def getview (self, view, pbar):
# {{{
import numpy as np
from pygeode.tools import loopover, npsum
out = np.zeros(view.shape, self.dtype)
W = np.zeros(view.shape, self.dtype)
for outsl, (indata, inw) in loopover([self.var, self.mweights], view, self.var.axes, pbar=pbar):
out[outsl] += npsum(indata * inw, self.indices) # Product of data and weights
f = indata.size / (inw.size * out[outsl].size)
W[outsl] += npsum(inw, self.indices) * f # Sum of weights
return out / W
def getview (self, view, pbar):
import numpy as np
from pygeode.tools import loopover, npsum
x = np.zeros(view.shape, self.dtype)
x2 = np.zeros(view.shape, self.dtype)
N = self.N
for outsl, (indata,) in loopover(self.var, view, pbar=pbar):
x[outsl] += npsum(indata, self.indices)
x2[outsl] += npsum(indata**2, self.indices)
x /= N
return (x2 - N*x**2) / (N - 1)
def getview(self, view, pbar):
import numpy as np
from pygeode.tools import loopover, npsum
x = np.zeros(view.shape, self.dtype)
x2 = np.zeros(view.shape, self.dtype)
N = self.N
for outsl, (indata, ) in loopover(self.var, view, pbar=pbar):
x[outsl] += npsum(indata, self.indices)
x2[outsl] += npsum(indata**2, self.indices)
x /= N
return (x2 - N * x**2) / (N - 1)
def getview (self, view, pbar):
# {{{
import numpy as np
from pygeode.tools import loopover, npsum
out = np.zeros(view.shape, self.dtype)
W = np.zeros(view.shape, self.dtype)
for outsl, (indata, inw) in loopover([self.var, self.mweights], view, self.var.axes, pbar=pbar):
out[outsl] += npsum(indata * inw, self.indices) # Product of data and weights
f = indata.size / (inw.size * out[outsl].size)
W[outsl] += npsum(inw, self.indices) * f # Sum of weights
return out / W
def getview (self, view, pbar):
import numpy as np
from pygeode.tools import loopover, npsum
out = np.zeros(view.shape, self.dtype)
for outsl, (indata,) in loopover(self.var, view, pbar=pbar):
out[outsl] += npsum(indata, self.indices)
return out
def getview(self, view, pbar):
import numpy as np
from pygeode.tools import loopover, npsum
out = np.zeros(view.shape, self.dtype)
for outsl, (indata, ) in loopover(self.var, view, pbar=pbar):
out[outsl] += npsum(indata, self.indices)
return out
def multiple_regress(Xs, Y, axes=None, N_fac=None, output='B,p', pbar=None):
# {{{
r'''Computes least-squares multiple regression of Y against variables Xs.
Parameters
==========
Xs : list of :class:`Var` instances
Variables to treat as independent regressors. Must have at least one axis
in common with each other and with Y.
Y : :class:`Var`
The dependent variable. Must have at least one axis in common with the Xs.
axes : list, optional
Axes over which to compute correlation; if nothing is specified, the correlation
is computed over all axes common to the Xs and Y.
N_fac : integer
A factor by which to rescale the estimated number of degrees of freedom; the effective
number will be given by the number estimated from the dataset divided by ``N_fac``.
output : string, optional
A string determining which parameters are returned; see list of possible outputs
in the Returns section. The specifications must be separated by a comma. Defaults
to 'B,p'.
pbar : progress bar, optional
A progress bar object. If nothing is provided, a progress bar will be displayed
if the calculation takes sufficiently long.
Returns
=======
results : tuple of floats or :class:`Var` instances.
The return values are specified by the ``output`` argument. The names of the
variables match the output request string (i.e. if ``ds`` is the returned dataset, the
linear coefficient of the regression can be obtained by ``ds.m``).
A fit of the form :math:`Y = \sum_i \beta_i X_i + \epsilon` is assumed.
