Python numpy.ma.apply_along_axis() Examples
The following are 24
code examples of numpy.ma.apply_along_axis().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
numpy.ma
, or try the search function
.
.
Example #1
| Source File: mstats_extras.py From Splunking-Crime with GNU Affero General Public License v3.0 | 5 votes |
|
def idealfourths(data, axis=None):
"""
Returns an estimate of the lower and upper quartiles.
Uses the ideal fourths algorithm.
Parameters
----------
data : array_like
Input array.
axis : int, optional
Axis along which the quartiles are estimated. If None, the arrays are
flattened.
Returns
-------
idealfourths : {list of floats, masked array}
Returns the two internal values that divide `data` into four parts
using the ideal fourths algorithm either along the flattened array
(if `axis` is None) or along `axis` of `data`.
"""
def _idf(data):
x = data.compressed()
n = len(x)
if n < 3:
return [np.nan,np.nan]
(j,h) = divmod(n/4. + 5/12.,1)
j = int(j)
qlo = (1-h)*x[j-1] + h*x[j]
k = n - j
qup = (1-h)*x[k] + h*x[k-1]
return [qlo, qup]
data = ma.sort(data, axis=axis).view(MaskedArray)
if (axis is None):
return _idf(data)
else:
return ma.apply_along_axis(_idf, axis, data)
Example #2
| Source File: mstats_basic.py From lambda-packs with MIT License | 5 votes |
|
def stde_median(data, axis=None):
"""Returns the McKean-Schrader estimate of the standard error of the sample
median along the given axis. masked values are discarded.
Parameters
----------
data : ndarray
Data to trim.
axis : {None,int}, optional
Axis along which to perform the trimming.
If None, the input array is first flattened.
"""
def _stdemed_1D(data):
data = np.sort(data.compressed())
n = len(data)
z = 2.5758293035489004
k = int(np.round((n+1)/2. - z * np.sqrt(n/4.),0))
return ((data[n-k] - data[k-1])/(2.*z))
data = ma.array(data, copy=False, subok=True)
if (axis is None):
return _stdemed_1D(data)
else:
if data.ndim > 2:
raise ValueError("Array 'data' must be at most two dimensional, "
"but got data.ndim = %d" % data.ndim)
return ma.apply_along_axis(_stdemed_1D, axis, data)
Example #3
| Source File: mstats_extras.py From lambda-packs with MIT License | 5 votes |
|
def idealfourths(data, axis=None):
"""
Returns an estimate of the lower and upper quartiles.
Uses the ideal fourths algorithm.
Parameters
----------
data : array_like
Input array.
axis : int, optional
Axis along which the quartiles are estimated. If None, the arrays are
flattened.
Returns
-------
idealfourths : {list of floats, masked array}
Returns the two internal values that divide `data` into four parts
using the ideal fourths algorithm either along the flattened array
(if `axis` is None) or along `axis` of `data`.
"""
def _idf(data):
x = data.compressed()
n = len(x)
if n < 3:
return [np.nan,np.nan]
(j,h) = divmod(n/4. + 5/12.,1)
j = int(j)
qlo = (1-h)*x[j-1] + h*x[j]
k = n - j
qup = (1-h)*x[k] + h*x[k-1]
return [qlo, qup]
data = ma.sort(data, axis=axis).view(MaskedArray)
if (axis is None):
return _idf(data)
else:
return ma.apply_along_axis(_idf, axis, data)
Example #4
| Source File: mstats_basic.py From Splunking-Crime with GNU Affero General Public License v3.0 | 5 votes |
|
def stde_median(data, axis=None):
"""Returns the McKean-Schrader estimate of the standard error of the sample
median along the given axis. masked values are discarded.
Parameters
----------
data : ndarray
Data to trim.
axis : {None,int}, optional
Axis along which to perform the trimming.
If None, the input array is first flattened.
