Python _util._asarray_validated函数代码示例

def py_vq2(obs, code_book, check_finite=True):
    """2nd Python version of vq algorithm.

    The algorithm simply computes the euclidian distance between each
    observation and every frame in the code_book/

    Parameters
    ----------
    obs : ndarray
        Expect a rank 2 array. Each row is one observation.
    code_book : ndarray
        Code book to use. Same format than obs. Should have same number of
        features (eg columns) than obs.
    check_finite : bool, optional
        Whether to check that the input matrices contain only finite numbers.
        Disabling may give a performance gain, but may result in problems
        (crashes, non-termination) if the inputs do contain infinities or NaNs.
        Default: True

    Returns
    -------
    code : ndarray
        code[i] gives the label of the ith obversation, that its code is
        code_book[code[i]].
    mind_dist : ndarray
        min_dist[i] gives the distance between the ith observation and its
        corresponding code.

    Notes
    -----
    This could be faster when number of codebooks is small, but it
    becomes a real memory hog when codebook is large. It requires
    N by M by O storage where N=number of obs, M = number of
    features, and O = number of codes.

    """
    obs = _asarray_validated(obs, check_finite=check_finite)
    code_book = _asarray_validated(code_book, check_finite=check_finite)
    d = shape(obs)[1]

    # code books and observations should have same number of features
    if not d == code_book.shape[1]:
        raise ValueError(
            """
            code book(%d) and obs(%d) should have the same
            number of features (eg columns)"""
            % (code_book.shape[1], d)
        )

    diff = obs[newaxis, :, :] - code_book[:, newaxis, :]
    dist = sqrt(np.sum(diff * diff, -1))
    code = argmin(dist, 0)
    min_dist = minimum.reduce(dist, 0)
    # The next line I think is equivalent and should be faster than the one
    # above, but in practice didn't seem to make much difference:
    # min_dist = choose(code,dist)
    return code, min_dist

def py_vq(obs, code_book, check_finite=True):
    """ Python version of vq algorithm.

    The algorithm computes the euclidian distance between each
    observation and every frame in the code_book.

    Parameters
    ----------
    obs : ndarray
        Expects a rank 2 array. Each row is one observation.
    code_book : ndarray
        Code book to use. Same format than obs. Should have same number of
        features (eg columns) than obs.
    check_finite : bool, optional
        Whether to check that the input matrices contain only finite numbers.
        Disabling may give a performance gain, but may result in problems
        (crashes, non-termination) if the inputs do contain infinities or NaNs.
        Default: True

    Returns
    -------
    code : ndarray
        code[i] gives the label of the ith obversation, that its code is
        code_book[code[i]].
    mind_dist : ndarray
        min_dist[i] gives the distance between the ith observation and its
        corresponding code.

    Notes
    -----
    This function is slower than the C version but works for
    all input types.  If the inputs have the wrong types for the
    C versions of the function, this one is called as a last resort.

    It is about 20 times slower than the C version.

    """
    obs = _asarray_validated(obs, check_finite=check_finite)
    code_book = _asarray_validated(code_book, check_finite=check_finite)

    if obs.ndim != code_book.ndim:
        raise ValueError("Observation and code_book should have the same rank")

    if obs.ndim == 1:
        obs = obs[:, np.newaxis]
        code_book = code_book[:, np.newaxis]

    dist = cdist(obs, code_book)
    code = dist.argmin(axis=1)
    min_dist = dist[np.arange(len(code)), code]
    return code, min_dist

    def __init__(self, x, y, axis=0, extrapolate=None):
        x = _asarray_validated(x, check_finite=False, as_inexact=True)
        y = _asarray_validated(y, check_finite=False, as_inexact=True)

        axis = axis % y.ndim

        xp = x.reshape((x.shape[0],) + (1,)*(y.ndim-1))
        yp = np.rollaxis(y, axis)

        dk = self._find_derivatives(xp, yp)
        data = np.hstack((yp[:, None, ...], dk[:, None, ...]))

        _b = BPoly.from_derivatives(x, data, orders=None)
        super(PchipInterpolator, self).__init__(_b.c, _b.x,
                                                extrapolate=extrapolate)
        self.axis = axis

def whiten(obs, check_finite=True):
    """
    Normalize a group of observations on a per feature basis.

    Before running k-means, it is beneficial to rescale each feature
    dimension of the observation set with whitening. Each feature is
    divided by its standard deviation across all observations to give
    it unit variance.

    Parameters
    ----------
    obs : ndarray
        Each row of the array is an observation.  The
        columns are the features seen during each observation.