Note that a constant term is not included by default. The following
parameters can be returned:
* 'B': Linear coefficients :math:`\beta_i` of each regressor
* 'r2': Fraction of the variance in Y explained by all Xs (:math:`R^2`)
* 'p': p-value of regession; see notes.
* 'sb': Standard deviation of each linear coefficient
* 'covb': Covariance matrix of the linear coefficients
* 'se': Standard deviation of residuals
The outputs 'B', 'p', and 'sb' will produce as many outputs as there are
regressors.
Notes
=====
The statistics described are computed following von Storch and Zwiers 1999,
section 8.4. The p-value 'p' is computed using the t-statistic appropriate
for the multi-variate normal estimator :math:`\hat{\vec{a}}` given in section
8.4.2; it corresponds to the probability of obtaining the regression
coefficient under the null hypothesis that there is no linear relationship.
Note this may not be the best way to determine if a given parameter is
contributing a significant fraction to the explained variance of Y. The
variances 'se' and 'sb' are :math:`\hat{\sigma}_E` and the square root of the
diagonal elements of :math:`\hat{\sigma}^2_E (\chi^T\chi)` in von Storch and
Zwiers, respectively. The data is assumed to be normally distributed.'''
from pygeode.tools import loopover, whichaxis, combine_axes, shared_axes, npsum
from pygeode.view import View
# Split output request now
ovars = ['beta', 'r2', 'p', 'sb', 'covb', 'se']
output = [o for o in output.split(',') if o in ovars]
if len(output) < 1:
raise ValueError(
'No valid outputs are requested from correlation. Possible outputs are %s.'
% str(ovars))
Nr = len(Xs)
Xaxes = combine_axes(Xs)
srcaxes = combine_axes([Xaxes, Y])
oiaxes, riaxes = shared_axes(srcaxes, [Xaxes, Y.axes])
if axes is not None:
ri_new = []
for a in axes:
ia = whichaxis(srcaxes, a)
if ia in riaxes: ri_new.append(ia)
else:
raise KeyError(
'One of the Xs or Y does not have the axis %s.' % a)
oiaxes.extend([r for r in riaxes if r not in ri_new])
riaxes = ri_new
oaxes = tuple([srcaxes[i] for i in oiaxes])
inaxes = oaxes + tuple([srcaxes[i] for i in riaxes])
oview = View(oaxes)
siaxes = list(range(len(oaxes), len(srcaxes)))
if pbar is None:
from pygeode.progress import PBar
pbar = PBar()
assert len(
riaxes) > 0, 'Regressors and %s share no axes to be regressed over' % (
Y.name)
# Construct work arrays
os = oview.shape
os1 = os + (Nr, )
os2 = os + (Nr, Nr)
y = np.zeros(os, 'd')
yy = np.zeros(os, 'd')
xy = np.zeros(os1, 'd')
xx = np.zeros(os2, 'd')
xxinv = np.zeros(os2, 'd')
N = np.prod([len(srcaxes[i]) for i in riaxes])
# Accumulate data
for outsl, datatuple in loopover(Xs + [Y], oview, inaxes, pbar=pbar):
ydata = datatuple[-1].astype('d')
xdata = [datatuple[i].astype('d') for i in range(Nr)]
y[outsl] += npsum(ydata, siaxes)
yy[outsl] += npsum(ydata**2, siaxes)
for i in range(Nr):
xy[outsl + (i, )] += npsum(xdata[i] * ydata, siaxes)
for j in range(i + 1):
xx[outsl + (i, j)] += npsum(xdata[i] * xdata[j], siaxes)
# Fill in opposite side of xTx
for i in range(Nr):
for j in range(i):
xx[..., j, i] = xx[..., i, j]
# Compute inverse of covariance matrix (could be done more intellegently? certainly the python
# loop over oview does not help)
xx = xx.reshape(-1, Nr, Nr)
xxinv = xxinv.reshape(-1, Nr, Nr)