"""
def _stdemed_1D(data):
data = np.sort(data.compressed())
n = len(data)
z = 2.5758293035489004
k = int(np.round((n+1)/2. - z * np.sqrt(n/4.),0))
return ((data[n-k] - data[k-1])/(2.*z))
data = ma.array(data, copy=False, subok=True)
if (axis is None):
return _stdemed_1D(data)
else:
if data.ndim > 2:
raise ValueError("Array 'data' must be at most two dimensional, "
"but got data.ndim = %d" % data.ndim)
return ma.apply_along_axis(_stdemed_1D, axis, data)
Example #5
| Source File: mstats_basic.py From Computable with MIT License | 5 votes |
|
def mode(a, axis=0):
a, axis = _chk_asarray(a, axis)
def _mode1D(a):
(rep,cnt) = find_repeats(a)
if not cnt.ndim:
return (0, 0)
elif cnt.size:
return (rep[cnt.argmax()], cnt.max())
else:
not_masked_indices = ma.flatnotmasked_edges(a)
first_not_masked_index = not_masked_indices[0]
return (a[first_not_masked_index], 1)
if axis is None:
output = _mode1D(ma.ravel(a))
output = (ma.array(output[0]), ma.array(output[1]))
else:
output = ma.apply_along_axis(_mode1D, axis, a)
newshape = list(a.shape)
newshape[axis] = 1
slices = [slice(None)] * output.ndim
slices[axis] = 0
modes = output[tuple(slices)].reshape(newshape)
slices[axis] = 1
counts = output[tuple(slices)].reshape(newshape)
output = (modes, counts)
return output
Example #6
| Source File: mstats_basic.py From Computable with MIT License | 5 votes |
|
def stde_median(data, axis=None):
"""Returns the McKean-Schrader estimate of the standard error of the sample
median along the given axis. masked values are discarded.
Parameters
----------
data : ndarray
Data to trim.
axis : {None,int}, optional
Axis along which to perform the trimming.
If None, the input array is first flattened.
"""
def _stdemed_1D(data):
data = np.sort(data.compressed())
n = len(data)
z = 2.5758293035489004
k = int(np.round((n+1)/2. - z * np.sqrt(n/4.),0))
return ((data[n-k] - data[k-1])/(2.*z))
#
data = ma.array(data, copy=False, subok=True)
if (axis is None):
return _stdemed_1D(data)
else:
if data.ndim > 2:
raise ValueError("Array 'data' must be at most two dimensional, but got data.ndim = %d" % data.ndim)
return ma.apply_along_axis(_stdemed_1D, axis, data)
#####--------------------------------------------------------------------------
#---- --- Normality Tests ---
#####--------------------------------------------------------------------------
Example #7
| Source File: mstats_extras.py From Computable with MIT License | 5 votes |
|
def idealfourths(data, axis=None):
"""
Returns an estimate of the lower and upper quartiles.
Uses the ideal fourths algorithm.
Parameters
----------
data : array_like
Input array.
axis : int, optional
Axis along which the quartiles are estimated. If None, the arrays are
flattened.
Returns
-------
idealfourths : {list of floats, masked array}
Returns the two internal values that divide `data` into four parts
using the ideal fourths algorithm either along the flattened array
(if `axis` is None) or along `axis` of `data`.
"""
def _idf(data):
x = data.compressed()
n = len(x)
if n < 3:
return [np.nan,np.nan]
(j,h) = divmod(n/4. + 5/12.,1)
j = int(j)
qlo = (1-h)*x[j-1] + h*x[j]
k = n - j
qup = (1-h)*x[k] + h*x[k-1]
return [qlo, qup]
data = ma.sort(data, axis=axis).view(MaskedArray)
if (axis is None):
return _idf(data)
else:
return ma.apply_along_axis(_idf, axis, data)
Example #8
| Source File: mstats_extras.py From GraphicDesignPatternByPython with MIT License | 5 votes |
|
def idealfourths(data, axis=None):
"""
Returns an estimate of the lower and upper quartiles.
Uses the ideal fourths algorithm.
Parameters
----------
data : array_like
Input array.
axis : int, optional
Axis along which the quartiles are estimated. If None, the arrays are
flattened.
Returns
-------
idealfourths : {list of floats, masked array}
Returns the two internal values that divide `data` into four parts
using the ideal fourths algorithm either along the flattened array
(if `axis` is None) or along `axis` of `data`.
"""
def _idf(data):
x = data.compressed()
n = len(x)
if n < 3:
return [np.nan,np.nan]
(j,h) = divmod(n/4. + 5/12.,1)
j = int(j)
qlo = (1-h)*x[j-1] + h*x[j]
k = n - j
qup = (1-h)*x[k] + h*x[k-1]
return [qlo, qup]
data = ma.sort(data, axis=axis).view(MaskedArray)
if (axis is None):
return _idf(data)
else:
return ma.apply_along_axis(_idf, axis, data)
Example #9
| Source File: mstats_basic.py From GraphicDesignPatternByPython with MIT License | 5 votes |
|
def stde_median(data, axis=None):
"""Returns the McKean-Schrader estimate of the standard error of the sample
median along the given axis. masked values are discarded.
