Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Numeric fix for histograms with small binning #102

Merged
merged 1 commit into from
Aug 13, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 32 additions & 2 deletions src/lgdo/types/histogram.py
Original file line number Diff line number Diff line change
Expand Up @@ -75,8 +75,31 @@ def __init__(

@classmethod
def from_edges(
cls, edges: NDArray, binedge_attrs: dict[str, Any] | None = None
cls,
edges: NDArray | Iterable[float],
binedge_attrs: dict[str, Any] | None = None,
) -> Histogram.Axis:
"""Create a new axis with variable binning described by ``edges``."""
edges = np.array(edges)
return cls(edges, None, None, None, True, binedge_attrs)

@classmethod
def from_range_edges(
cls,
edges: NDArray | Iterable[float],
binedge_attrs: dict[str, Any] | None = None,
) -> Histogram.Axis:
"""Create a new axis from the binning described by ``edges``, but try to convert it to
a evenly-spaced range object first.

.. warning ::

This function might return a wrong binning, especially in the case of very small
magnitudes of the spacing. See the documentation of :func:`numpy.isclose` for
details. Use this function only with caution, if you know the binning's order of
magniutude.
"""
edges = np.array(edges)
edge_diff = np.diff(edges)
if np.any(~np.isclose(edge_diff, edge_diff[0])):
return cls(edges, None, None, None, True, binedge_attrs)
Expand Down Expand Up @@ -204,7 +227,14 @@ def __init__(
if not isinstance(ax, (hist.axis.Regular, hist.axis.Variable)):
msg = "only regular or variable axes of hist.Hist can be converted"
raise ValueError(msg)
b.append(Histogram.Axis.from_edges(ax.edges, binedge_attrs))
if isinstance(ax, hist.axis.Regular):
step = (ax.edges[-1] - ax.edges[0]) / ax.size
bax = Histogram.Axis(
None, ax.edges[0], ax.edges[-1], step, True, binedge_attrs
)
b.append(bax)
else:
b.append(Histogram.Axis.from_edges(ax.edges, binedge_attrs))
b = self._create_binning(b)
else:
if binning is None:
Expand Down
8 changes: 5 additions & 3 deletions tests/lh5/test_lh5_write.py
Original file line number Diff line number Diff line change
Expand Up @@ -434,8 +434,8 @@ def test_write_histogram(caplog, tmptestdir):
"my_group/my_histogram", f"{tmptestdir}/write_histogram_test.lh5"
)
assert np.array_equal(h3.weights.nda, np.array([[10, 10], [10, 10]]))
assert h3.binning[0].first == 2
assert h3.binning[1].last == 7
assert h3.binning[0].edges[0] == 2
assert h3.binning[1].edges[-1] == 7
assert h3.isdensity
assert h3.binning[0].get_binedgeattrs() == {"units": "ns"}

Expand Down Expand Up @@ -475,7 +475,9 @@ def test_write_histogram_variable(caplog, tmptestdir):
np.array([[10, 10], [10, 10]]),
(np.array([2, 3.5, 4]), np.array([5, 6.5, 7])),
isdensity=True,
) # Same field name, different values
)

# Same field name, different values
store = lh5.LH5Store()
store.write(
h1,
Expand Down
31 changes: 28 additions & 3 deletions tests/types/test_histogram.py
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,10 @@ def test_init_hist_regular():
h = Histogram(h, None)

assert len(h.binning) == 2
assert len(h.binning[0].edges) == 11
assert h.binning[0].first == 0
assert h.binning[0].last == 1
assert h.binning[0].step == 0.1

h = hist.Hist(hist.axis.Integer(start=0, stop=10))
with pytest.raises(ValueError, match="only regular or variable axes"):
Expand Down Expand Up @@ -92,7 +96,10 @@ def test_datatype_name():
def test_axes():
h = Histogram(
np.array([[1, 1], [1, 1]]),
(np.array([0, 1, 2]), np.array([2.1, 2.2, 2.3])),
(
Histogram.Axis.from_range_edges([0, 1, 2]),
Histogram.Axis.from_range_edges([2.1, 2.2, 2.3]),
),
attrs={"units": "m"},
)
assert len(h.binning) == 2
Expand All @@ -112,12 +119,25 @@ def test_axes():
assert np.isclose(ax1.step, 0.1)
assert isinstance(ax0.nbins, int)

h = Histogram(
np.array([[1, 1], [1, 1]]),
(np.array([0, 1, 2]), np.array([2.1, 2.2, 2.3])),
attrs={"units": "m"},
)
assert len(h.binning) == 2
str(h)
assert not h.binning[0].is_range
assert not h.binning[1].is_range

h = Histogram(
np.array([[1, 1], [1, 1]]),
[(1, 3, 1), (4, 6, 1)],
)
ax0 = h.binning[0]
str(h)
assert ax0.first == 1
assert ax0.last == 3
assert len(ax0.edges) == 3

h = Histogram(
np.array([[1, 1], [1, 1]]),
Expand Down Expand Up @@ -201,7 +221,7 @@ def test_ax_attributes():


def test_view_as_hist():
h = Histogram(np.array([1, 1]), (np.array([0, 1, 2]),))
h = Histogram(np.array([1, 1]), (Histogram.Axis.from_range_edges([0, 1, 2]),))
hi = h.view_as("hist")
assert isinstance(hi.axes[0], hist.axis.Regular)

Expand All @@ -220,9 +240,14 @@ def test_view_as_hist():
hi = h.view_as("hist")
assert isinstance(hi.axes[0], hist.axis.Variable)

# no auto-conversion from variable to regular.
h = Histogram(np.array([1, 1]), (np.array([0, 1, 2]),))
hi = h.view_as("hist")
assert isinstance(hi.axes[0], hist.axis.Variable)


def test_view_as_np():
h = Histogram(np.array([1, 1]), (np.array([0, 1, 2]),))
h = Histogram(np.array([1, 1]), (Histogram.Axis.from_range_edges([0, 1, 2]),))
assert h.binning[0].is_range
assert h.binning[0].nbins == 2
nda, axes = h.view_as("np")
Expand Down