        >>> #         f0    f1    f2
        >>> obs = [[  1.,   1.,   1.],  #o0
        ...        [  2.,   2.,   2.],  #o1
        ...        [  3.,   3.,   3.],  #o2
        ...        [  4.,   4.,   4.]]  #o3

    check_finite : bool, optional
        Whether to check that the input matrices contain only finite numbers.
        Disabling may give a performance gain, but may result in problems
        (crashes, non-termination) if the inputs do contain infinities or NaNs.
        Default: True

    Returns
    -------
    result : ndarray
        Contains the values in `obs` scaled by the standard deviation
        of each column.

    Examples
    --------
    >>> from scipy.cluster.vq import whiten
    >>> features  = np.array([[1.9, 2.3, 1.7],
    ...                       [1.5, 2.5, 2.2],
    ...                       [0.8, 0.6, 1.7,]])
    >>> whiten(features)
    array([[ 4.17944278,  2.69811351,  7.21248917],
           [ 3.29956009,  2.93273208,  9.33380951],
           [ 1.75976538,  0.7038557 ,  7.21248917]])

    """
    obs = _asarray_validated(obs, check_finite=check_finite)
    std_dev = std(obs, axis=0)
    zero_std_mask = std_dev == 0
    if zero_std_mask.any():
        std_dev[zero_std_mask] = 1.0
        warnings.warn("Some columns have standard deviation zero. "
                      "The values of these columns will not change.",
                      RuntimeWarning)
    return obs / std_dev

def fixed_point(func, x0, args=(), xtol=1e-8, maxiter=500, method='del2'):
    """
    Find a fixed point of the function.

    Given a function of one or more variables and a starting point, find a
    fixed-point of the function: i.e. where ``func(x0) == x0``.

    Parameters
    ----------
    func : function
        Function to evaluate.
    x0 : array_like
        Fixed point of function.
    args : tuple, optional
        Extra arguments to `func`.
    xtol : float, optional
        Convergence tolerance, defaults to 1e-08.
    maxiter : int, optional
        Maximum number of iterations, defaults to 500.
    method : {"del2", "iteration"}, optional
        Method of finding the fixed-point, defaults to "del2"
        which uses Steffensen's Method with Aitken's ``Del^2``
        convergence acceleration [1]_. The "iteration" method simply iterates
        the function until convergence is detected, without attempting to
        accelerate the convergence.

    References
    ----------
    .. [1] Burden, Faires, "Numerical Analysis", 5th edition, pg. 80

    Examples
    --------
    >>> from scipy import optimize
    >>> def func(x, c1, c2):
    ...    return np.sqrt(c1/(x+c2))
    >>> c1 = np.array([10,12.])
    >>> c2 = np.array([3, 5.])
    >>> optimize.fixed_point(func, [1.2, 1.3], args=(c1,c2))
    array([ 1.4920333 ,  1.37228132])

    """
    use_accel = {'del2': True, 'iteration': False}[method]
    x0 = _asarray_validated(x0, as_inexact=True)
    return _fixed_point_helper(func, x0, args, xtol, maxiter, use_accel)

def eig(a, b=None, left=False, right=True, overwrite_a=False,
        overwrite_b=False, check_finite=True, homogeneous_eigvals=False):
    """
    Solve an ordinary or generalized eigenvalue problem of a square matrix.

    Find eigenvalues w and right or left eigenvectors of a general matrix::

        a   vr[:,i] = w[i]        b   vr[:,i]
        a.H vl[:,i] = w[i].conj() b.H vl[:,i]

    where ``.H`` is the Hermitian conjugation.

    Parameters
    ----------
    a : (M, M) array_like
        A complex or real matrix whose eigenvalues and eigenvectors
        will be computed.
    b : (M, M) array_like, optional
        Right-hand side matrix in a generalized eigenvalue problem.
        Default is None, identity matrix is assumed.
    left : bool, optional
        Whether to calculate and return left eigenvectors.  Default is False.
    right : bool, optional
        Whether to calculate and return right eigenvectors.  Default is True.
    overwrite_a : bool, optional
        Whether to overwrite `a`; may improve performance.  Default is False.
    overwrite_b : bool, optional
        Whether to overwrite `b`; may improve performance.  Default is False.
    check_finite : bool, optional
        Whether to check that the input matrices contain only finite numbers.
        Disabling may give a performance gain, but may result in problems
        (crashes, non-termination) if the inputs do contain infinities or NaNs.
    homogeneous_eigvals : bool, optional
        If True, return the eigenvalues in homogeneous coordinates.
        In this case ``w`` is a (2, M) array so that::

            w[1,i] a vr[:,i] = w[0,i] b vr[:,i]

        Default is False.

