def test_from_and_to_hist():
h3 = hist.NamedHist(
hist.axis.Regular(25, -3.5, 3, name="x", flow=False),
hist.axis.Regular(21, -4, 5, name="y", flow=False),
storage=hist.storage.Weight(),
)
x2 = np.random.randn(1_000)
y2 = 0.5 * np.random.randn(1_000)
h3.fill(x=x2, y=y2)
from zfit._data.binneddatav1 import BinnedData
for _ in range(10): # make sure this works many times
h1 = BinnedData.from_hist(h3)
np.testing.assert_allclose(h1.variances(), h3.variances())
np.testing.assert_allclose(h1.values(), h3.values())
unbinned = h1.to_unbinned()
assert unbinned.value().shape[1] == 2
assert unbinned.value().shape[0] == unbinned.weights.shape[0]
h3recreated = h1.to_hist()
assert h3recreated == h3
bh3 = bh.Histogram(h1)
np.testing.assert_allclose(h1.variances(), bh3.variances())
np.testing.assert_allclose(h1.values(), bh3.values())
def __init__(
self,
data: ztyping.BinnedDataInputType,
extended: Optional[ztyping.ExtendedInputType] = None,
norm: Optional[ztyping.NormInputType] = None,
name: str = "HistogramPDF",
) -> None:
"""Binned PDF resembling a histogram.
Simple histogram PDF that can be used to model a histogram as a PDF.
Args:
data: Histogram to be used as PDF.
extended: |@doc:pdf.init.extended| The overall yield of the PDF.
If this is parameter-like, it will be used as the yield,
the expected number of events, and the PDF will be extended.
An extended PDF has additional functionality, such as the
`ext_*` methods and the `counts` (for binned PDFs). |@docend:pdf.init.extended|
|@doc:pdf.init.extended.auto| If `True`,
the PDF will be extended automatically if the PDF is extended
using the total number of events in the histogram.
This is the default. |@docend:pdf.init.extended.auto|
norm: |@doc:pdf.init.norm| Normalization of the PDF.
By default, this is the same as the default space of the PDF. |@docend:pdf.init.norm|
name: |@doc:model.init.name| Human-readable name
or label of
the PDF for better identification.
Has no programmatical functional purpose as identification. |@docend:model.init.name|
"""
if extended is None:
extended = True
if not isinstance(data, ZfitBinnedData):
if isinstance(data, PlottableHistogram):
from zfit._data.binneddatav1 import BinnedData
data = BinnedData.from_hist(data)
else:
raise TypeError(
"data must be of type PlottableHistogram (UHI) or ZfitBinnedData"
)
params = {}
if extended is True:
self._automatically_extended = True
extended = znp.sum(data.values())
else:
self._automatically_extended = False
super().__init__(obs=data.space,
extended=extended,
norm=norm,
params=params,
name=name)
self._data = data
def __init__(
self,
model: ztyping.BinnedPDFInputType,
data: ztyping.BinnedDataInputType,
constraints: ConstraintsInputType = None,
options: OptionsInputType = None,
):
model = convert_to_container(model)
data = convert_to_container(data)
from zfit._data.binneddatav1 import BinnedData
data = [
BinnedData.from_hist(d) if
(isinstance(d, PlottableHistogram)
and not isinstance(d, ZfitBinnedData)) else d for d in data
]
not_binned_pdf = [
mod for mod in model if not isinstance(mod, ZfitBinnedPDF)
]
not_binned_data = [
dat for dat in data if not isinstance(dat, ZfitBinnedData)
]
not_binned_pdf_msg = (
"The following PDFs are not binned but need to be. They can be wrapped in an "
f"BinnedFromUnbinnedPDF. {not_binned_pdf} ")
not_binned_data_msg = (
"The following datasets are not binned but need to be. They can be converted to a binned "
f"using the `to_binned` method. {not_binned_data}")
error_msg = ""
if not_binned_pdf:
error_msg += not_binned_pdf_msg
if not_binned_data:
error_msg += not_binned_data_msg
if error_msg:
raise ValueError(error_msg)
super().__init__(
model=model,
data=data,
constraints=constraints,
fit_range=None,
options=options,
)
def _convert_input_binned_x(self, x, none_is_space=None):
if x is None and none_is_space:
return self.space
if isinstance(x, uhi.typing.plottable.PlottableHistogram) and not isinstance(
x, ZfitBinnedData
):
x = BinnedData.from_hist(x)
if not isinstance(x, ZfitBinnedData):
if not isinstance(x, ZfitSpace):
if not isinstance(x, ZfitUnbinnedData):
try:
x = Data.from_tensor(obs=self.obs, tensor=x)
except Exception as error:
raise TypeError(
f"Data to {self} has to be Binned Data, not {x}. (It can also be unbinned Data)"
+ f" but conversion to it failed (see also above) with the following error:"
+ f" {error})"
) from error
# TODO: should we allow spaces? Or what?
return x
def test_from_and_to_binned():
h3 = hist.Hist(
hist.axis.Regular(3, -3, 3, name="x", flow=False),
hist.axis.Regular(2, -5, 5, name="y", flow=False),
storage=hist.storage.Weight(),
)
x2 = np.random.randn(1_000)
y2 = 0.5 * np.random.randn(1_000)
h3.fill(x=x2, y=y2)
from zfit._data.binneddatav1 import BinnedData
h1 = BinnedData.from_hist(h3)
for _ in range(10): # make sure this works many times
unbinned = h1.to_unbinned()
binned = unbinned.to_binned(space=h1.space)
np.testing.assert_allclose(binned.values(), h1.values())
# we can't test the variances, this info is lost
h1 = binned
bh3 = bh.Histogram(h1)
np.testing.assert_allclose(h1.values(), bh3.values())
def test_with_obs():
from zfit._data.binneddatav1 import BinnedData
h1 = hist.NamedHist(
hist.axis.Regular(25, -3.5, 3, name="x", flow=False),
hist.axis.Regular(21, -4, 5, name="y", flow=False),
hist.axis.Regular(15, -2, 1, name="z", flow=False),
storage=hist.storage.Weight(),
)
x2 = np.random.randn(1_000)
y2 = 0.5 * np.random.randn(1_000)
z2 = 0.3 * np.random.randn(1_000)
h1.fill(x=x2, y=y2, z=z2)
h = BinnedData.from_hist(h1)
obs = ("x", "y", "z")
obs2 = ("y", "x", "z")
assert obs == h.obs
h2 = h.with_obs(obs2)
assert h2.obs == obs2
np.testing.assert_allclose(h.values()[:, 3, 5], h2.values()[3, :, 5])
np.testing.assert_allclose(h.variances()[:, 3, 5], h2.variances()[3, :, 5])