Source code for sklearn.utils.validation

"""Utilities for input validation"""

# Authors: Olivier Grisel
#          Gael Varoquaux
#          Andreas Mueller
#          Lars Buitinck
#          Alexandre Gramfort
#          Nicolas Tresegnie
# License: BSD 3 clause

import warnings
import numbers

import numpy as np
import scipy.sparse as sp

from ..externals import six
from ..utils.fixes import signature
from .deprecation import deprecated
from ..exceptions import DataConversionWarning as _DataConversionWarning
from ..exceptions import NonBLASDotWarning as _NonBLASDotWarning
from ..exceptions import NotFittedError as _NotFittedError


@deprecated("DataConversionWarning has been moved into the sklearn.exceptions"
            " module. It will not be available here from version 0.19")
class DataConversionWarning(_DataConversionWarning):
    pass


@deprecated("NonBLASDotWarning has been moved into the sklearn.exceptions"
            " module. It will not be available here from version 0.19")
class NonBLASDotWarning(_NonBLASDotWarning):
    pass


@deprecated("NotFittedError has been moved into the sklearn.exceptions module."
            " It will not be available here from version 0.19")
class NotFittedError(_NotFittedError):
    pass

FLOAT_DTYPES = (np.float64, np.float32, np.float16)

# Silenced by default to reduce verbosity. Turn on at runtime for
# performance profiling.
warnings.simplefilter('ignore', _NonBLASDotWarning)


def _assert_all_finite(X):
    """Like assert_all_finite, but only for ndarray."""
    X = np.asanyarray(X)
    # First try an O(n) time, O(1) space solution for the common case that
    # everything is finite; fall back to O(n) space np.isfinite to prevent
    # false positives from overflow in sum method.
    if (X.dtype.char in np.typecodes['AllFloat'] and not np.isfinite(X.sum())
            and not np.isfinite(X).all()):
        raise ValueError("Input contains NaN, infinity"
                         " or a value too large for %r." % X.dtype)


def assert_all_finite(X):
    """Throw a ValueError if X contains NaN or infinity.

    Input MUST be an np.ndarray instance or a scipy.sparse matrix."""
    _assert_all_finite(X.data if sp.issparse(X) else X)


def as_float_array(X, copy=True, force_all_finite=True):
    """Converts an array-like to an array of floats

    The new dtype will be np.float32 or np.float64, depending on the original
    type. The function can create a copy or modify the argument depending
    on the argument copy.

    Parameters
    ----------
    X : {array-like, sparse matrix}

    copy : bool, optional
        If True, a copy of X will be created. If False, a copy may still be
        returned if X's dtype is not a floating point type.

    force_all_finite : boolean (default=True)
        Whether to raise an error on np.inf and np.nan in X.

    Returns
    -------
    XT : {array, sparse matrix}
        An array of type np.float
    """
    if isinstance(X, np.matrix) or (not isinstance(X, np.ndarray)
                                    and not sp.issparse(X)):
        return check_array(X, ['csr', 'csc', 'coo'], dtype=np.float64,
                           copy=copy, force_all_finite=force_all_finite,
                           ensure_2d=False)
    elif sp.issparse(X) and X.dtype in [np.float32, np.float64]:
        return X.copy() if copy else X
    elif X.dtype in [np.float32, np.float64]:  # is numpy array
        return X.copy('F' if X.flags['F_CONTIGUOUS'] else 'C') if copy else X
    else:
        return X.astype(np.float32 if X.dtype == np.int32 else np.float64)


def _is_arraylike(x):
    """Returns whether the input is array-like"""
    return (hasattr(x, '__len__') or
            hasattr(x, 'shape') or
            hasattr(x, '__array__'))


def _num_samples(x):
    """Return number of samples in array-like x."""
    if hasattr(x, 'fit'):
        # Don't get num_samples from an ensembles length!
        raise TypeError('Expected sequence or array-like, got '
                        'estimator %s' % x)
    if not hasattr(x, '__len__') and not hasattr(x, 'shape'):
        if hasattr(x, '__array__'):
            x = np.asarray(x)
        else:
            raise TypeError("Expected sequence or array-like, got %s" %
                            type(x))
    if hasattr(x, 'shape'):
        if len(x.shape) == 0:
            raise TypeError("Singleton array %r cannot be considered"
                            " a valid collection." % x)
        return x.shape[0]
    else:
        return len(x)


def _shape_repr(shape):
    """Return a platform independent representation of an array shape

    Under Python 2, the `long` type introduces an 'L' suffix when using the
    default %r format for tuples of integers (typically used to store the shape
    of an array).