    Returns
    -------
    w : (M,) or (2, M) double or complex ndarray
        The eigenvalues, each repeated according to its
        multiplicity. The shape is (M,) unless
        ``homogeneous_eigvals=True``.
    vl : (M, M) double or complex ndarray
        The normalized left eigenvector corresponding to the eigenvalue
        ``w[i]`` is the column vl[:,i]. Only returned if ``left=True``.
    vr : (M, M) double or complex ndarray
        The normalized right eigenvector corresponding to the eigenvalue
        ``w[i]`` is the column ``vr[:,i]``.  Only returned if ``right=True``.

    Raises
    ------
    LinAlgError
        If eigenvalue computation does not converge.

    See Also
    --------
    eigvals : eigenvalues of general arrays
    eigh : Eigenvalues and right eigenvectors for symmetric/Hermitian arrays.
    eig_banded : eigenvalues and right eigenvectors for symmetric/Hermitian
        band matrices
    eigh_tridiagonal : eigenvalues and right eiegenvectors for
        symmetric/Hermitian tridiagonal matrices

    Examples
    --------
    >>> from scipy import linalg
    >>> a = np.array([[0., -1.], [1., 0.]])
    >>> linalg.eigvals(a)
    array([0.+1.j, 0.-1.j])

    >>> b = np.array([[0., 1.], [1., 1.]])
    >>> linalg.eigvals(a, b)
    array([ 1.+0.j, -1.+0.j])

    >>> a = np.array([[3., 0., 0.], [0., 8., 0.], [0., 0., 7.]])
    >>> linalg.eigvals(a, homogeneous_eigvals=True)
    array([[3.+0.j, 8.+0.j, 7.+0.j],
           [1.+0.j, 1.+0.j, 1.+0.j]])

    """
    a1 = _asarray_validated(a, check_finite=check_finite)
    if len(a1.shape) != 2 or a1.shape[0] != a1.shape[1]:
        raise ValueError('expected square matrix')
    overwrite_a = overwrite_a or (_datacopied(a1, a))
    if b is not None:
        b1 = _asarray_validated(b, check_finite=check_finite)
        overwrite_b = overwrite_b or _datacopied(b1, b)
        if len(b1.shape) != 2 or b1.shape[0] != b1.shape[1]:
            raise ValueError('expected square matrix')
        if b1.shape != a1.shape:
            raise ValueError('a and b must have the same shape')
        return _geneig(a1, b1, left, right, overwrite_a, overwrite_b,
                       homogeneous_eigvals)

    geev, geev_lwork = get_lapack_funcs(('geev', 'geev_lwork'), (a1,))
    compute_vl, compute_vr = left, right
#.........这里部分代码省略.........

def hessenberg(a, calc_q=False, overwrite_a=False, check_finite=True):
    """
    Compute Hessenberg form of a matrix.

    The Hessenberg decomposition is::

        A = Q H Q^H

    where `Q` is unitary/orthogonal and `H` has only zero elements below
    the first sub-diagonal.

    Parameters
    ----------
    a : (M, M) array_like
        Matrix to bring into Hessenberg form.
    calc_q : bool, optional
        Whether to compute the transformation matrix.  Default is False.
    overwrite_a : bool, optional
        Whether to overwrite `a`; may improve performance.
        Default is False.
    check_finite : bool, optional
        Whether to check that the input matrix contains only finite numbers.
        Disabling may give a performance gain, but may result in problems
        (crashes, non-termination) if the inputs do contain infinities or NaNs.

    Returns
    -------
    H : (M, M) ndarray
        Hessenberg form of `a`.
    Q : (M, M) ndarray
        Unitary/orthogonal similarity transformation matrix ``A = Q H Q^H``.
        Only returned if ``calc_q=True``.

