validation.py

import warnings
import scipy.sparse as sp
from numpy.core.numeric import ComplexWarning
import numpy as np
from _config import get_config as _get_config
import numbers


def _assert_all_finite(X, allow_nan=False, msg_dtype=None):
    """Like assert_all_finite, but only for ndarray."""
    # validation is also imported in extmath
    # modify
    # from .extmath import _safe_accumulator_op
    from extmath import _safe_accumulator_op

    if _get_config()['assume_finite']:
        return
    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. The sum is also calculated
    # safely to reduce dtype induced overflows.
    is_float = X.dtype.kind in 'fc'
    if is_float and (np.isfinite(_safe_accumulator_op(np.sum, X))):
        pass
    elif is_float:
        msg_err = "Input contains {} or a value too large for {!r}."
        if (allow_nan and np.isinf(X).any() or
                not allow_nan and not np.isfinite(X).all()):
            type_err = 'infinity' if allow_nan else 'NaN, infinity'
            raise ValueError(
                    msg_err.format
                    (type_err,
                     msg_dtype if msg_dtype is not None else X.dtype)
            )
    # for object dtype data, we only check for NaNs (GH-13254)
    elif X.dtype == np.dtype('object') and not allow_nan:
        if _object_dtype_isnan(X).any():
            raise ValueError("Input contains NaN")

def _ensure_no_complex_data(array):
    if hasattr(array, 'dtype') and array.dtype is not None and hasattr(array.dtype, 'kind') and array.dtype.kind == "c":
        raise ValueError("Complex data not supported\n"
                         "{}\n".format(array))


def _num_samples(x):
    """Return number of samples in array-like x."""
    message = 'Expected sequence or array-like, got %s' % type(x)
    if hasattr(x, 'fit') and callable(x.fit):
        # Don't get num_samples from an ensembles length!
        raise TypeError(message)

    if not hasattr(x, '__len__') and not hasattr(x, 'shape'):
        if hasattr(x, '__array__'):
            x = np.asarray(x)
        else:
            raise TypeError(message)

    if hasattr(x, 'shape') and x.shape is not None:
        if len(x.shape) == 0:
            raise TypeError("Singleton array %r cannot be considered"
                            " a valid collection." % x)
        # Check that shape is returning an integer or default to len
        # Dask dataframes may not return numeric shape[0] value
        if isinstance(x.shape[0], numbers.Integral):
            return x.shape[0]

    try:
        return len(x)
    except TypeError:
        raise TypeError(message)

def check_array(array, accept_sparse=False, accept_large_sparse=True,
                dtype="numeric", order=None, copy=False, force_all_finite=True,
                ensure_2d=True, allow_nd=False, ensure_min_samples=1,
                ensure_min_features=1, estimator=None):
    # store reference to original array to check if copy is needed when
    # function returns
    array_orig = array

    # store whether originally we wanted numeric dtype
    dtype_numeric = isinstance(dtype, str) and 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

    # check if the object contains several dtypes (typically a pandas
    # DataFrame), and store them. If not, store None.
    dtypes_orig = None
    if hasattr(array, "dtypes") and hasattr(array.dtypes, '__array__'):
        # throw warning if pandas dataframe is sparse
        with suppress(ImportError):
            from pandas.api.types import is_sparse
            if array.dtypes.apply(is_sparse).any():
                warnings.warn(
                    "pandas.DataFrame with sparse columns found."
                    "It will be converted to a dense numpy array."
                )

        dtypes_orig = list(array.dtypes)
        # pandas boolean dtype __array__ interface coerces bools to objects
        for i, dtype_iter in enumerate(dtypes_orig):
            if dtype_iter.kind == 'b':
                dtypes_orig[i] = np.object

        if all(isinstance(dtype, np.dtype) for dtype in dtypes_orig):
            dtype_orig = np.result_type(*dtypes_orig)