Parameters
----------
data : ndarray
Data to trim.
axis : {None,int}, optional
Axis along which to perform the trimming.
If None, the input array is first flattened.
"""
def _stdemed_1D(data):
data = np.sort(data.compressed())
n = len(data)
z = 2.5758293035489004
k = int(np.round((n+1)/2. - z * np.sqrt(n/4.),0))
return ((data[n-k] - data[k-1])/(2.*z))
data = ma.array(data, copy=False, subok=True)
if (axis is None):
return _stdemed_1D(data)
else:
if data.ndim > 2:
raise ValueError("Array 'data' must be at most two dimensional, "
"but got data.ndim = %d" % data.ndim)
return ma.apply_along_axis(_stdemed_1D, axis, data)
Example #10
| Source File: mstats_basic.py From GraphicDesignPatternByPython with MIT License | 4 votes |
|
def rankdata(data, axis=None, use_missing=False):
"""Returns the rank (also known as order statistics) of each data point
along the given axis.
If some values are tied, their rank is averaged.
If some values are masked, their rank is set to 0 if use_missing is False,
or set to the average rank of the unmasked values if use_missing is True.
Parameters
----------
data : sequence
Input data. The data is transformed to a masked array
axis : {None,int}, optional
Axis along which to perform the ranking.
If None, the array is first flattened. An exception is raised if
the axis is specified for arrays with a dimension larger than 2
use_missing : bool, optional
Whether the masked values have a rank of 0 (False) or equal to the
average rank of the unmasked values (True).
"""
def _rank1d(data, use_missing=False):
n = data.count()
rk = np.empty(data.size, dtype=float)
idx = data.argsort()
rk[idx[:n]] = np.arange(1,n+1)
if use_missing:
rk[idx[n:]] = (n+1)/2.
else:
rk[idx[n:]] = 0
repeats = find_repeats(data.copy())
for r in repeats[0]:
condition = (data == r).filled(False)
rk[condition] = rk[condition].mean()
return rk
data = ma.array(data, copy=False)
if axis is None:
if data.ndim > 1:
return _rank1d(data.ravel(), use_missing).reshape(data.shape)
else:
return _rank1d(data, use_missing)
else:
return ma.apply_along_axis(_rank1d,axis,data,use_missing).view(ndarray)
Example #11
| Source File: mstats_extras.py From Splunking-Crime with GNU Affero General Public License v3.0 | 4 votes |
|
def mjci(data, prob=[0.25,0.5,0.75], axis=None):
"""
Returns the Maritz-Jarrett estimators of the standard error of selected
experimental quantiles of the data.
Parameters
----------
data : ndarray
Data array.
prob : sequence, optional
Sequence of quantiles to compute.
axis : int or None, optional
Axis along which to compute the quantiles. If None, use a flattened
array.
"""
def _mjci_1D(data, p):
data = np.sort(data.compressed())
n = data.size
prob = (np.array(p) * n + 0.5).astype(int_)
betacdf = beta.cdf
mj = np.empty(len(prob), float_)
x = np.arange(1,n+1, dtype=float_) / n
y = x - 1./n
for (i,m) in enumerate(prob):
W = betacdf(x,m-1,n-m) - betacdf(y,m-1,n-m)
C1 = np.dot(W,data)
C2 = np.dot(W,data**2)
mj[i] = np.sqrt(C2 - C1**2)
return mj
data = ma.array(data, copy=False)
if data.ndim > 2:
raise ValueError("Array 'data' must be at most two dimensional, "
"but got data.ndim = %d" % data.ndim)
p = np.array(prob, copy=False, ndmin=1)
# Computes quantiles along axis (or globally)
if (axis is None):
return _mjci_1D(data, p)
else:
return ma.apply_along_axis(_mjci_1D, axis, data, p)
Example #12
| Source File: mstats_extras.py From Splunking-Crime with GNU Affero General Public License v3.0 | 4 votes |
|
def hdquantiles_sd(data, prob=list([.25,.5,.75]), axis=None):
"""
The standard error of the Harrell-Davis quantile estimates by jackknife.