    """
    a1 = _asarray_validated(a, check_finite=check_finite)
    if len(a1.shape) != 2 or (a1.shape[0] != a1.shape[1]):
        raise ValueError("expected square matrix")
    overwrite_a = overwrite_a or (_datacopied(a1, a))

    # if 2x2 or smaller: already in Hessenberg
    if a1.shape[0] <= 2:
        if calc_q:
            return a1, numpy.eye(a1.shape[0])
        return a1

    gehrd, gebal, gehrd_lwork = get_lapack_funcs(("gehrd", "gebal", "gehrd_lwork"), (a1,))
    ba, lo, hi, pivscale, info = gebal(a1, permute=0, overwrite_a=overwrite_a)
    if info < 0:
        raise ValueError("illegal value in %d-th argument of internal gebal " "(hessenberg)" % -info)
    n = len(a1)

    lwork = _compute_lwork(gehrd_lwork, ba.shape[0], lo=lo, hi=hi)

    hq, tau, info = gehrd(ba, lo=lo, hi=hi, lwork=lwork, overwrite_a=1)
    if info < 0:
        raise ValueError("illegal value in %d-th argument of internal gehrd " "(hessenberg)" % -info)
    h = numpy.triu(hq, -1)
    if not calc_q:
        return h

    # use orghr/unghr to compute q
    orghr, orghr_lwork = get_lapack_funcs(("orghr", "orghr_lwork"), (a1,))
    lwork = _compute_lwork(orghr_lwork, n, lo=lo, hi=hi)

    q, info = orghr(a=hq, tau=tau, lo=lo, hi=hi, lwork=lwork, overwrite_a=1)
    if info < 0:
        raise ValueError("illegal value in %d-th argument of internal orghr " "(hessenberg)" % -info)
    return h, q

def kmeans(obs, k_or_guess, iter=20, thresh=1e-5, check_finite=True):
    """
    Performs k-means on a set of observation vectors forming k clusters.

    The k-means algorithm adjusts the centroids until sufficient
    progress cannot be made, i.e. the change in distortion since
    the last iteration is less than some threshold. This yields
    a code book mapping centroids to codes and vice versa.

    Distortion is defined as the sum of the squared differences
    between the observations and the corresponding centroid.

    Parameters
    ----------
    obs : ndarray
       Each row of the M by N array is an observation vector. The
       columns are the features seen during each observation.
       The features must be whitened first with the `whiten` function.

    k_or_guess : int or ndarray
       The number of centroids to generate. A code is assigned to
       each centroid, which is also the row index of the centroid
       in the code_book matrix generated.

       The initial k centroids are chosen by randomly selecting
       observations from the observation matrix. Alternatively,
       passing a k by N array specifies the initial k centroids.

    iter : int, optional
       The number of times to run k-means, returning the codebook
       with the lowest distortion. This argument is ignored if
       initial centroids are specified with an array for the
       ``k_or_guess`` parameter. This parameter does not represent the
       number of iterations of the k-means algorithm.

    thresh : float, optional
       Terminates the k-means algorithm if the change in
       distortion since the last k-means iteration is less than
       or equal to thresh.

    check_finite : bool, optional
        Whether to check that the input matrices contain only finite numbers.
        Disabling may give a performance gain, but may result in problems
        (crashes, non-termination) if the inputs do contain infinities or NaNs.
        Default: True

    Returns
    -------
    codebook : ndarray
       A k by N array of k centroids. The i'th centroid
       codebook[i] is represented with the code i. The centroids
       and codes generated represent the lowest distortion seen,
       not necessarily the globally minimal distortion.

    distortion : float
       The distortion between the observations passed and the
       centroids generated.

    See Also
    --------
    kmeans2 : a different implementation of k-means clustering
       with more methods for generating initial centroids but without
       using a distortion change threshold as a stopping criterion.

    whiten : must be called prior to passing an observation matrix
       to kmeans.

    Examples
    --------
    >>> from numpy import array
    >>> from scipy.cluster.vq import vq, kmeans, whiten
    >>> features  = array([[ 1.9,2.3],
    ...                    [ 1.5,2.5],
    ...                    [ 0.8,0.6],
    ...                    [ 0.4,1.8],
    ...                    [ 0.1,0.1],
    ...                    [ 0.2,1.8],
    ...                    [ 2.0,0.5],
    ...                    [ 0.3,1.5],
    ...                    [ 1.0,1.0]])
    >>> whitened = whiten(features)
    >>> book = array((whitened[0],whitened[2]))
    >>> kmeans(whitened,book)
    (array([[ 2.3110306 ,  2.86287398],    # random
           [ 0.93218041,  1.24398691]]), 0.85684700941625547)

    >>> from numpy import random
    >>> random.seed((1000,2000))
    >>> codes = 3
    >>> kmeans(whitened,codes)
    (array([[ 2.3110306 ,  2.86287398],    # random
           [ 1.32544402,  0.65607529],
           [ 0.40782893,  2.02786907]]), 0.5196582527686241)

    """
    obs = _asarray_validated(obs, check_finite=check_finite)
    if int(iter) < 1:
        raise ValueError('iter must be at least 1.')