    Under Windows 64 bit (and Python 2), the `long` type is used by default
    in numpy shapes even when the integer dimensions are well below 32 bit.
    The platform specific type causes string messages or doctests to change
    from one platform to another which is not desirable.

    Under Python 3, there is no more `long` type so the `L` suffix is never
    introduced in string representation.

    >>> _shape_repr((1, 2))
    '(1, 2)'
    >>> one = 2 ** 64 / 2 ** 64  # force an upcast to `long` under Python 2
    >>> _shape_repr((one, 2 * one))
    '(1, 2)'
    >>> _shape_repr((1,))
    '(1,)'
    >>> _shape_repr(())
    '()'
    """
    if len(shape) == 0:
        return "()"
    joined = ", ".join("%d" % e for e in shape)
    if len(shape) == 1:
        # special notation for singleton tuples
        joined += ','
    return "(%s)" % joined


def check_consistent_length(*arrays):
    """Check that all arrays have consistent first dimensions.

    Checks whether all objects in arrays have the same shape or length.

    Parameters
    ----------
    *arrays : list or tuple of input objects.
        Objects that will be checked for consistent length.
    """

    lengths = [_num_samples(X) for X in arrays if X is not None]
    uniques = np.unique(lengths)
    if len(uniques) > 1:
        raise ValueError("Found input variables with inconsistent numbers of"
                         " samples: %r" % [int(l) for l in lengths])


def indexable(*iterables):
    """Make arrays indexable for cross-validation.

    Checks consistent length, passes through None, and ensures that everything
    can be indexed by converting sparse matrices to csr and converting
    non-interable objects to arrays.

    Parameters
    ----------
    *iterables : lists, dataframes, arrays, sparse matrices
        List of objects to ensure sliceability.
    """
    result = []
    for X in iterables:
        if sp.issparse(X):
            result.append(X.tocsr())
        elif hasattr(X, "__getitem__") or hasattr(X, "iloc"):
            result.append(X)
        elif X is None:
            result.append(X)
        else:
            result.append(np.array(X))
    check_consistent_length(*result)
    return result


def _ensure_sparse_format(spmatrix, accept_sparse, dtype, copy,
                          force_all_finite):
    """Convert a sparse matrix to a given format.

    Checks the sparse format of spmatrix and converts if necessary.

    Parameters
    ----------
    spmatrix : scipy sparse matrix
        Input to validate and convert.

    accept_sparse : string, list of string or None (default=None)
        String[s] representing allowed sparse matrix formats ('csc',
        'csr', 'coo', 'dok', 'bsr', 'lil', 'dia'). None means that sparse
        matrix input will raise an error.  If the input is sparse but not in
        the allowed format, it will be converted to the first listed format.

    dtype : string, type or None (default=none)
        Data type of result. If None, the dtype of the input is preserved.

    copy : boolean (default=False)
        Whether a forced copy will be triggered. If copy=False, a copy might
        be triggered by a conversion.

    force_all_finite : boolean (default=True)
        Whether to raise an error on np.inf and np.nan in X.

    Returns
    -------
    spmatrix_converted : scipy sparse matrix.
        Matrix that is ensured to have an allowed type.
    """
    if accept_sparse in [None, False]:
        raise TypeError('A sparse matrix was passed, but dense '
                        'data is required. Use X.toarray() to '
                        'convert to a dense numpy array.')
    if dtype is None:
        dtype = spmatrix.dtype

    changed_format = False
    if (isinstance(accept_sparse, (list, tuple))
            and spmatrix.format not in accept_sparse):
        # create new with correct sparse
        spmatrix = spmatrix.asformat(accept_sparse[0])
        changed_format = True

    if dtype != spmatrix.dtype:
        # convert dtype
        spmatrix = spmatrix.astype(dtype)
    elif copy and not changed_format:
        # force copy
        spmatrix = spmatrix.copy()

    if force_all_finite:
        if not hasattr(spmatrix, "data"):
            warnings.warn("Can't check %s sparse matrix for nan or inf."
                          % spmatrix.format)
        else:
            _assert_all_finite(spmatrix.data)
    return spmatrix