Parameters
----------
data : array_like
Data array.
prob : sequence, optional
Sequence of quantiles to compute.
axis : int, optional
Axis along which to compute the quantiles. If None, use a flattened
array.
Returns
-------
hdquantiles_sd : MaskedArray
Standard error of the Harrell-Davis quantile estimates.
"""
def _hdsd_1D(data,prob):
"Computes the std error for 1D arrays."
xsorted = np.sort(data.compressed())
n = len(xsorted)
#.........
hdsd = np.empty(len(prob), float_)
if n < 2:
hdsd.flat = np.nan
vv = np.arange(n) / float(n-1)
betacdf = beta.cdf
for (i,p) in enumerate(prob):
_w = betacdf(vv, (n+1)*p, (n+1)*(1-p))
w = _w[1:] - _w[:-1]
mx_ = np.fromiter([np.dot(w,xsorted[np.r_[list(range(0,k)),
list(range(k+1,n))].astype(int_)])
for k in range(n)], dtype=float_)
mx_var = np.array(mx_.var(), copy=False, ndmin=1) * n / float(n-1)
hdsd[i] = float(n-1) * np.sqrt(np.diag(mx_var).diagonal() / float(n))
return hdsd
# Initialization & checks
data = ma.array(data, copy=False, dtype=float_)
p = np.array(prob, copy=False, ndmin=1)
# Computes quantiles along axis (or globally)
if (axis is None):
result = _hdsd_1D(data, p)
else:
if data.ndim > 2:
raise ValueError("Array 'data' must be at most two dimensional, "
"but got data.ndim = %d" % data.ndim)
result = ma.apply_along_axis(_hdsd_1D, axis, data, p)
return ma.fix_invalid(result, copy=False).ravel()
Example #13
| Source File: mstats_basic.py From Splunking-Crime with GNU Affero General Public License v3.0 | 4 votes |
|
def mode(a, axis=0):
"""
Returns an array of the modal (most common) value in the passed array.
Parameters
----------
a : array_like
n-dimensional array of which to find mode(s).
axis : int or None, optional
Axis along which to operate. Default is 0. If None, compute over
the whole array `a`.
Returns
-------
mode : ndarray
Array of modal values.
count : ndarray
Array of counts for each mode.
Notes
-----
For more details, see `stats.mode`.
"""
a, axis = _chk_asarray(a, axis)
def _mode1D(a):
(rep,cnt) = find_repeats(a)
if not cnt.ndim:
return (0, 0)
elif cnt.size:
return (rep[cnt.argmax()], cnt.max())
else:
not_masked_indices = ma.flatnotmasked_edges(a)
first_not_masked_index = not_masked_indices[0]
return (a[first_not_masked_index], 1)
if axis is None:
output = _mode1D(ma.ravel(a))
output = (ma.array(output[0]), ma.array(output[1]))
else:
output = ma.apply_along_axis(_mode1D, axis, a)
newshape = list(a.shape)
newshape[axis] = 1
slices = [slice(None)] * output.ndim
slices[axis] = 0
modes = output[tuple(slices)].reshape(newshape)
slices[axis] = 1
counts = output[tuple(slices)].reshape(newshape)
output = (modes, counts)
return ModeResult(*output)
Example #14
| Source File: mstats_basic.py From Splunking-Crime with GNU Affero General Public License v3.0 | 4 votes |
|
def rankdata(data, axis=None, use_missing=False):
"""Returns the rank (also known as order statistics) of each data point
along the given axis.
If some values are tied, their rank is averaged.
If some values are masked, their rank is set to 0 if use_missing is False,
or set to the average rank of the unmasked values if use_missing is True.
Parameters
----------
data : sequence
Input data. The data is transformed to a masked array
axis : {None,int}, optional
Axis along which to perform the ranking.
If None, the array is first flattened. An exception is raised if
the axis is specified for arrays with a dimension larger than 2
use_missing : bool, optional
Whether the masked values have a rank of 0 (False) or equal to the
average rank of the unmasked values (True).