    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 force_all_finite not in (True, False, 'allow-nan'):
        raise ValueError('force_all_finite should be a bool or "allow-nan"'
                         '. Got {!r} instead'.format(force_all_finite))

    if estimator is not None:
        if isinstance(estimator, str):
            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):
        _ensure_no_complex_data(array)
        array = _ensure_sparse_format(array, accept_sparse=accept_sparse,
                                      dtype=dtype, copy=copy,
                                      force_all_finite=force_all_finite,
                                      accept_large_sparse=accept_large_sparse)
    else:
        # If np.array(..) gives ComplexWarning, then we convert the warning
        # to an error. This is needed because specifying a non complex
        # dtype to the function converts complex to real dtype,
        # thereby passing the test made in the lines following the scope
        # of warnings context manager.
        with warnings.catch_warnings():
            try:
                warnings.simplefilter('error', ComplexWarning)
                if dtype is not None and np.dtype(dtype).kind in 'iu':
                    # Conversion float -> int should not contain NaN or
                    # inf (numpy#14412). We cannot use casting='safe' because
                    # then conversion float -> int would be disallowed.
                    array = np.asarray(array, order=order)
                    if array.dtype.kind == 'f':
                        _assert_all_finite(array, allow_nan=False,
                                           msg_dtype=dtype)
                    array = array.astype(dtype, casting="unsafe", copy=False)
                else:
                    array = np.asarray(array, order=order, dtype=dtype)
            except ComplexWarning:
                raise ValueError("Complex data not supported\n"
                                 "{}\n".format(array))

        # It is possible that the np.array(..) gave no warning. This happens
        # when no dtype conversion happened, for example dtype = None. The
        # result is that np.array(..) produces an array of complex dtype
        # and we need to catch and raise exception for such cases.
        _ensure_no_complex_data(array)

        if ensure_2d:
            # If input is scalar raise error
            if array.ndim == 0:
                raise ValueError(
                    "Expected 2D array, got scalar array instead:\narray={}.\n"
                    "Reshape your data either using array.reshape(-1, 1) if "
                    "your data has a single feature or array.reshape(1, -1) "
                    "if it contains a single sample.".format(array))
            # If input is 1D raise error
            if array.ndim == 1:
                raise ValueError(
                    "Expected 2D array, got 1D array instead:\narray={}.\n"
                    "Reshape your data either using array.reshape(-1, 1) if "
                    "your data has a single feature or array.reshape(1, -1) "
                    "if it contains a single sample.".format(array))

        # in the future np.flexible dtypes will be handled like object dtypes
        if dtype_numeric and np.issubdtype(array.dtype, np.flexible):
            warnings.warn(
                "Beginning in version 0.22, arrays of bytes/strings will be "
                "converted to decimal numbers if dtype='numeric'. "
                "It is recommended that you convert the array to "
                "a float dtype before using it in scikit-learn, "
                "for example by using "
                "your_array = your_array.astype(np.float64).",
                FutureWarning, stacklevel=2)

        # 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,
                               allow_nan=force_all_finite == 'allow-nan')

    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, array.shape, 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, array.shape, ensure_min_features,
                                context))

    if copy and np.may_share_memory(array, array_orig):
        array = np.array(array, dtype=dtype, order=order)

    return array

def check_X_y(X, y, accept_sparse=False, accept_large_sparse=True,
              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,
              estimator=None):
    if y is None:
        raise ValueError("y cannot be None")

    X = check_array(X, accept_sparse=accept_sparse,
                    accept_large_sparse=accept_large_sparse,
                    dtype=dtype, order=order, copy=copy,
                    force_all_finite=force_all_finite,
                    ensure_2d=ensure_2d, allow_nd=allow_nd,
                    ensure_min_samples=ensure_min_samples,
                    ensure_min_features=ensure_min_features,
                    estimator=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):
    y = np.asarray(y)
    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(
        "y should be a 1d array, "
        "got an array of shape {} instead.".format(shape))

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 check_random_state(seed):
    if seed is None or seed is np.random:
        return np.random.mtrand._rand
    if isinstance(seed, numbers.Integral):
        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)

# ------check_X_y--------
# X = [[1,2],[3,4]]
# y = [5,6]
# X, y = check_X_y(X, y)

# ------check_random_state----
# check_random_state(1000)