Python numpy.ma.where() Examples

def f_oneway(*args):
    """
Performs a 1-way ANOVA, returning an F-value and probability given
any number of groups.  From Heiman, pp.394-7.

Usage:   f_oneway (*args)    where *args is 2 or more arrays, one per
                                  treatment group
Returns: f-value, probability
"""
    # Construct a single array of arguments: each row is a group
    data = argstoarray(*args)
    ngroups = len(data)
    ntot = data.count()
    sstot = (data**2).sum() - (data.sum())**2/float(ntot)
    ssbg = (data.count(-1) * (data.mean(-1)-data.mean())**2).sum()
    sswg = sstot-ssbg
    dfbg = ngroups-1
    dfwg = ntot - ngroups
    msb = ssbg/float(dfbg)
    msw = sswg/float(dfwg)
    f = msb/msw
    prob = stats.fprob(dfbg,dfwg,f)
    return f, prob 

def skewtest(a, axis=0):
    a, axis = _chk_asarray(a, axis)
    if axis is None:
        a = a.ravel()
        axis = 0
    b2 = skew(a,axis)
    n = a.count(axis)
    if np.min(n) < 8:
        warnings.warn(
            "skewtest only valid for n>=8 ... continuing anyway, n=%i" %
            np.min(n))
    y = b2 * ma.sqrt(((n+1)*(n+3)) / (6.0*(n-2)))
    beta2 = (3.0*(n*n+27*n-70)*(n+1)*(n+3)) / ((n-2.0)*(n+5)*(n+7)*(n+9))
    W2 = -1 + ma.sqrt(2*(beta2-1))
    delta = 1/ma.sqrt(0.5*ma.log(W2))
    alpha = ma.sqrt(2.0/(W2-1))
    y = ma.where(y == 0, 1, y)
    Z = delta*ma.log(y/alpha + ma.sqrt((y/alpha)**2+1))
    return Z, (1.0 - stats.zprob(Z))*2 

def kurtosis(a, axis=0, fisher=True, bias=True):
    a, axis = _chk_asarray(a, axis)
    m2 = moment(a,2,axis)
    m4 = moment(a,4,axis)
    olderr = np.seterr(all='ignore')
    try:
        vals = ma.where(m2 == 0, 0, m4 / m2**2.0)
    finally:
        np.seterr(**olderr)

    if not bias:
        n = a.count(axis)
        can_correct = (n > 3) & (m2 is not ma.masked and m2 > 0)
        if can_correct.any():
            n = np.extract(can_correct, n)
            m2 = np.extract(can_correct, m2)
            m4 = np.extract(can_correct, m4)
            nval = 1.0/(n-2)/(n-3)*((n*n-1.0)*m4/m2**2.0-3*(n-1)**2.0)
            np.place(vals, can_correct, nval+3.0)
    if fisher:
        return vals - 3
    else:
        return vals 

def skew(a, axis=0, bias=True):
    a, axis = _chk_asarray(a,axis)
    n = a.count(axis)
    m2 = moment(a, 2, axis)
    m3 = moment(a, 3, axis)
    olderr = np.seterr(all='ignore')
    try:
        vals = ma.where(m2 == 0, 0, m3 / m2**1.5)
    finally:
        np.seterr(**olderr)

    if not bias:
        can_correct = (n > 2) & (m2 > 0)
        if can_correct.any():
            m2 = np.extract(can_correct, m2)
            m3 = np.extract(can_correct, m3)
            nval = ma.sqrt((n-1.0)*n)/(n-2.0)*m3/m2**1.5
            np.place(vals, can_correct, nval)
    return vals 

def trimboth(data, proportiontocut=0.2, inclusive=(True,True), axis=None):
    """
    Trims the smallest and largest data values.

    Trims the `data` by masking the ``int(proportiontocut * n)`` smallest and
    ``int(proportiontocut * n)`` largest values of data along the given axis,
    where n is the number of unmasked values before trimming.

    Parameters
    ----------
    data : ndarray
        Data to trim.
    proportiontocut : float, optional
        Percentage of trimming (as a float between 0 and 1).
        If n is the number of unmasked values before trimming, the number of
        values after trimming is ``(1 - 2*proportiontocut) * n``.
        Default is 0.2.
    inclusive : {(bool, bool) tuple}, optional
        Tuple indicating whether the number of data being masked on each side
        should be rounded (True) or truncated (False).
    axis : int, optional
        Axis along which to perform the trimming.
        If None, the input array is first flattened.