[docs]def check_array(array, accept_sparse=None, dtype="numeric", order=None, copy=False, force_all_finite=True, ensure_2d=True, allow_nd=False, ensure_min_samples=1, ensure_min_features=1, warn_on_dtype=False, estimator=None): """Input validation on an array, list, sparse matrix or similar. By default, the input is converted to an at least 2D numpy array. If the dtype of the array is object, attempt converting to float, raising on failure. Parameters ---------- array : object Input object to check / convert. accept_sparse : string, list of string or None (default=None) String[s] representing allowed sparse matrix formats, such as 'csc', 'csr', etc. None means that sparse matrix input will raise an error. If the input is sparse but not in the allowed format, it will be converted to the first listed format. dtype : string, type, list of types or None (default="numeric") Data type of result. If None, the dtype of the input is preserved. If "numeric", dtype is preserved unless array.dtype is object. If dtype is a list of types, conversion on the first type is only performed if the dtype of the input is not in the list. order : 'F', 'C' or None (default=None) Whether an array will be forced to be fortran or c-style. When order is None (default), then if copy=False, nothing is ensured about the memory layout of the output array; otherwise (copy=True) the memory layout of the returned array is kept as close as possible to the original array. copy : boolean (default=False) Whether a forced copy will be triggered. If copy=False, a copy might be triggered by a conversion. force_all_finite : boolean (default=True) Whether to raise an error on np.inf and np.nan in X. ensure_2d : boolean (default=True) Whether to make X at least 2d. allow_nd : boolean (default=False) Whether to allow X.ndim > 2. ensure_min_samples : int (default=1) Make sure that the array has a minimum number of samples in its first axis (rows for a 2D array). Setting to 0 disables this check. ensure_min_features : int (default=1) Make sure that the 2D array has some minimum number of features (columns). The default value of 1 rejects empty datasets. This check is only enforced when the input data has effectively 2 dimensions or is originally 1D and ``ensure_2d`` is True. Setting to 0 disables this check. warn_on_dtype : boolean (default=False) Raise DataConversionWarning if the dtype of the input data structure does not match the requested dtype, causing a memory copy. estimator : str or estimator instance (default=None) If passed, include the name of the estimator in warning messages. Returns ------- X_converted : object The converted and validated X. """ if isinstance(accept_sparse, str): accept_sparse = [accept_sparse] # store whether originally we wanted numeric dtype dtype_numeric = dtype == "numeric" dtype_orig = getattr(array, "dtype", None) if not hasattr(dtype_orig, 'kind'): # not a data type (e.g. a column named dtype in a pandas DataFrame) dtype_orig = None if dtype_numeric: if dtype_orig is not None and dtype_orig.kind == "O": # if input is object, convert to float. dtype = np.float64 else: dtype = None if isinstance(dtype, (list, tuple)): if dtype_orig is not None and dtype_orig in dtype: # no dtype conversion required dtype = None else: # dtype conversion required. Let's select the first element of the # list of accepted types. dtype = dtype[0] if estimator is not None: if isinstance(estimator, six.string_types): estimator_name = estimator else: estimator_name = estimator.__class__.__name__ else: estimator_name = "Estimator" context = " by %s" % estimator_name if estimator is not None else "" if sp.issparse(array): array = _ensure_sparse_format(array, accept_sparse, dtype, copy, force_all_finite) else: array = np.array(array, dtype=dtype, order=order, copy=copy) if ensure_2d: if array.ndim == 1: if ensure_min_samples >= 2: raise ValueError("%s expects at least 2 samples provided " "in a 2 dimensional array-like input" % estimator_name) warnings.warn( "Passing 1d arrays as data is deprecated in 0.17 and will " "raise ValueError in 0.19. Reshape your data either using " "X.reshape(-1, 1) if your data has a single feature or " "X.reshape(1, -1) if it contains a single sample.", DeprecationWarning) array = np.atleast_2d(array) # To ensure that array flags are maintained array = np.array(array, dtype=dtype, order=order, copy=copy) # make sure we actually converted to numeric: if dtype_numeric and array.dtype.kind == "O": array = array.astype(np.float64) if not allow_nd and array.ndim >= 3: raise ValueError("Found array with dim %d. %s expected <= 2." % (array.ndim, estimator_name)) if