array([[0, 1], [1, 1]]))
    'multilabel-indicator'
    """
    valid = ((isinstance(y, (Sequence, spmatrix)) or hasattr(y, '__array__'))
             and not isinstance(y, string_types))

    if not valid:
        raise ValueError('Expected array-like (array or non-string sequence), '
                         'got %r' % y)

    if is_multilabel(y):
        return 'multilabel-indicator'

    try:
        y = np.asarray(y)
    except ValueError:
        # Known to fail in numpy 1.3 for array of arrays
        return 'unknown'

    # The old sequence of sequences format
    try:
        if (not hasattr(y[0], '__array__') and isinstance(y[0], Sequence)
                and not isinstance(y[0], string_types)):
            raise ValueError('You appear to be using a legacy multi-label data'
                             ' representation. Sequence of sequences are no'
                             ' longer supported; use a binary array or sparse'
                             ' matrix instead.')
    except IndexError:
        pass

    # Invalid inputs
    if y.ndim > 2 or (y.dtype == object and len(y) and
                      not isinstance(y.flat[0], string_types)):
        return 'unknown'  # [[[1, 2]]] or [obj_1] and not ["label_1"]

    if y.ndim == 2 and y.shape[1] == 0:
        return 'unknown'  # [[]]

    if y.ndim == 2 and y.shape[1] > 1:
        suffix = "-multioutput"  # [[1, 2], [1, 2]]
    else:
        suffix = ""  # [1, 2, 3] or [[1], [2], [3]]

    # check float and contains non-integer float values
    if y.dtype.kind == 'f' and np.any(y != y.astype(int)):
        # [.1, .2, 3] or [[.1, .2, 3]] or [[1., .2]] and not [1., 2., 3.]
        return 'continuous' + suffix

    if (len(np.unique(y)) > 2) or (y.ndim >= 2 and len(y[0]) > 1):
        return 'multiclass' + suffix  # [1, 2, 3] or [[1., 2., 3]] or [[1, 2]]
    else:
        return 'binary'  # [1, 2] or [["a"], ["b"]]


def _check_partial_fit_first_call(clf, classes=None):
    """Private helper function for factorizing common classes param logic

    Estimators that implement the ``partial_fit`` API need to be provided with
    the list of possible classes at the first call to partial_fit.

    Subsequent calls to partial_fit should check that ``classes`` is still
    consistent with a previous value of ``clf.classes_`` when provided.

    This function returns True if it detects that this was the first call to
    ``partial_fit`` on ``clf``. In that case the ``classes_`` attribute is also
    set on ``clf``.

    """
    if getattr(clf, 'classes_', None) is None and classes is None:
        raise ValueError("classes must be passed on the first call "
                         "to partial_fit.")

    elif classes is not None:
        if getattr(clf, 'classes_', None) is not None:
            if not array_equal(clf.classes_, unique_labels(classes)):
                raise ValueError(
                    "`classes=%r` is not the same as on last call "
                    "to partial_fit, was: %r" % (classes, clf.classes_))

        else:
            # This is the first call to partial_fit
            clf.classes_ = unique_labels(classes)
            return True

    # classes is None and clf.classes_ has already previously been set:
    # nothing to do
    return False


def class_distribution(y, sample_weight=None):
    """Compute class priors from multioutput-multiclass target data

    Parameters
    ----------
    y : array like or sparse matrix of size (n_samples, n_outputs)
        The labels for each example.

    sample_weight : array-like of shape = (n_samples,), optional
        Sample weights.

    Returns
    -------
    classes : list of size n_outputs of arrays of size (n_classes,)
        List of classes for each column.

    n_classes : list of integers of size n_outputs
        Number of classes in each column

    class_prior : list of size n_outputs of arrays of size (n_classes,)
        Class distribution of each column.

    """
    classes = []
    n_classes = []
    class_prior = []

    n_samples, n_outputs = y.shape

    if issparse(y):
        y = y.tocsc()
        y_nnz = np.diff(y.indptr)

        for k in range(n_outputs):
            col_nonzero = y.indices[y.indptr[k]:y.indptr[k + 1]]
            # separate sample weights for zero and non-zero elements
            if sample_weight is not None:
                nz_samp_weight = np.asarray(sample_weight)[col_nonzero]
                zeros_samp_weight_sum = (np.sum(sample_weight) -
                                         np.sum(nz_samp_weight))
            else:
                nz_samp_weight = None
                zeros_samp_weight_sum = y.shape[0] - y_nnz[k]

            classes_k, y_k = np.unique(y.data[y.indptr[k]:y.indptr[k + 1]],
                                       return_inverse=True)
            class_prior_k = bincount(y_k, weights=nz_samp_weight)

            # An explicit zero was found, combine its weight with the weight
            # of the implicit zeros
            if 0 in classes_k:
                class_prior_k[classes_k == 0] += zeros_samp_weight_sum

            # If an there is an implicit zero and it is not in classes and
            # class_prior, make an entry for it
            if 0 not in classes_k and y_nnz[k] < y.shape[0]:
                classes_k = np.insert(classes_k, 0, 0)
                class_prior_k = np.insert(class_prior_k, 0,
                                          zeros_samp_weight_sum)

            classes.append(classes_k)
            n_classes.append(classes_k.shape[0])
            class_prior.append(class_prior_k / class_prior_k.sum())
    else:
        for k in range(n_outputs):
            classes_k, y_k = np.unique(y[:, k], return_inverse=True)
            classes.append(classes_k)
            n_classes.append(classes_k.shape[0])
            class_prior_k = bincount(y_k, weights=sample_weight)
            class_prior.append(class_prior_k / class_prior_k.sum())

    return (classes, n_classes, class_prior)