    """
    return trimr(data, limits=(proportiontocut,proportiontocut),
                 inclusive=inclusive, axis=axis) 

def transform_non_affine(self, a):
        sign = np.sign(a)
        masked = ma.masked_inside(a, -self.invlinthresh,
                                  self.invlinthresh, copy=False)
        exp = sign * self.linthresh * (
            ma.power(self.base, (sign * (masked / self.linthresh))
            - self._linscale_adj))
        if masked.mask.any():
            return ma.where(masked.mask, a / self._linscale_adj, exp)
        else:
            return exp 

def _mask_non_positives(a):
    """
    Return a Numpy masked array where all non-positive values are
    masked.  If there are no non-positive values, the original array
    is returned.
    """
    mask = a <= 0.0
    if mask.any():
        return ma.MaskedArray(a, mask=mask)
    return a 

def transform_non_affine(self, a):
        sign = np.sign(a)
        masked = ma.masked_inside(a, -self.invlinthresh,
                                  self.invlinthresh, copy=False)
        exp = sign * self.linthresh * (
            ma.power(self.base, (sign * (masked / self.linthresh))
            - self._linscale_adj))
        if masked.mask.any():
            return ma.where(masked.mask, a / self._linscale_adj, exp)
        else:
            return exp 

def transform_non_affine(self, a):
        sign = np.sign(a)
        masked = ma.masked_inside(a,
                                  -self.linthresh,
                                  self.linthresh,
                                  copy=False)
        log = sign * self.linthresh * (
            self._linscale_adj +
            ma.log(np.abs(masked) / self.linthresh) / self._log_base)
        if masked.mask.any():
            return ma.where(masked.mask, a * self._linscale_adj, log)
        else:
            return log 

def argstoarray(*args):
    """
    Constructs a 2D array from a group of sequences.

    Sequences are filled with missing values to match the length of the longest
    sequence.

    Parameters
    ----------
    args : sequences
        Group of sequences.

    Returns
    -------
    argstoarray : MaskedArray
        A ( `m` x `n` ) masked array, where `m` is the number of arguments and
        `n` the length of the longest argument.

    Notes
    -----
    `numpy.ma.row_stack` has identical behavior, but is called with a sequence
    of sequences.

    """
    if len(args) == 1 and not isinstance(args[0], ndarray):
        output = ma.asarray(args[0])
        if output.ndim != 2:
            raise ValueError("The input should be 2D")
    else:
        n = len(args)
        m = max([len(k) for k in args])
        output = ma.array(np.empty((n,m), dtype=float), mask=True)
        for (k,v) in enumerate(args):
            output[k,:len(v)] = v

    output[np.logical_not(np.isfinite(output._data))] = masked
    return output 

def argstoarray(*args):
    """
    Constructs a 2D array from a group of sequences.

    Sequences are filled with missing values to match the length of the longest
    sequence.

    Parameters
    ----------
    args : sequences
        Group of sequences.

    Returns
    -------
    argstoarray : MaskedArray
        A ( `m` x `n` ) masked array, where `m` is the number of arguments and
        `n` the length of the longest argument.

    Notes
    -----
    `numpy.ma.row_stack` has identical behavior, but is called with a sequence
    of sequences.

    """
    if len(args) == 1 and not isinstance(args[0], ndarray):
        output = ma.asarray(args[0])
        if output.ndim != 2:
            raise ValueError("The input should be 2D")
    else:
        n = len(args)
        m = max([len(k) for k in args])
        output = ma.array(np.empty((n,m), dtype=float), mask=True)
        for (k,v) in enumerate(args):
            output[k,:len(v)] = v

    output[np.logical_not(np.isfinite(output._data))] = masked
    return output 

def _betai(a, b, x):
    x = np.asanyarray(x)
    x = ma.where(x < 1.0, x, 1.0)  # if x > 1 then return 1.0
    return special.betainc(a, b, x) 

def transform_non_affine(self, a):
        sign = np.sign(a)
        masked = ma.masked_inside(a, -self.invlinthresh,
                                  self.invlinthresh, copy=False)
        exp = sign * self.linthresh * (
            ma.power(self.base, (sign * (masked / self.linthresh))
            - self._linscale_adj))
        if masked.mask.any():
            return ma.where(masked.mask, a / self._linscale_adj, exp)
        else:
            return exp 

def f_oneway(*args):
    """
    Performs a 1-way ANOVA, returning an F-value and probability given
    any number of groups.  From Heiman, pp.394-7.