force_all_finite: _assert_all_finite(array) shape_repr = _shape_repr(array.shape) if ensure_min_samples > 0: n_samples = _num_samples(array) if n_samples < ensure_min_samples: raise ValueError("Found array with %d sample(s) (shape=%s) while a" " minimum of %d is required%s." % (n_samples, shape_repr, ensure_min_samples, context)) if ensure_min_features > 0 and array.ndim == 2: n_features = array.shape[1] if n_features < ensure_min_features: raise ValueError("Found array with %d feature(s) (shape=%s) while" " a minimum of %d is required%s." % (n_features, shape_repr, ensure_min_features, context)) if warn_on_dtype and dtype_orig is not None and array.dtype != dtype_orig: msg = ("Data with input dtype %s was converted to %s%s." % (dtype_orig, array.dtype, context)) warnings.warn(msg, _DataConversionWarning) return array
[docs]def check_X_y(X, y, accept_sparse=None, dtype="numeric", order=None, copy=False, force_all_finite=True, ensure_2d=True, allow_nd=False, multi_output=False, ensure_min_samples=1, ensure_min_features=1, y_numeric=False, warn_on_dtype=False, estimator=None): """Input validation for standard estimators. Checks X and y for consistent length, enforces X 2d and y 1d. Standard input checks are only applied to y, such as checking that y does not have np.nan or np.inf targets. For multi-label y, set multi_output=True to allow 2d and sparse y. If the dtype of X is object, attempt converting to float, raising on failure. Parameters ---------- X : nd-array, list or sparse matrix Input data. y : nd-array, list or sparse matrix Labels. accept_sparse : string, list of string or None (default=None) String[s] representing allowed sparse matrix formats, such as 'csc', 'csr', etc. None means that sparse matrix input will raise an error. If the input is sparse but not in the allowed format, it will be converted to the first listed format. dtype : string, type, list of types or None (default="numeric") Data type of result. If None, the dtype of the input is preserved. If "numeric", dtype is preserved unless array.dtype is object. If dtype is a list of types, conversion on the first type is only performed if the dtype of the input is not in the list. order : 'F', 'C' or None (default=None) Whether an array will be forced to be fortran or c-style. copy : boolean (default=False) Whether a forced copy will be triggered. If copy=False, a copy might be triggered by a conversion. force_all_finite : boolean (default=True) Whether to raise an error on np.inf and np.nan in X. This parameter does not influence whether y can have np.inf or np.nan values. ensure_2d : boolean (default=True) Whether to make X at least 2d. allow_nd : boolean (default=False) Whether to allow X.ndim > 2. multi_output : boolean (default=False) Whether to allow 2-d y (array or sparse matrix). If false, y will be validated as a vector. y cannot have np.nan or np.inf values if multi_output=True. ensure_min_samples : int (default=1) Make sure that X has a minimum number of samples in its first axis (rows for a 2D array). ensure_min_features : int (default=1) Make sure that the 2D array has some minimum number of features (columns). The default value of 1 rejects empty datasets. This check is only enforced when X has effectively 2 dimensions or is originally 1D and ``ensure_2d`` is True. Setting to 0 disables this check. y_numeric : boolean (default=False) Whether to ensure that y has a numeric type. If dtype of y is object, it is converted to float64. Should only be used for regression algorithms. warn_on_dtype : boolean (default=False) Raise DataConversionWarning if the dtype of the input data structure does not match the requested dtype, causing a memory copy. estimator : str or estimator instance (default=None) If passed, include the name of the estimator in warning messages. Returns ------- X_converted : object The converted and validated X. y_converted : object The converted and validated y. """ X = check_array(X, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator) if multi_output: y = check_array(y, 'csr', force_all_finite=True, ensure_2d=False, dtype=None) else: y = column_or_1d(y, warn=True) _assert_all_finite(y) if y_numeric and y.dtype.kind == 'O': y = y.astype(np.float64) check_consistent_length(X, y) return X, y