for i in range(xx.shape[0]):
xxinv[i, :, :] = np.linalg.inv(xx[i, :, :])
xx = xx.reshape(os2)
xxinv = xxinv.reshape(os2)
beta = np.sum(xy.reshape(os + (1, Nr)) * xxinv, -1)
vare = np.sum(xy * beta, -1)
if N_fac is None: N_eff = N
else: N_eff = N // N_fac
sigbeta = [
np.sqrt((yy - vare) * xxinv[..., i, i] / N_eff) for i in range(Nr)
]
xns = [X.name if X.name != '' else 'X%d' % i for i, X in enumerate(Xs)]
yn = Y.name if Y.name != '' else 'Y'
from .var import Var
from .dataset import asdataset
from .axis import NonCoordinateAxis
ra = NonCoordinateAxis(values=np.arange(Nr),
regressor=xns,
name='regressor')
ra2 = NonCoordinateAxis(values=np.arange(Nr),
regressor=xns,
name='regressor2')
Nd = len(oaxes)
rvs = []
if 'beta' in output:
B = Var(oaxes + (ra, ), values=beta, name='beta')
B.atts['longname'] = 'regression coefficient'
rvs.append(B)
if 'r2' in output:
vary = (yy - y**2 / N)
R2 = 1 - (yy - vare) / vary
R2 = Var(oaxes, values=R2, name='R2')
R2.atts['longname'] = 'fraction of variance explained'
rvs.append(R2)
if 'p' in output:
p = [
2. *
(1. - tdist.cdf(np.abs(beta[..., i] / sigbeta[i]), N_eff - Nr))
for i in range(Nr)
]
p = np.transpose(np.array(p), [Nd] + list(range(Nd)))
p = Var(oaxes + (ra, ), values=p, name='p')
p.atts['longname'] = 'p-values'
rvs.append(p)
if 'sb' in output:
sigbeta = np.transpose(np.array(sigbeta), [Nd] + list(range(Nd)))
sb = Var(oaxes + (ra, ), values=sigbeta, name='sb')
sb.atts['longname'] = 'standard deviation of linear coefficients'
rvs.append(sb)
if 'covb' in output:
sigmat = np.zeros(os2, 'd')
for i in range(Nr):
for j in range(Nr):
#sigmat[..., i, j] = np.sqrt((yy - vare) * xxinv[..., i, j] / N_eff)
sigmat[..., i, j] = (yy - vare) * xxinv[..., i, j] / N_eff
covb = Var(oaxes + (ra, ra2), values=sigmat, name='covb')
covb.atts['longname'] = 'Covariance matrix of the linear coefficients'
rvs.append(covb)
if 'se' in output:
se = np.sqrt((yy - vare) / N_eff)
se = Var(oaxes, values=se, name='se')
se.atts['longname'] = 'standard deviation of residual'
rvs.append(se)
ds = asdataset(rvs)
ds.atts[
'description'] = 'multiple linear regression parameters for %s regressed against %s' % (
yn, xns)
return ds
def multiple_regress(Xs, Y, axes=None, pbar=None, N_fac=None, output='B,p'):
# {{{
r'''Computes least-squares multiple regression of Y against variables Xs.
Parameters
==========
Xs : list of :class:`Var` instances
Variables to treat as independent regressors. Must have at least one axis
in common with each other and with Y.
Y : :class:`Var`
The dependent variable. Must have at least one axis in common with the Xs.
axes : list, optional
Axes over which to compute correlation; if nothing is specified, the correlation
is computed over all axes common to the Xs and Y.
pbar : progress bar, optional
A progress bar object. If nothing is provided, a progress bar will be displayed
if the calculation takes sufficiently long.
N_fac : integer
A factor by which to rescale the estimated number of degrees of freedom; the effective
number will be given by the number estimated from the dataset divided by ``N_fac``.
output : string, optional
A string determining which parameters are returned; see list of possible outputs
in the Returns section. The specifications must be separated by a comma. Defaults
to 'B,p'.