    # Determine whether a count (scalar) or an initial guess (array) was passed.
#.........这里部分代码省略.........

def kmeans2(data, k, iter=10, thresh=1e-5, minit='random',
        missing='warn', check_finite=True):
    """
    Classify a set of observations into k clusters using the k-means algorithm.

    The algorithm attempts to minimize the Euclidian distance between
    observations and centroids. Several initialization methods are
    included.

    Parameters
    ----------
    data : ndarray
        A 'M' by 'N' array of 'M' observations in 'N' dimensions or a length
        'M' array of 'M' one-dimensional observations.
    k : int or ndarray
        The number of clusters to form as well as the number of
        centroids to generate. If `minit` initialization string is
        'matrix', or if a ndarray is given instead, it is
        interpreted as initial cluster to use instead.
    iter : int, optional
        Number of iterations of the k-means algrithm to run. Note
        that this differs in meaning from the iters parameter to
        the kmeans function.
    thresh : float, optional
        (not used yet)
    minit : str, optional
        Method for initialization. Available methods are 'random',
        'points', 'uniform', and 'matrix':

        'random': generate k centroids from a Gaussian with mean and
        variance estimated from the data.

        'points': choose k observations (rows) at random from data for
        the initial centroids.

        'uniform': generate k observations from the data from a uniform
        distribution defined by the data set (unsupported).

        'matrix': interpret the k parameter as a k by M (or length k
        array for one-dimensional data) array of initial centroids.
    missing : str, optional
        Method to deal with empty clusters. Available methods are
        'warn' and 'raise':

        'warn': give a warning and continue.

        'raise': raise an ClusterError and terminate the algorithm.
    check_finite : bool, optional
        Whether to check that the input matrices contain only finite numbers.
        Disabling may give a performance gain, but may result in problems
        (crashes, non-termination) if the inputs do contain infinities or NaNs.
        Default: True

    Returns
    -------
    centroid : ndarray
        A 'k' by 'N' array of centroids found at the last iteration of
        k-means.
    label : ndarray
        label[i] is the code or index of the centroid the
        i'th observation is closest to.

    """
    data = _asarray_validated(data, check_finite=check_finite)
    if missing not in _valid_miss_meth:
        raise ValueError("Unkown missing method: %s" % str(missing))
    # If data is rank 1, then we have 1 dimension problem.
    nd = np.ndim(data)
    if nd == 1:
        d = 1
        # raise ValueError("Input of rank 1 not supported yet")
    elif nd == 2:
        d = data.shape[1]
    else:
        raise ValueError("Input of rank > 2 not supported")

    if np.size(data) < 1:
        raise ValueError("Input has 0 items.")

    # If k is not a single value, then it should be compatible with data's
    # shape
    if np.size(k) > 1 or minit == 'matrix':
        if not nd == np.ndim(k):
            raise ValueError("k is not an int and has not same rank than data")
        if d == 1:
            nc = len(k)
        else:
            (nc, dc) = k.shape
            if not dc == d:
                raise ValueError("k is not an int and has not same rank than\
                        data")
        clusters = k.copy()
    else:
        try:
            nc = int(k)
        except TypeError:
            raise ValueError("k (%s) could not be converted to an integer " % str(k))

        if nc < 1:
            raise ValueError("kmeans2 for 0 clusters ? (k was %s)" % str(k))
#.........这里部分代码省略.........

def vq(obs, code_book, check_finite=True):
    """
    Assign codes from a code book to observations.

    Assigns a code from a code book to each observation. Each
    observation vector in the 'M' by 'N' `obs` array is compared with the
    centroids in the code book and assigned the code of the closest
    centroid.

    The features in `obs` should have unit variance, which can be
    achieved by passing them through the whiten function.  The code
    book can be created with the k-means algorithm or a different
    encoding algorithm.

    Parameters
    ----------
    obs : ndarray
        Each row of the 'M' x 'N' array is an observation.  The columns are
        the "features" seen during each observation. The features must be
        whitened first using the whiten function or something equivalent.
    code_book : ndarray
        The code book is usually generated using the k-means algorithm.
        Each row of the array holds a different code, and the columns are
        the features of the code.

         >>> #              f0    f1    f2   f3
         >>> code_book = [
         ...             [  1.,   2.,   3.,   4.],  #c0
         ...             [  1.,   2.,   3.,   4.],  #c1
         ...             [  1.,   2.,   3.,   4.]]  #c2

    check_finite : bool, optional
        Whether to check that the input matrices contain only finite numbers.
        Disabling may give a performance gain, but may result in problems
        (crashes, non-termination) if the inputs do contain infinities or NaNs.
        Default: True

    Returns
    -------
    code : ndarray
        A length M array holding the code book index for each observation.
    dist : ndarray
        The distortion (distance) between the observation and its nearest
        code.