    Usage: ``f_oneway(*args)``, where ``*args`` is 2 or more arrays,
    one per treatment group.

    Returns
    -------
    statistic : float
        The computed F-value of the test.
    pvalue : float
        The associated p-value from the F-distribution.

    """
    # Construct a single array of arguments: each row is a group
    data = argstoarray(*args)
    ngroups = len(data)
    ntot = data.count()
    sstot = (data**2).sum() - (data.sum())**2/float(ntot)
    ssbg = (data.count(-1) * (data.mean(-1)-data.mean())**2).sum()
    sswg = sstot-ssbg
    dfbg = ngroups-1
    dfwg = ntot - ngroups
    msb = ssbg/float(dfbg)
    msw = sswg/float(dfwg)
    f = msb/msw
    prob = special.fdtrc(dfbg, dfwg, f)  # equivalent to stats.f.sf

    return F_onewayResult(f, prob) 

def transform_non_affine(self, a):
        sign = np.sign(a)
        masked = ma.masked_inside(a,
                                  -self.linthresh,
                                  self.linthresh,
                                  copy=False)
        log = sign * self.linthresh * (
            self._linscale_adj +
            ma.log(np.abs(masked) / self.linthresh) / self._log_base)
        if masked.mask.any():
            return ma.where(masked.mask, a * self._linscale_adj, log)
        else:
            return log 

def transform_non_affine(self, a):
        sign = np.sign(a)
        masked = ma.masked_inside(a, -self.invlinthresh,
                                  self.invlinthresh, copy=False)
        exp = sign * self.linthresh * (
            ma.power(self.base, (sign * (masked / self.linthresh))
            - self._linscale_adj))
        if masked.mask.any():
            return ma.where(masked.mask, a / self._linscale_adj, exp)
        else:
            return exp 

def iterate(self, arr):
        # iterate through a matrix and accept or reject various indices
        m = np.mean(arr)
        s = np.std(arr)
        ym = ma.masked_inside(arr, m-5*s, m+5*s)
        return ma.where(ym == False) 

def argstoarray(*args):
    """
    Constructs a 2D array from a group of sequences.

    Sequences are filled with missing values to match the length of the longest
    sequence.

    Parameters
    ----------
    args : sequences
        Group of sequences.

    Returns
    -------
    argstoarray : MaskedArray
        A ( `m` x `n` ) masked array, where `m` is the number of arguments and
        `n` the length of the longest argument.

    Notes
    -----
    `numpy.ma.row_stack` has identical behavior, but is called with a sequence
    of sequences.

    """
    if len(args) == 1 and not isinstance(args[0], ndarray):
        output = ma.asarray(args[0])
        if output.ndim != 2:
            raise ValueError("The input should be 2D")
    else:
        n = len(args)
        m = max([len(k) for k in args])
        output = ma.array(np.empty((n,m), dtype=float), mask=True)
        for (k,v) in enumerate(args):
            output[k,:len(v)] = v

    output[np.logical_not(np.isfinite(output._data))] = masked
    return output 

def _betai(a, b, x):
    x = np.asanyarray(x)
    x = ma.where(x < 1.0, x, 1.0)  # if x > 1 then return 1.0
    return special.betainc(a, b, x) 

def normaltest(a, axis=0):
    """
    Tests whether a sample differs from a normal distribution.

    Parameters
    ----------
    a : array_like
        The array containing the data to be tested.
    axis : int or None, optional
        Axis along which to compute test. Default is 0. If None,
        compute over the whole array `a`.

    Returns
    -------
    statistic : float or array
        ``s^2 + k^2``, where ``s`` is the z-score returned by `skewtest` and
        ``k`` is the z-score returned by `kurtosistest`.
    pvalue : float or array
       A 2-sided chi squared probability for the hypothesis test.

    Notes
    -----
    For more details about `normaltest`, see `stats.normaltest`.