Returns
=======
results : tuple of floats or :class:`Var` instances.
The return values are specified by the ``output`` argument. A fit of the form
:math:`Y = \sum_i \beta_i X_i + \epsilon` is assumed. Note that a constant term
is not included by default. The following parameters can be returned:
* 'B': Linear coefficients :math:`\beta_i` of each regressor
* 'r': Fraction of the variance in Y explained by all Xs (:math:`R^2`)
* 'p': Probability of this fit if the true linear coefficient was zero for each regressor
* 'sb': Standard deviation of each linear coefficient
* 'covb': Covariance matrix of the linear coefficients
* 'se': Standard deviation of residuals
If the regression is computed over all axes so that the result is a scalar,
the above are returned as a tuple of floats in the order specified by
``output``. Otherwise they are returned as :class:`Var` instances. The outputs
'B', 'p', and 'sb' will produce as many outputs as there are regressors.
Notes
=====
The statistics described are computed following von Storch and Zwiers 1999,
section 8.4. The p-value 'p' is computed using the t-statistic appropriate
for the multi-variate normal estimator :math:`\hat{\vec{a}}` given in section
8.4.2; note this may not be the best way to determine if a given parameter is
contributing a significant fraction to the explained variance of Y. The
variances 'se' and 'sb' are :math:`\hat{\sigma}_E` and the square root of the
diagonal elements of :math:`\hat{\sigma}^2_E (\chi^T\chi)` in von Storch and
Zwiers, respectively. The data is assumed to be normally distributed.'''
from pygeode.tools import loopover, whichaxis, combine_axes, shared_axes, npsum
from pygeode.view import View
Nr = len(Xs)
Xaxes = combine_axes(Xs)
srcaxes = combine_axes([Xaxes, Y])
oiaxes, riaxes = shared_axes(srcaxes, [Xaxes, Y.axes])
if axes is not None:
ri_new = []
for a in axes:
ia = whichaxis(srcaxes, a)
if ia in riaxes: ri_new.append(ia)
else: raise KeyError('One of the Xs or Y does not have the axis %s.' % a)
oiaxes.extend([r for r in riaxes if r not in ri_new])
riaxes = ri_new
oaxes = [srcaxes[i] for i in oiaxes]
inaxes = oaxes + [srcaxes[i] for i in riaxes]
oview = View(oaxes)
siaxes = list(range(len(oaxes), len(srcaxes)))
if pbar is None:
from pygeode.progress import PBar
pbar = PBar()
assert len(riaxes) > 0, 'Regressors and %s share no axes to be regressed over' % (Y.name)
# Construct work arrays
os = oview.shape
os1 = os + (Nr,)
os2 = os + (Nr,Nr)
y = np.zeros(os, 'd')
yy = np.zeros(os, 'd')
xy = np.zeros(os1, 'd')
xx = np.zeros(os2, 'd')
xxinv = np.zeros(os2, 'd')
N = np.prod([len(srcaxes[i]) for i in riaxes])
# Accumulate data
for outsl, datatuple in loopover(Xs + [Y], oview, inaxes, pbar=pbar):
ydata = datatuple[-1].astype('d')
xdata = [datatuple[i].astype('d') for i in range(Nr)]
y[outsl] += npsum(ydata, siaxes)
yy[outsl] += npsum(ydata**2, siaxes)
for i in range(Nr):
xy[outsl+(i,)] += npsum(xdata[i]*ydata, siaxes)
for j in range(i+1):
xx[outsl+(i,j)] += npsum(xdata[i]*xdata[j], siaxes)
# Fill in opposite side of xTx
for i in range(Nr):
for j in range(i):
xx[..., j, i] = xx[..., i, j]