    Examples
    --------
    >>> from numpy import array
    >>> from scipy.cluster.vq import vq
    >>> code_book = array([[1.,1.,1.],
    ...                    [2.,2.,2.]])
    >>> features  = array([[  1.9,2.3,1.7],
    ...                    [  1.5,2.5,2.2],
    ...                    [  0.8,0.6,1.7]])
    >>> vq(features,code_book)
    (array([1, 1, 0],'i'), array([ 0.43588989,  0.73484692,  0.83066239]))

    """
    obs = _asarray_validated(obs, check_finite=check_finite)
    code_book = _asarray_validated(code_book, check_finite=check_finite)
    ct = common_type(obs, code_book)

    c_obs = obs.astype(ct, copy=False)

    if code_book.dtype != ct:
        c_code_book = code_book.astype(ct)
    else:
        c_code_book = code_book

    if ct in (single, double):
        results = _vq.vq(c_obs, c_code_book)
    else:
        results = py_vq(obs, code_book)
    return results

def py_vq(obs, code_book, check_finite=True):
    """ Python version of vq algorithm.

    The algorithm computes the euclidian distance between each
    observation and every frame in the code_book.

    Parameters
    ----------
    obs : ndarray
        Expects a rank 2 array. Each row is one observation.
    code_book : ndarray
        Code book to use. Same format than obs. Should have same number of
        features (eg columns) than obs.
    check_finite : bool, optional
        Whether to check that the input matrices contain only finite numbers.
        Disabling may give a performance gain, but may result in problems
        (crashes, non-termination) if the inputs do contain infinities or NaNs.
        Default: True

    Returns
    -------
    code : ndarray
        code[i] gives the label of the ith obversation, that its code is
        code_book[code[i]].
    mind_dist : ndarray
        min_dist[i] gives the distance between the ith observation and its
        corresponding code.

    Notes
    -----
    This function is slower than the C version but works for
    all input types.  If the inputs have the wrong types for the
    C versions of the function, this one is called as a last resort.

    It is about 20 times slower than the C version.

    """
    obs = _asarray_validated(obs, check_finite=check_finite)
    code_book = _asarray_validated(code_book, check_finite=check_finite)

    # n = number of observations
    # d = number of features
    if np.ndim(obs) == 1:
        if not np.ndim(obs) == np.ndim(code_book):
            raise ValueError(
                    "Observation and code_book should have the same rank")
        else:
            return _py_vq_1d(obs, code_book)
    else:
        (n, d) = shape(obs)

    # code books and observations should have same number of features and same
    # shape
    if not np.ndim(obs) == np.ndim(code_book):
        raise ValueError("Observation and code_book should have the same rank")
    elif not d == code_book.shape[1]:
        raise ValueError("Code book(%d) and obs(%d) should have the same "
                         "number of features (eg columns)""" %
                         (code_book.shape[1], d))

    code = zeros(n, dtype=int)
    min_dist = zeros(n)
    for i in range(n):
        dist = np.sum((obs[i] - code_book) ** 2, 1)
        code[i] = argmin(dist)
        min_dist[i] = dist[code[i]]

    return code, sqrt(min_dist)

 def _prepare_x(self, x):
     """Reshape input x array to 1-D"""
     x = _asarray_validated(x, check_finite=False, as_inexact=True)
     x_shape = x.shape
     return x.ravel(), x_shape

def sqrtm(A, disp=True, blocksize=64):
    """
    Matrix square root.

    Parameters
    ----------
    A : (N, N) array_like
        Matrix whose square root to evaluate
    disp : bool, optional
        Print warning if error in the result is estimated large
        instead of returning estimated error. (Default: True)
    blocksize : integer, optional
        If the blocksize is not degenerate with respect to the
        size of the input array, then use a blocked algorithm. (Default: 64)

    Returns
    -------
    sqrtm : (N, N) ndarray
        Value of the sqrt function at `A`

    errest : float
        (if disp == False)

        Frobenius norm of the estimated error, ||err||_F / ||A||_F

    References
    ----------
    .. [1] Edvin Deadman, Nicholas J. Higham, Rui Ralha (2013)
           "Blocked Schur Algorithms for Computing the Matrix Square Root,
           Lecture Notes in Computer Science, 7782. pp. 171-182.