"""
def _rank1d(data, use_missing=False):
n = data.count()
rk = np.empty(data.size, dtype=float)
idx = data.argsort()
rk[idx[:n]] = np.arange(1,n+1)
if use_missing:
rk[idx[n:]] = (n+1)/2.
else:
rk[idx[n:]] = 0
repeats = find_repeats(data.copy())
for r in repeats[0]:
condition = (data == r).filled(False)
rk[condition] = rk[condition].mean()
return rk
data = ma.array(data, copy=False)
if axis is None:
if data.ndim > 1:
return _rank1d(data.ravel(), use_missing).reshape(data.shape)
else:
return _rank1d(data, use_missing)
else:
return ma.apply_along_axis(_rank1d,axis,data,use_missing).view(ndarray)
Example #15
| Source File: mstats_extras.py From GraphicDesignPatternByPython with MIT License | 4 votes |
|
def mjci(data, prob=[0.25,0.5,0.75], axis=None):
"""
Returns the Maritz-Jarrett estimators of the standard error of selected
experimental quantiles of the data.
Parameters
----------
data : ndarray
Data array.
prob : sequence, optional
Sequence of quantiles to compute.
axis : int or None, optional
Axis along which to compute the quantiles. If None, use a flattened
array.
"""
def _mjci_1D(data, p):
data = np.sort(data.compressed())
n = data.size
prob = (np.array(p) * n + 0.5).astype(int_)
betacdf = beta.cdf
mj = np.empty(len(prob), float_)
x = np.arange(1,n+1, dtype=float_) / n
y = x - 1./n
for (i,m) in enumerate(prob):
W = betacdf(x,m-1,n-m) - betacdf(y,m-1,n-m)
C1 = np.dot(W,data)
C2 = np.dot(W,data**2)
mj[i] = np.sqrt(C2 - C1**2)
return mj
data = ma.array(data, copy=False)
if data.ndim > 2:
raise ValueError("Array 'data' must be at most two dimensional, "
"but got data.ndim = %d" % data.ndim)
p = np.array(prob, copy=False, ndmin=1)
# Computes quantiles along axis (or globally)
if (axis is None):
return _mjci_1D(data, p)
else:
return ma.apply_along_axis(_mjci_1D, axis, data, p)
Example #16
| Source File: mstats_extras.py From GraphicDesignPatternByPython with MIT License | 4 votes |
|
def hdquantiles_sd(data, prob=list([.25,.5,.75]), axis=None):
"""
The standard error of the Harrell-Davis quantile estimates by jackknife.
Parameters
----------
data : array_like
Data array.
prob : sequence, optional
Sequence of quantiles to compute.
axis : int, optional
Axis along which to compute the quantiles. If None, use a flattened
array.
Returns
-------
hdquantiles_sd : MaskedArray
Standard error of the Harrell-Davis quantile estimates.
See Also
--------
hdquantiles
"""
def _hdsd_1D(data, prob):
"Computes the std error for 1D arrays."
xsorted = np.sort(data.compressed())
n = len(xsorted)
hdsd = np.empty(len(prob), float_)
if n < 2:
hdsd.flat = np.nan
vv = np.arange(n) / float(n-1)
betacdf = beta.cdf
for (i,p) in enumerate(prob):
_w = betacdf(vv, (n+1)*p, (n+1)*(1-p))
w = _w[1:] - _w[:-1]
mx_ = np.fromiter([np.dot(w,xsorted[np.r_[list(range(0,k)),
list(range(k+1,n))].astype(int_)])
for k in range(n)], dtype=float_)
mx_var = np.array(mx_.var(), copy=False, ndmin=1) * n / float(n-1)
hdsd[i] = float(n-1) * np.sqrt(np.diag(mx_var).diagonal() / float(n))
return hdsd
# Initialization & checks
data = ma.array(data, copy=False, dtype=float_)
p = np.array(prob, copy=False, ndmin=1)
# Computes quantiles along axis (or globally)
if (axis is None):
result = _hdsd_1D(data, p)
else:
if data.ndim > 2:
raise ValueError("Array 'data' must be at most two dimensional, "
"but got data.ndim = %d" % data.ndim)
result = ma.apply_along_axis(_hdsd_1D, axis, data, p)
return ma.fix_invalid(result, copy=False).ravel()
Example #17
| Source File: mstats_basic.py From GraphicDesignPatternByPython with MIT License | 4 votes |
|
def mode(a, axis=0):
"""
Returns an array of the modal (most common) value in the passed array.