# Compute inverse of covariance matrix (could be done more intellegently? certainly the python
# loop over oview does not help)
xx = xx.reshape(-1, Nr, Nr)
xxinv = xxinv.reshape(-1, Nr, Nr)
for i in range(xx.shape[0]):
xxinv[i,:,:] = np.linalg.inv(xx[i,:,:])
xx = xx.reshape(os2)
xxinv = xxinv.reshape(os2)
beta = np.sum(xy.reshape(os + (1, Nr)) * xxinv, -1)
vare = np.sum(xy * beta, -1)
if N_fac is None: N_eff = N
else: N_eff = N // N_fac
sigbeta = [np.sqrt((yy - vare) * xxinv[..., i, i] / N_eff) for i in range(Nr)]
xns = [X.name if X.name != '' else 'X%d' % i for i, X in enumerate(Xs)]
yn = Y.name if Y.name != '' else 'Y'
from pygeode.var import Var
output = output.split(',')
ret = []
for o in output:
if o == 'B':
if len(oaxes) == 0:
ret.append(beta)
else:
ret.append([Var(oaxes, values=beta[...,i], name='beta_%s' % xns[i]) for i in range(Nr)])
elif o == 'r':
vary = (yy - y**2/N)
R2 = 1 - (yy - vare) / vary
if len(oaxes) == 0:
ret.append(R2)
else:
ret.append(Var(oaxes, values=R2, name='R2'))
elif o == 'p':
ps = [tdist.cdf(np.abs(beta[...,i]/sigbeta[i]), N_eff-Nr) * np.sign(beta[...,i]) for i in range(Nr)]
if len(oaxes) == 0:
ret.append(ps)
else:
ret.append([Var(oaxes, values=ps[i], name='p_%s' % xns[i]) for i in range(Nr)])
elif o == 'sb':
if len(oaxes) == 0:
ret.append(sigbeta)
else:
ret.append([Var(oaxes, values=sigbeta[i], name='sig_%s' % xns[i]) for i in range(Nr)])
elif o == 'covb':
from .axis import NonCoordinateAxis as nca
cr1 = nca(values=list(range(Nr)), regressor1=[X.name for X in Xs], name='regressor1')
cr2 = nca(values=list(range(Nr)), regressor2=[X.name for X in Xs], name='regressor2')
sigmat = np.zeros(os2, 'd')
for i in range(Nr):
for j in range(Nr):
#sigmat[..., i, j] = np.sqrt((yy - vare) * xxinv[..., i, j] / N_eff)
sigmat[..., i, j] = (yy - vare) * xxinv[..., i, j] / N_eff
ret.append(Var(oaxes + [cr1, cr2], values=sigmat, name='smat'))
elif o == 'se':
se = np.sqrt((yy - vare) / N_eff)
if len(oaxes) == 0:
ret.append(se)
else:
ret.append(Var(oaxes, values=se, name='sig_resid'))
else:
print('multiple_regress: unrecognized output "%s"' % o)
return ret
def regress(X, Y, axes=None, pbar=None, N_fac=None, output='m,b,p'):
# {{{
r'''Computes least-squares linear regression of Y against X.
Parameters
==========
X, Y : :class:`Var`
Variables to regress. Must have at least one axis in common.
axes : list, optional
Axes over which to compute correlation; if nothing is specified, the correlation
is computed over all axes common to X and Y.
pbar : progress bar, optional
A progress bar object. If nothing is provided, a progress bar will be displayed
if the calculation takes sufficiently long.
N_fac : integer
A factor by which to rescale the estimated number of degrees of freedom; the effective
number will be given by the number estimated from the dataset divided by ``N_fac``.
output : string, optional
A string determining which parameters are returned; see list of possible outputs
in the Returns section. The specifications must be separated by a comma. Defaults
to 'm,b,p'.
Returns
=======
results : list of :class:`Var` instances.