    Examples
    --------
    >>> from scipy.linalg import sqrtm
    >>> a = np.array([[1.0, 3.0], [1.0, 4.0]])
    >>> r = sqrtm(a)
    >>> r
    array([[ 0.75592895,  1.13389342],
           [ 0.37796447,  1.88982237]])
    >>> r.dot(r)
    array([[ 1.,  3.],
           [ 1.,  4.]])

    """
    A = _asarray_validated(A, check_finite=True, as_inexact=True)
    if len(A.shape) != 2:
        raise ValueError("Non-matrix input to matrix function.")
    if blocksize < 1:
        raise ValueError("The blocksize should be at least 1.")
    keep_it_real = np.isrealobj(A)
    if keep_it_real:
        T, Z = schur(A)
        if not np.array_equal(T, np.triu(T)):
            T, Z = rsf2csf(T, Z)
    else:
        T, Z = schur(A, output='complex')
    failflag = False
    try:
        R = _sqrtm_triu(T, blocksize=blocksize)
        ZH = np.conjugate(Z).T
        X = Z.dot(R).dot(ZH)
    except SqrtmError:
        failflag = True
        X = np.empty_like(A)
        X.fill(np.nan)

    if disp:
        nzeig = np.any(np.diag(T) == 0)
        if nzeig:
            print("Matrix is singular and may not have a square root.")
        elif failflag:
            print("Failed to find a square root.")
        return X
    else:
        try:
            arg2 = norm(X.dot(X) - A, 'fro')**2 / norm(A, 'fro')
        except ValueError:
            # NaNs in matrix
            arg2 = np.inf

        return X, arg2

def hessenberg(a, calc_q=False, overwrite_a=False, check_finite=True):
    """
    Compute Hessenberg form of a matrix.

    The Hessenberg decomposition is::

        A = Q H Q^H

    where `Q` is unitary/orthogonal and `H` has only zero elements below
    the first sub-diagonal.

    Parameters
    ----------
    a : (M, M) array_like
        Matrix to bring into Hessenberg form.
    calc_q : bool, optional
        Whether to compute the transformation matrix.  Default is False.
    overwrite_a : bool, optional
        Whether to overwrite `a`; may improve performance.
        Default is False.
    check_finite : bool, optional
        Whether to check that the input matrix contains only finite numbers.
        Disabling may give a performance gain, but may result in problems
        (crashes, non-termination) if the inputs do contain infinities or NaNs.

    Returns
    -------
    H : (M, M) ndarray
        Hessenberg form of `a`.
    Q : (M, M) ndarray
        Unitary/orthogonal similarity transformation matrix ``A = Q H Q^H``.
        Only returned if ``calc_q=True``.

    Examples
    --------
    >>> from scipy.linalg import hessenberg
    >>> A = np.array([[2, 5, 8, 7], [5, 2, 2, 8], [7, 5, 6, 6], [5, 4, 4, 8]])
    >>> H, Q = hessenberg(A, calc_q=True)
    >>> H
    array([[  2.        , -11.65843866,   1.42005301,   0.25349066],
           [ -9.94987437,  14.53535354,  -5.31022304,   2.43081618],
           [  0.        ,  -1.83299243,   0.38969961,  -0.51527034],
           [  0.        ,   0.        ,  -3.83189513,   1.07494686]])
    >>> np.allclose(Q @ H @ Q.conj().T - A, np.zeros((4, 4)))
    True
    """
    a1 = _asarray_validated(a, check_finite=check_finite)
    if len(a1.shape) != 2 or (a1.shape[0] != a1.shape[1]):
        raise ValueError('expected square matrix')
    overwrite_a = overwrite_a or (_datacopied(a1, a))

    # if 2x2 or smaller: already in Hessenberg
    if a1.shape[0] <= 2:
        if calc_q:
            return a1, numpy.eye(a1.shape[0])
        return a1

    gehrd, gebal, gehrd_lwork = get_lapack_funcs(('gehrd', 'gebal',
                                                  'gehrd_lwork'), (a1,))
    ba, lo, hi, pivscale, info = gebal(a1, permute=0, overwrite_a=overwrite_a)
    _check_info(info, 'gebal (hessenberg)', positive=False)
    n = len(a1)

    lwork = _compute_lwork(gehrd_lwork, ba.shape[0], lo=lo, hi=hi)

    hq, tau, info = gehrd(ba, lo=lo, hi=hi, lwork=lwork, overwrite_a=1)
    _check_info(info, 'gehrd (hessenberg)', positive=False)
    h = numpy.triu(hq, -1)
    if not calc_q:
        return h