Parameters
----------
a : array_like
n-dimensional array of which to find mode(s).
axis : int or None, optional
Axis along which to operate. Default is 0. If None, compute over
the whole array `a`.
Returns
-------
mode : ndarray
Array of modal values.
count : ndarray
Array of counts for each mode.
Notes
-----
For more details, see `stats.mode`.
"""
a, axis = _chk_asarray(a, axis)
def _mode1D(a):
(rep,cnt) = find_repeats(a)
if not cnt.ndim:
return (0, 0)
elif cnt.size:
return (rep[cnt.argmax()], cnt.max())
else:
not_masked_indices = ma.flatnotmasked_edges(a)
first_not_masked_index = not_masked_indices[0]
return (a[first_not_masked_index], 1)
if axis is None:
output = _mode1D(ma.ravel(a))
output = (ma.array(output[0]), ma.array(output[1]))
else:
output = ma.apply_along_axis(_mode1D, axis, a)
newshape = list(a.shape)
newshape[axis] = 1
slices = [slice(None)] * output.ndim
slices[axis] = 0
modes = output[tuple(slices)].reshape(newshape)
slices[axis] = 1
counts = output[tuple(slices)].reshape(newshape)
output = (modes, counts)
return ModeResult(*output)
Example #18
| Source File: mstats_basic.py From lambda-packs with MIT License | 4 votes |
|
def rankdata(data, axis=None, use_missing=False):
"""Returns the rank (also known as order statistics) of each data point
along the given axis.
If some values are tied, their rank is averaged.
If some values are masked, their rank is set to 0 if use_missing is False,
or set to the average rank of the unmasked values if use_missing is True.
Parameters
----------
data : sequence
Input data. The data is transformed to a masked array
axis : {None,int}, optional
Axis along which to perform the ranking.
If None, the array is first flattened. An exception is raised if
the axis is specified for arrays with a dimension larger than 2
use_missing : bool, optional
Whether the masked values have a rank of 0 (False) or equal to the
average rank of the unmasked values (True).
"""
def _rank1d(data, use_missing=False):
n = data.count()
rk = np.empty(data.size, dtype=float)
idx = data.argsort()
rk[idx[:n]] = np.arange(1,n+1)
if use_missing:
rk[idx[n:]] = (n+1)/2.
else:
rk[idx[n:]] = 0
repeats = find_repeats(data.copy())
for r in repeats[0]:
condition = (data == r).filled(False)
rk[condition] = rk[condition].mean()
return rk
data = ma.array(data, copy=False)
if axis is None:
if data.ndim > 1:
return _rank1d(data.ravel(), use_missing).reshape(data.shape)
else:
return _rank1d(data, use_missing)
else:
return ma.apply_along_axis(_rank1d,axis,data,use_missing).view(ndarray)
Example #19
| Source File: mstats_extras.py From Computable with MIT License | 4 votes |
|
def mjci(data, prob=[0.25,0.5,0.75], axis=None):
"""
Returns the Maritz-Jarrett estimators of the standard error of selected
experimental quantiles of the data.
Parameters
----------
data: ndarray
Data array.
prob: sequence
Sequence of quantiles to compute.
axis : int
Axis along which to compute the quantiles. If None, use a flattened
array.
"""
def _mjci_1D(data, p):
data = np.sort(data.compressed())
n = data.size
prob = (np.array(p) * n + 0.5).astype(int_)
betacdf = beta.cdf
#
mj = np.empty(len(prob), float_)
x = np.arange(1,n+1, dtype=float_) / n
y = x - 1./n
for (i,m) in enumerate(prob):
(m1,m2) = (m-1, n-m)
W = betacdf(x,m-1,n-m) - betacdf(y,m-1,n-m)
C1 = np.dot(W,data)
C2 = np.dot(W,data**2)
mj[i] = np.sqrt(C2 - C1**2)
return mj
#
data = ma.array(data, copy=False)
if data.ndim > 2:
raise ValueError("Array 'data' must be at most two dimensional, but got data.ndim = %d" % data.ndim)
p = np.array(prob, copy=False, ndmin=1)
# Computes quantiles along axis (or globally)
if (axis is None):
return _mjci_1D(data, p)
else:
return ma.apply_along_axis(_mjci_1D, axis, data, p)
#..............................................................................