The return values are specified by the ``output`` argument. A fit of the form
:math:`Y = m X + b + \epsilon` is assumed, and the following parameters
can be returned:
* 'm': Linear coefficient of the regression
* 'b': Constant coefficient of the regression
* 'r': Fraction of the variance in Y explained by X (:math:`R^2`)
* 'p': Probability of this fit if the true linear coefficient was zero
* 'sm': Variance in linear coefficient
* 'se': Variance of residuals
Notes
=====
The statistics described are computed following von Storch and Zwiers 1999,
section 8.3. The p-value 'p' is computed using the t-statistic given in
section 8.3.8, and confidence intervals for the slope and intercept can be
computed from 'se' and 'se' (:math:`\hat{\sigma}_E` and
:math:`\hat{\sigma}_E/\sqrt{S_{XX}}` in von Storch and Zwiers, respectively).
The data is assumed to be normally distributed.'''
from pygeode.tools import loopover, whichaxis, combine_axes, shared_axes, npsum
from pygeode.view import View
srcaxes = combine_axes([X, Y])
oiaxes, riaxes = shared_axes(srcaxes, [X.axes, Y.axes])
if axes is not None:
ri_new = []
for a in axes:
i = whichaxis(srcaxes, a)
if i not in riaxes:
raise KeyError('%s axis not shared by X ("%s") and Y ("%s")' % (a, X.name, Y.name))
ri_new.append(i)
oiaxes.extend([r for r in riaxes if r not in ri_new])
riaxes = ri_new
oaxes = [srcaxes[i] for i in oiaxes]
inaxes = oaxes + [srcaxes[i] for i in riaxes]
oview = View(oaxes)
siaxes = list(range(len(oaxes), len(srcaxes)))
if pbar is None:
from pygeode.progress import PBar
pbar = PBar()
assert len(riaxes) > 0, '%s and %s share no axes to be regressed over' % (X.name, Y.name)
# Construct work arrays
x = np.zeros(oview.shape, 'd')
y = np.zeros(oview.shape, 'd')
xx = np.zeros(oview.shape, 'd')
xy = np.zeros(oview.shape, 'd')
yy = np.zeros(oview.shape, 'd')
# Accumulate data
for outsl, (xdata, ydata) in loopover([X, Y], oview, inaxes, pbar=pbar):
xdata = xdata.astype('d')
ydata = ydata.astype('d')
x[outsl] += npsum(xdata, siaxes)
y[outsl] += npsum(ydata, siaxes)
xx[outsl] += npsum(xdata**2, siaxes)
yy[outsl] += npsum(ydata**2, siaxes)
xy[outsl] += npsum(xdata*ydata, siaxes)
N = np.prod([len(srcaxes[i]) for i in riaxes])
# remove the mean (NOTE: numerically unstable if mean >> stdev)
xx -= x**2/N
yy -= y**2/N
xy -= (x*y)/N
m = xy/xx
b = (y - m*x)/float(N)
if N_fac is None: N_eff = N
else: N_eff = N // N_fac
sige = (yy - m * xy) / (N_eff - 2.)
sigm = np.sqrt(sige / xx)
t = np.abs(m) / sigm
p = tdist.cdf(t, N-2) * np.sign(m)
xn = X.name if X.name != '' else 'X'
yn = Y.name if Y.name != '' else 'Y'
from pygeode.var import Var
output = output.split(',')
ret = []
if 'm' in output:
M = Var(oaxes, values=m, name='%s vs. %s' % (yn, xn))
ret.append(M)
if 'b' in output:
B = Var(oaxes, values=b, name='Intercept (%s vs. %s)' % (yn, xn))
ret.append(B)
if 'r' in output:
ret.append(Var(oaxes, values=xy**2/(xx*yy), name='R2(%s vs. %s)' % (yn, xn)))
if 'p' in output:
P = Var(oaxes, values=p, name='P(%s vs. %s != 0)' % (yn, xn))
ret.append(P)
if 'sm' in output:
ret.append(Var(oaxes, values=sigm, name='Sig. Intercept (%s vs. %s != 0)' % (yn, xn)))
if 'se' in output:
ret.append(Var(oaxes, values=np.sqrt(sige), name='Sig. Resid. (%s vs. %s != 0)' % (yn, xn)))
return ret