def column_or_1d(y, warn=False): """ Ravel column or 1d numpy array, else raises an error Parameters ---------- y : array-like warn : boolean, default False To control display of warnings. Returns ------- y : array """ shape = np.shape(y) if len(shape) == 1: return np.ravel(y) if len(shape) == 2 and shape[1] == 1: if warn: warnings.warn("A column-vector y was passed when a 1d array was" " expected. Please change the shape of y to " "(n_samples, ), for example using ravel().", _DataConversionWarning, stacklevel=2) return np.ravel(y) raise ValueError("bad input shape {0}".format(shape)) def check_random_state(seed): """Turn seed into a np.random.RandomState instance If seed is None, return the RandomState singleton used by np.random. If seed is an int, return a new RandomState instance seeded with seed. If seed is already a RandomState instance, return it. Otherwise raise ValueError. """ if seed is None or seed is np.random: return np.random.mtrand._rand if isinstance(seed, (numbers.Integral, np.integer)): return np.random.RandomState(seed) if isinstance(seed, np.random.RandomState): return seed raise ValueError('%r cannot be used to seed a numpy.random.RandomState' ' instance' % seed) def has_fit_parameter(estimator, parameter): """Checks whether the estimator's fit method supports the given parameter. Examples -------- >>> from sklearn.svm import SVC >>> has_fit_parameter(SVC(), "sample_weight") True """ return parameter in signature(estimator.fit).parameters def check_symmetric(array, tol=1E-10, raise_warning=True, raise_exception=False): """Make sure that array is 2D, square and symmetric. If the array is not symmetric, then a symmetrized version is returned. Optionally, a warning or exception is raised if the matrix is not symmetric. Parameters ---------- array : nd-array or sparse matrix Input object to check / convert. Must be two-dimensional and square, otherwise a ValueError will be raised. tol : float Absolute tolerance for equivalence of arrays. Default = 1E-10. raise_warning : boolean (default=True) If True then raise a warning if conversion is required. raise_exception : boolean (default=False) If True then raise an exception if array is not symmetric. Returns ------- array_sym : ndarray or sparse matrix Symmetrized version of the input array, i.e. the average of array and array.transpose(). If sparse, then duplicate entries are first summed and zeros are eliminated. """ if (array.ndim != 2) or (array.shape[0] != array.shape[1]): raise ValueError("array must be 2-dimensional and square. " "shape = {0}".format(array.shape)) if sp.issparse(array): diff = array - array.T # only csr, csc, and coo have `data` attribute if diff.format not in ['csr', 'csc', 'coo']: diff = diff.tocsr() symmetric = np.all(abs(diff.data) < tol) else: symmetric = np.allclose(array, array.T, atol=tol) if not symmetric: if raise_exception: raise ValueError("Array must be symmetric") if raise_warning: warnings.warn("Array is not symmetric, and will be converted " "to symmetric by average with its transpose.") if sp.issparse(array): conversion = 'to' + array.format array = getattr(0.5 * (array + array.T), conversion)() else: array = 0.5 * (array + array.T) return array def check_is_fitted(estimator, attributes, msg=None, all_or_any=all): """Perform is_fitted validation for estimator. Checks if the estimator is fitted by verifying the presence of "all_or_any" of the passed attributes and raises a NotFittedError with the given message. Parameters ---------- estimator : estimator instance. estimator instance for which the check is performed. attributes : attribute name(s) given as string or a list/tuple of strings Eg. : ["coef_", "estimator_", ...], "coef_" msg : string The default error message is, "This %(name)s instance is not fitted yet. Call 'fit' with appropriate arguments before using this method." For custom messages if "%(name)s" is present in the message string, it is substituted for the estimator name. Eg. : "Estimator, %(name)s, must be fitted before sparsifying". all_or_any : callable, {all, any}, default all Specify whether all or any of the given attributes must exist. """ if msg is None: msg = ("This %(name)s instance is not fitted yet. Call 'fit' with " "appropriate arguments before using this method.") if not hasattr(estimator, 'fit'): raise TypeError("%s is not an estimator instance." % (estimator)) if not isinstance(attributes, (list, tuple)): attributes = [attributes] if not all_or_any([hasattr(estimator, attr) for attr in attributes]): # FIXME NotFittedError_ --> NotFittedError in 0.19 raise _NotFittedError(msg % {'name': type(estimator).__name__}) def check_non_negative(X, whom): """ Check if there is any negative value in an array. Parameters ---------- X : array-like or sparse matrix Input data. whom : string Who passed X to this function. """ X = X.data if sp.issparse(X) else X if (X < 0).any(): raise ValueError("Negative values in data passed to %s" % whom)