scikit-learn/sklearn/utils/multiclass.py

425 lines
14 KiB
Python

# 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
import warnings
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
def _unique_multiclass(y):
if hasattr(y, '__array__'):
return np.unique(np.asarray(y))
else:
return set(y)
def _unique_sequence_of_sequence(y):
if hasattr(y, '__array__'):
y = np.asarray(y)
return set(chain.from_iterable(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-sequences': _unique_sequence_of_sequence,
'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: %r" % 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_label_indicator_matrix(y):
""" Check if ``y`` is in the label indicator matrix format (multilabel).
Parameters
----------
y : numpy array of shape [n_samples] or sequence of sequences
Target values. In the multilabel case the nested sequences can
have variable lengths.
Returns
-------
out : bool,
Return ``True``, if ``y`` is in a label indicator matrix format,
else ``False``.
Examples
--------
>>> import numpy as np
>>> from sklearn.utils.multiclass import is_label_indicator_matrix
>>> is_label_indicator_matrix([0, 1, 0, 1])
False
>>> is_label_indicator_matrix([[1], [0, 2], []])
False
>>> is_label_indicator_matrix(np.array([[1, 0], [0, 0]]))
True
>>> is_label_indicator_matrix(np.array([[1], [0], [0]]))
False
>>> is_label_indicator_matrix(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.ptp(y.data) == 0 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 is_sequence_of_sequences(y):
""" Check if ``y`` is in the sequence of sequences format (multilabel).
This format is DEPRECATED.
Parameters
----------
y : sequence or array.
Returns
-------
out : bool,
Return ``True``, if ``y`` is a sequence of sequences else ``False``.
"""
# the explicit check for ndarray is for forward compatibility; future
# versions of Numpy might want to register ndarray as a Sequence
try:
if hasattr(y, '__array__'):
y = np.asarray(y)
out = (not hasattr(y[0], '__array__') and isinstance(y[0], Sequence)
and not isinstance(y[0], string_types))
except (IndexError, TypeError):
return False
if out:
warnings.warn('Direct support for sequence of sequences multilabel '
'representation will be unavailable from version 0.17. '
'Use sklearn.preprocessing.MultiLabelBinarizer to '
'convert to a label indicator representation.',
DeprecationWarning)
return out
def is_multilabel(y):
""" Check if ``y`` is in a multilabel format.
Parameters
----------
y : numpy array of shape [n_samples] or sequence of sequences
Target values. In the multilabel case the nested sequences can
have variable lengths.
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(np.array([[1, 0], [0, 0]]))
True
>>> is_multilabel(np.array([[1], [0], [0]]))
False
>>> is_multilabel(np.array([[1, 0, 0]]))
True
"""
return is_label_indicator_matrix(y) or is_sequence_of_sequences(y)
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-sequences': `y` is a sequence of sequences, a 1d
array-like of objects that are sequences of labels.
* '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, 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])
'multiclass'
>>> type_of_target(['a', 'b', 'c'])
'multiclass'
>>> type_of_target(np.array([[1, 2], [3, 1]]))
'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_sequence_of_sequences(y):
return 'multilabel-sequences'
elif is_label_indicator_matrix(y):
return 'multilabel-indicator'
try:
y = np.asarray(y)
except ValueError:
# known to fail in numpy 1.3 for array of arrays
return 'unknown'
if y.ndim > 2 or (y.dtype == object and len(y) and
not isinstance(y.flat[0], string_types)):
return 'unknown'
if y.ndim == 2 and y.shape[1] == 0:
return 'unknown'
elif y.ndim == 2 and y.shape[1] > 1:
suffix = '-multioutput'
else:
# column vector or 1d
suffix = ''
# check float and contains non-integer float values:
if y.dtype.kind == 'f' and np.any(y != y.astype(int)):
return 'continuous' + suffix
if len(np.unique(y)) <= 2:
assert not suffix, "2d binary array-like should be multilabel"
return 'binary'
else:
return 'multiclass' + suffix
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 np.all(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.
Return
------
classes : list of size n_outputs of arrays of size (n_classes,)
List of classes for each column.
n_classes : list of integrs 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 = np.bincount(y_k, weights=nz_samp_weight)
# An explicit zero was found, combine its wieght with the wieght
# of the implicit zeros
if 0 in classes_k:
class_prior_k[classes_k == 0] += zeros_samp_weight_sum
# If an there is an implict 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 = np.bincount(y_k, weights=sample_weight)
class_prior.append(class_prior_k / class_prior_k.sum())
return (classes, n_classes, class_prior)