Example #20
| Source File: mstats_extras.py From Computable with MIT License | 4 votes |
|
def hdquantiles_sd(data, prob=list([.25,.5,.75]), axis=None):
"""
The standard error of the Harrell-Davis quantile estimates by jackknife.
Parameters
----------
data : array_like
Data array.
prob : sequence
Sequence of quantiles to compute.
axis : int
Axis along which to compute the quantiles. If None, use a flattened
array.
Returns
-------
hdquantiles_sd : MaskedArray
Standard error of the Harrell-Davis quantile estimates.
"""
def _hdsd_1D(data,prob):
"Computes the std error for 1D arrays."
xsorted = np.sort(data.compressed())
n = len(xsorted)
#.........
hdsd = np.empty(len(prob), float_)
if n < 2:
hdsd.flat = np.nan
#.........
vv = np.arange(n) / float(n-1)
betacdf = beta.cdf
#
for (i,p) in enumerate(prob):
_w = betacdf(vv, (n+1)*p, (n+1)*(1-p))
w = _w[1:] - _w[:-1]
mx_ = np.fromiter([np.dot(w,xsorted[np.r_[list(range(0,k)),
list(range(k+1,n))].astype(int_)])
for k in range(n)], dtype=float_)
mx_var = np.array(mx_.var(), copy=False, ndmin=1) * n / float(n-1)
hdsd[i] = float(n-1) * np.sqrt(np.diag(mx_var).diagonal() / float(n))
return hdsd
# Initialization & checks ---------
data = ma.array(data, copy=False, dtype=float_)
p = np.array(prob, copy=False, ndmin=1)
# Computes quantiles along axis (or globally)
if (axis is None):
result = _hdsd_1D(data, p)
else:
if data.ndim > 2:
raise ValueError("Array 'data' must be at most two dimensional, but got data.ndim = %d" % data.ndim)
result = ma.apply_along_axis(_hdsd_1D, axis, data, p)
#
return ma.fix_invalid(result, copy=False).ravel()
#####--------------------------------------------------------------------------
#---- --- Confidence intervals ---
#####--------------------------------------------------------------------------
Example #21
| Source File: mstats_basic.py From Computable with MIT License | 4 votes |
|
def rankdata(data, axis=None, use_missing=False):
"""Returns the rank (also known as order statistics) of each data point
along the given axis.
If some values are tied, their rank is averaged.
If some values are masked, their rank is set to 0 if use_missing is False,
or set to the average rank of the unmasked values if use_missing is True.
Parameters
----------
data : sequence
Input data. The data is transformed to a masked array
axis : {None,int}, optional
Axis along which to perform the ranking.
If None, the array is first flattened. An exception is raised if
the axis is specified for arrays with a dimension larger than 2
use_missing : {boolean}, optional
Whether the masked values have a rank of 0 (False) or equal to the
average rank of the unmasked values (True).
"""
#
def _rank1d(data, use_missing=False):
n = data.count()
rk = np.empty(data.size, dtype=float)
idx = data.argsort()
rk[idx[:n]] = np.arange(1,n+1)
#
if use_missing:
rk[idx[n:]] = (n+1)/2.
else:
rk[idx[n:]] = 0
#
repeats = find_repeats(data.copy())
for r in repeats[0]:
condition = (data == r).filled(False)
rk[condition] = rk[condition].mean()
return rk
#
data = ma.array(data, copy=False)
if axis is None:
if data.ndim > 1:
return _rank1d(data.ravel(), use_missing).reshape(data.shape)
else:
return _rank1d(data, use_missing)
else:
return ma.apply_along_axis(_rank1d,axis,data,use_missing).view(ndarray)
#####--------------------------------------------------------------------------
#---- --- Central tendency ---
#####--------------------------------------------------------------------------
Example #22
| Source File: mstats_extras.py From lambda-packs with MIT License | 4 votes |
|
def mjci(data, prob=[0.25,0.5,0.75], axis=None):
"""
Returns the Maritz-Jarrett estimators of the standard error of selected
experimental quantiles of the data.
Parameters
----------
data : ndarray
Data array.
prob : sequence, optional
Sequence of quantiles to compute.
axis : int or None, optional
Axis along which to compute the quantiles. If None, use a flattened
array.