    # use orghr/unghr to compute q
    orghr, orghr_lwork = get_lapack_funcs(('orghr', 'orghr_lwork'), (a1,))
    lwork = _compute_lwork(orghr_lwork, n, lo=lo, hi=hi)

    q, info = orghr(a=hq, tau=tau, lo=lo, hi=hi, lwork=lwork, overwrite_a=1)
    _check_info(info, 'orghr (hessenberg)', positive=False)
    return h, q

def eigh_tridiagonal(d, e, eigvals_only=False, select='a', select_range=None,
                     check_finite=True, tol=0., lapack_driver='auto'):
    """
    Solve eigenvalue problem for a real symmetric tridiagonal matrix.

    Find eigenvalues `w` and optionally right eigenvectors `v` of ``a``::

        a v[:,i] = w[i] v[:,i]
        v.H v    = identity

    For a real symmetric matrix ``a`` with diagonal elements `d` and
    off-diagonal elements `e`.

    Parameters
    ----------
    d : ndarray, shape (ndim,)
        The diagonal elements of the array.
    e : ndarray, shape (ndim-1,)
        The off-diagonal elements of the array.
    select : {'a', 'v', 'i'}, optional
        Which eigenvalues to calculate

        ======  ========================================
        select  calculated
        ======  ========================================
        'a'     All eigenvalues
        'v'     Eigenvalues in the interval (min, max]
        'i'     Eigenvalues with indices min <= i <= max
        ======  ========================================
    select_range : (min, max), optional
        Range of selected eigenvalues
    check_finite : bool, optional
        Whether to check that the input matrix contains only finite numbers.
        Disabling may give a performance gain, but may result in problems
        (crashes, non-termination) if the inputs do contain infinities or NaNs.
    tol : float
        The absolute tolerance to which each eigenvalue is required
        (only used when 'stebz' is the `lapack_driver`).
        An eigenvalue (or cluster) is considered to have converged if it
        lies in an interval of this width. If <= 0. (default),
        the value ``eps*|a|`` is used where eps is the machine precision,
        and ``|a|`` is the 1-norm of the matrix ``a``.
    lapack_driver : str
        LAPACK function to use, can be 'auto', 'stemr', 'stebz', 'sterf',
        or 'stev'. When 'auto' (default), it will use 'stemr' if ``select='a'``
        and 'stebz' otherwise. When 'stebz' is used to find the eigenvalues and
        ``eigvals_only=False``, then a second LAPACK call (to ``?STEIN``) is
        used to find the corresponding eigenvectors. 'sterf' can only be
        used when ``eigvals_only=True`` and ``select='a'``. 'stev' can only
        be used when ``select='a'``.

    Returns
    -------
    w : (M,) ndarray
        The eigenvalues, in ascending order, each repeated according to its
        multiplicity.
    v : (M, M) ndarray
        The normalized eigenvector corresponding to the eigenvalue ``w[i]`` is
        the column ``v[:,i]``.

    Raises
    ------
    LinAlgError
        If eigenvalue computation does not converge.

    See Also
    --------
    eigvalsh_tridiagonal : eigenvalues of symmetric/Hermitian tridiagonal
        matrices
    eig : eigenvalues and right eigenvectors for non-symmetric arrays
    eigh : eigenvalues and right eigenvectors for symmetric/Hermitian arrays
    eig_banded : eigenvalues and right eigenvectors for symmetric/Hermitian
        band matrices

    Notes
    -----
    This function makes use of LAPACK ``S/DSTEMR`` routines.

    Examples
    --------
    >>> from scipy.linalg import eigh_tridiagonal
    >>> d = 3*np.ones(4)
    >>> e = -1*np.ones(3)
    >>> w, v = eigh_tridiagonal(d, e)
    >>> A = np.diag(d) + np.diag(e, k=1) + np.diag(e, k=-1)
    >>> np.allclose(A @ v - v @ np.diag(w), np.zeros((4, 4)))
    True
    """
    d = _asarray_validated(d, check_finite=check_finite)
    e = _asarray_validated(e, check_finite=check_finite)
    for check in (d, e):
        if check.ndim != 1:
            raise ValueError('expected one-dimensional array')
        if check.dtype.char in 'GFD':  # complex
            raise TypeError('Only real arrays currently supported')
    if d.size != e.size + 1:
        raise ValueError('d (%s) must have one more element than e (%s)'
                         % (d.size, e.size))
    select, vl, vu, il, iu, _ = _check_select(
        select, select_range, 0, d.size)
#.........这里部分代码省略.........