loc=self._means[rr].T, scale=self._stds[rr].T).cdf(xr)).sum(axis=0)
def _updated_ctor_param(self):
"""
Set the bins as additional constructor argument
"""
dct = super(mixmod_gen, self)._updated_ctor_param()
dct['means'] = self._means
dct['stds'] = self._stds
dct['weights'] = self._weights
return dct
@classmethod
def add_mappings(cls):
"""
Add this classes mappings to the conversion dictionary
"""
cls._add_creation_method(cls.create, None)
cls._add_extraction_method(extract_mixmod_fit_samples, None)
mixmod = mixmod_gen.create
mixmod_gen.test_data = dict(mixmod=dict(gen_func=mixmod,\
ctor_data=dict(weights=WEIGHT_MIXMOD,\
means=MEAN_MIXMOD,\
stds=STD_MIXMOD),\
convert_data=dict(), test_xvals=TEST_XVALS,
atol_diff2=1.))
add_class(mixmod_gen)
def plot_native(cls, pdf, **kwargs):
"""Plot the PDF in a way that is particular to this type of distibution
For a histogram this shows the bin edges
"""
axes, _, kw = get_axes_and_xlims(**kwargs)
vals = pdf.dist.pdfs[pdf.kwds['row']]
return plot_pdf_histogram_on_axes(axes, hist=(pdf.dist.bins, vals), **kw)
@classmethod
def add_mappings(cls):
"""
Add this classes mappings to the conversion dictionary
"""
cls._add_creation_method(cls.create, None)
cls._add_extraction_method(extract_hist_values, None)
cls._add_extraction_method(extract_hist_samples, "samples")
hist = hist_gen.create
hist_gen.test_data = dict(hist=dict(gen_func=hist, ctor_data=dict(bins=XBINS, pdfs=HIST_DATA),\
convert_data=dict(bins=XBINS), atol_diff=1e-1, atol_diff2=1e-1, test_xvals=TEST_XVALS),
hist_samples=dict(gen_func=hist, ctor_data=dict(bins=XBINS, pdfs=HIST_DATA),\
convert_data=dict(bins=XBINS, method='samples',\
size=NSAMPLES),\
atol_diff=1e-1, atol_diff2=1e-1,\
test_xvals=TEST_XVALS, do_samples=True))
add_class(hist_gen)
@classmethod
def plot_native(cls, pdf, **kwargs):
"""Plot the PDF in a way that is particular to this type of distibution
For a interpolated PDF this uses the interpolation points
"""
axes, _, kw = get_axes_and_xlims(**kwargs)
xvals_row = pdf.dist.xvals
return plot_pdf_on_axes(axes, pdf, xvals_row, **kw)
@classmethod
def add_mappings(cls):
"""
Add this classes mappings to the conversion dictionary
"""
cls._add_creation_method(cls.create, None)
cls._add_extraction_method(extract_xy_vals, None)
cls._add_extraction_method(extract_xy_sparse, None)
interp_irregular = interp_irregular_gen.create
interp_irregular_gen.test_data = dict(interp_irregular=dict(gen_func=interp_irregular, ctor_data=dict(xvals=XARRAY, yvals=YARRAY),\
convert_data=dict(xvals=XBINS), test_xvals=TEST_XVALS))
interp_gen.test_data = dict(interp=dict(gen_func=interp, ctor_data=dict(xvals=XBINS, yvals=YARRAY),\
convert_data=dict(xvals=XBINS), test_xvals=TEST_XVALS))
add_class(interp_gen)
add_class(interp_irregular_gen)
dct['sig'] = self.sig
dct['dims'] = self.dims
return dct
@classmethod
def add_mappings(cls):
"""
Add this classes mappings to the conversion dictionary
"""
cls._add_creation_method(cls.create, None)
cls._add_extraction_method(extract_sparse_from_xy, None)
sparse = sparse_gen.create
add_class(sparse_gen)
def build_test_data():
"""build a test case out of real pdfs"""
qproot = sys.modules['qp'].__path__[0]
filein = os.path.join(qproot, '../docs/notebooks/CFHTLens_sample.P.npy')
#FORMAT FILE, EACH ROW IS THE PDF FOR EACH GALAXY, LAST ROW IS THE REDSHIFT POSITION
P = np.load(filein)
z = P[-1]
P = P[:NPDF]
P = P / sciint.trapz(P, z).reshape(-1, 1)
minz = np.min(z)
nz = 301
_, j = np.where(P > 0)
maxz = np.max(z[j + 1])
@classmethod
def add_mappings(cls):
"""
Add this classes mappings to the conversion dictionary
"""
cls._add_creation_method(cls.create, None)
cls._add_extraction_method(extract_quantiles, None)
quant = quant_gen.create
quant_gen.test_data = dict(quant=dict(gen_func=quant, ctor_data=dict(quants=QUANTS, locs=QLOCS),\
convert_data=dict(quants=QUANTS), test_xvals=TEST_XVALS))
add_class(quant_gen)
class quant_piecewise_gen(Pdf_rows_gen):
"""Quantile based distribution, where the PDF is defined piecewise from the quantiles
Notes
-----
This implements a CDF by interpolating a set of quantile values
It simply takes a set of x and y values and uses `scipy.interpolate.interp1d` to
build the CDF
"""
# pylint: disable=protected-access
name = 'quant_piecewise'