"""
def _mjci_1D(data, p):
data = np.sort(data.compressed())
n = data.size
prob = (np.array(p) * n + 0.5).astype(int_)
betacdf = beta.cdf
mj = np.empty(len(prob), float_)
x = np.arange(1,n+1, dtype=float_) / n
y = x - 1./n
for (i,m) in enumerate(prob):
W = betacdf(x,m-1,n-m) - betacdf(y,m-1,n-m)
C1 = np.dot(W,data)
C2 = np.dot(W,data**2)
mj[i] = np.sqrt(C2 - C1**2)
return mj
data = ma.array(data, copy=False)
if data.ndim > 2:
raise ValueError("Array 'data' must be at most two dimensional, "
"but got data.ndim = %d" % data.ndim)
p = np.array(prob, copy=False, ndmin=1)
# Computes quantiles along axis (or globally)
if (axis is None):
return _mjci_1D(data, p)
else:
return ma.apply_along_axis(_mjci_1D, axis, data, p)
Example #23
| Source File: mstats_extras.py From lambda-packs with MIT License | 4 votes |
|
def hdquantiles_sd(data, prob=list([.25,.5,.75]), axis=None):
"""
The standard error of the Harrell-Davis quantile estimates by jackknife.
Parameters
----------
data : array_like
Data array.
prob : sequence, optional
Sequence of quantiles to compute.
axis : int, optional
Axis along which to compute the quantiles. If None, use a flattened
array.
Returns
-------
hdquantiles_sd : MaskedArray
Standard error of the Harrell-Davis quantile estimates.
See Also
--------
hdquantiles
"""
def _hdsd_1D(data, prob):
"Computes the std error for 1D arrays."
xsorted = np.sort(data.compressed())
n = len(xsorted)
hdsd = np.empty(len(prob), float_)
if n < 2:
hdsd.flat = np.nan
vv = np.arange(n) / float(n-1)
betacdf = beta.cdf
for (i,p) in enumerate(prob):
_w = betacdf(vv, (n+1)*p, (n+1)*(1-p))
w = _w[1:] - _w[:-1]
mx_ = np.fromiter([np.dot(w,xsorted[np.r_[list(range(0,k)),
list(range(k+1,n))].astype(int_)])
for k in range(n)], dtype=float_)
mx_var = np.array(mx_.var(), copy=False, ndmin=1) * n / float(n-1)
hdsd[i] = float(n-1) * np.sqrt(np.diag(mx_var).diagonal() / float(n))
return hdsd
# Initialization & checks
data = ma.array(data, copy=False, dtype=float_)
p = np.array(prob, copy=False, ndmin=1)
# Computes quantiles along axis (or globally)
if (axis is None):
result = _hdsd_1D(data, p)
else:
if data.ndim > 2:
raise ValueError("Array 'data' must be at most two dimensional, "
"but got data.ndim = %d" % data.ndim)
result = ma.apply_along_axis(_hdsd_1D, axis, data, p)
return ma.fix_invalid(result, copy=False).ravel()
Example #24
| Source File: mstats_basic.py From lambda-packs with MIT License | 4 votes |
|
def mode(a, axis=0):
"""
Returns an array of the modal (most common) value in the passed array.
Parameters
----------
a : array_like
n-dimensional array of which to find mode(s).
axis : int or None, optional
Axis along which to operate. Default is 0. If None, compute over
the whole array `a`.
Returns
-------
mode : ndarray
Array of modal values.
count : ndarray
Array of counts for each mode.
Notes
-----
For more details, see `stats.mode`.
"""
a, axis = _chk_asarray(a, axis)
def _mode1D(a):
(rep,cnt) = find_repeats(a)
if not cnt.ndim:
return (0, 0)
elif cnt.size:
return (rep[cnt.argmax()], cnt.max())
else:
not_masked_indices = ma.flatnotmasked_edges(a)
first_not_masked_index = not_masked_indices[0]
return (a[first_not_masked_index], 1)
if axis is None:
output = _mode1D(ma.ravel(a))
output = (ma.array(output[0]), ma.array(output[1]))
else:
output = ma.apply_along_axis(_mode1D, axis, a)
newshape = list(a.shape)
newshape[axis] = 1
slices = [slice(None)] * output.ndim
slices[axis] = 0
modes = output[tuple(slices)].reshape(newshape)
slices[axis] = 1
counts = output[tuple(slices)].reshape(newshape)
output = (modes, counts)
return ModeResult(*output)