    """
    a, axis = _chk_asarray(a, axis)
    s, _ = skewtest(a, axis)
    k, _ = kurtosistest(a, axis)
    k2 = s*s + k*k

    return NormaltestResult(k2, distributions.chi2.sf(k2, 2)) 

def transform_non_affine(self, a):
        sign = np.sign(a)
        masked = ma.masked_inside(a,
                                  -self.linthresh,
                                  self.linthresh,
                                  copy=False)
        log = sign * self.linthresh * (
            self._linscale_adj +
            ma.log(np.abs(masked) / self.linthresh) / self._log_base)
        if masked.mask.any():
            return ma.where(masked.mask, a * self._linscale_adj, log)
        else:
            return log 

def transform_non_affine(self, a):
        sign = np.sign(a)
        masked = ma.masked_inside(a, -self.invlinthresh,
                                  self.invlinthresh, copy=False)
        exp = sign * self.linthresh * (
            ma.power(self.base, (sign * (masked / self.linthresh))
            - self._linscale_adj))
        if masked.mask.any():
            return ma.where(masked.mask, a / self._linscale_adj, exp)
        else:
            return exp 

def transform_non_affine(self, a):
        sign = np.sign(a)
        masked = ma.masked_inside(a,
                                  -self.linthresh,
                                  self.linthresh,
                                  copy=False)
        log = sign * self.linthresh * (
            self._linscale_adj +
            ma.log(np.abs(masked) / self.linthresh) / self._log_base)
        if masked.mask.any():
            return ma.where(masked.mask, a * self._linscale_adj, log)
        else:
            return log 

def transform_non_affine(self, a):
        sign = np.sign(a)
        masked = ma.masked_inside(a, -self.invlinthresh,
                                  self.invlinthresh, copy=False)
        exp = sign * self.linthresh * (
            ma.power(self.base, (sign * (masked / self.linthresh))
            - self._linscale_adj))
        if masked.mask.any():
            return ma.where(masked.mask, a / self._linscale_adj, exp)
        else:
            return exp 

def _mask_non_positives(a):
    """
    Return a Numpy masked array where all non-positive values are
    masked.  If there are no non-positive values, the original array
    is returned.
    """
    mask = a <= 0.0
    if mask.any():
        return ma.MaskedArray(a, mask=mask)
    return a 

def _betai(a, b, x):
    x = np.asanyarray(x)
    x = ma.where(x < 1.0, x, 1.0)  # if x > 1 then return 1.0
    return special.betainc(a, b, x) 

def normaltest(a, axis=0):
    """
    Tests whether a sample differs from a normal distribution.

    Parameters
    ----------
    a : array_like
        The array containing the data to be tested.
    axis : int or None, optional
        Axis along which to compute test. Default is 0. If None,
        compute over the whole array `a`.

    Returns
    -------
    statistic : float or array
        ``s^2 + k^2``, where ``s`` is the z-score returned by `skewtest` and
        ``k`` is the z-score returned by `kurtosistest`.
    pvalue : float or array
       A 2-sided chi squared probability for the hypothesis test.

    Notes
    -----
    For more details about `normaltest`, see `stats.normaltest`.

    """
    a, axis = _chk_asarray(a, axis)
    s, _ = skewtest(a, axis)
    k, _ = kurtosistest(a, axis)
    k2 = s*s + k*k

    return NormaltestResult(k2, distributions.chi2.sf(k2, 2)) 

def _mask_non_positives(a):
    """
    Return a Numpy masked array where all non-positive values are
    masked.  If there are no non-positive values, the original array
    is returned.
    """
    mask = a <= 0.0
    if mask.any():
        return ma.MaskedArray(a, mask=mask)
    return a 

def transform_non_affine(self, a):
        sign = np.sign(a)
        masked = ma.masked_inside(a,
                                  -self.linthresh,
                                  self.linthresh,
                                  copy=False)
        log = sign * self.linthresh * (
            self._linscale_adj +
            ma.log(np.abs(masked) / self.linthresh) / self._log_base)
        if masked.mask.any():
            return ma.where(masked.mask, a * self._linscale_adj, log)
        else:
            return log 

def transform_non_affine(self, a):
        sign = np.sign(a)
        masked = ma.masked_inside(a, -self.invlinthresh,
                                  self.invlinthresh, copy=False)
        exp = sign * self.linthresh * (
            ma.power(self.base, (sign * (masked / self.linthresh))
            - self._linscale_adj))
        if masked.mask.any():
            return ma.where(masked.mask, a / self._linscale_adj, exp)
        else:
            return exp