Script 'mail_helper' called by obssrc
Hello community,
here is the log from the commit of package python-statsmodels for
openSUSE:Factory checked in at 2026-09-16 17:44:51
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Comparing /work/SRC/openSUSE:Factory/python-statsmodels (Old)
and /work/SRC/openSUSE:Factory/.python-statsmodels.new.383539 (New)
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "python-statsmodels"
Wed Sep 16 17:44:51 2026 rev:23 rq:1378231 version:0.15.0
Changes:
--------
--- /work/SRC/openSUSE:Factory/python-statsmodels/python-statsmodels.changes
2026-03-04 21:10:32.017629309 +0100
+++
/work/SRC/openSUSE:Factory/.python-statsmodels.new.383539/python-statsmodels.changes
2026-09-16 17:48:48.032200251 +0200
@@ -1,0 +2,71 @@
+Wed Sep 16 02:15:08 UTC 2026 - Steve Kowalik <[email protected]>
+
+- Update to 0.15.0:
+ * Outlier-robust covariance estimation.
+ * ccf can optionally return confidence intervals.
+ * Plot cross-correlations and the auto/cross-correlation matrix.
+ * Plot the prediction curve over a scatter plot in
+ GLMGamResults.plot_partial.
+ * Add MultivariateLS.
+ * Faster computation of state space revision impacts.
+ * Two-sample z-test, unequal-variances case.
+ * Improve lag selection in pacf.
+ * Add Cython 3 compatibility.
+ * GLM models now save the names of input pandas Series.
+ * Robust: additional tools and norms.
+ * Add CovDetMCD, CovDetMM, RLMDetSMM, and related estimators.
+ * Add a "one-sided" alternative for proportion_confint.
+ * Add an alternative option to confint_poisson.
+ * Add optional parameters to summary_col to indicate fixed effects.
+ * Ensure returned arrays are owned (not views).
+ * Improve precision of a diagnostic printout (mean_diff:.3g).
+ * Add the Leybourne-McCabe stationarity test.
+ * Add a sample-size calculation for Wilcoxon/Mann-Whitney tests.
+ * More reliable casting of pandas data.
+ * Add an abstracted formula engine supporting patsy and formulaic.
+ * x13_arima_analysis can produce seasonality fit diagnostics.
+ * Allow the ARDL model to use a "ctt" trend.
+ * Add plot keyword arguments to qqplot_2samples.
+ * x13_arima_analysis gained an optional raw spec parameter.
+ * Support array-like and pandas-like data more broadly.
+ * Add a “no cross terms” option to White’s heteroscedasticity test.
+ * Add a seasonal diagnostic plot to graphics.tsaplots.
+ * Make tsa.statespace Cython usage compatible with SciPy ILP64 builds.
+ * Allow seasonal-differencing-only models with non-seasonal estimators.
+ * Add add_ellipse to graphics, and support passing x/y arrays.
+ * Add order validation to the Hannan-Rissanen estimator.
+ * Consistently use rng to move towards SPEC-007.
+ * Add the partial cross-correlation function pccf and plot_pccf.
+ * Add the Hamilton filter.
+ * Add a delete-k (block) jackknife estimator.
+ * Allow pre-calculated error bands to be passed to the IRF plots.
+ * Support fixed_params in innovations_mle.
+ * Add a min_diag option to cov_nearest for zero or negative diagonal
+ entries.
+ * acf/pacf accept a list of lags in addition to maxlag.
+ * Return NamedTuple results in place of variable-length tuples.
+ * Accept Polars DataFrame/Series input in models and the formula API.
+ * Add the Jonckheere-Terpstra ordered trend test.
+ * Add the Diebold-Mariano test of equal predictive accuracy.
+ * Add the Pesaran-Timmermann test of directional predictive accuracy.
+ * Add local false discovery rate estimation (local_fdr_correction).
+ * Add LocalProjections, a Jorda local-projections estimator for impulse
+ response functions with Newey-West HAC standard errors.
+ * Implement an L1-penalized solver for GLM.
+ * Add CRV3 (cluster-jackknife) cluster-robust inference for OLS/ WLS.
+ * Warn when exog is (numerically) singular in the *LS model family, instead
+ of silently returning an unreliable fit.
+ * Make the ndim check in array_like orthogonal to maxdim, so the two can be
+ combined instead of one silently overriding the other.
+ * NominalGEE accepts non-numeric groups labels (for example strings),
+ instead of failing to cast them to float64 internally.
+ * Robust linear model (RLM) scale-estimator callables passed via scale_est
+ may now optionally accept the fitted model and residuals, in addition to
+ the previously-supported single-argument (residuals only) form, which
+ continues to work unchanged.
+ * Add fit_regularized to HurdleCountModel.
+ * MICEData is now iterable: each iteration step advances the chain by one
+ update cycle and yields the current imputed dataset, so
+ itertools.islice(mice_data, n) produces n successive imputed datasets.
+
+-------------------------------------------------------------------
Old:
----
statsmodels-0.14.6.tar.gz
New:
----
statsmodels-0.15.0.tar.gz
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Other differences:
------------------
++++++ python-statsmodels.spec ++++++
--- /var/tmp/diff_new_pack.oivAwu/_old 2026-09-16 17:48:50.984323548 +0200
+++ /var/tmp/diff_new_pack.oivAwu/_new 2026-09-16 17:48:50.989323757 +0200
@@ -27,7 +27,7 @@
%{?sle15_python_module_pythons}
Name: python-statsmodels%{psuffix}
-Version: 0.14.6
+Version: 0.15.0
Release: 0
Summary: A Python module that allows users to explore data
License: BSD-3-Clause
@@ -35,16 +35,17 @@
Source:
https://files.pythonhosted.org/packages/source/s/statsmodels/statsmodels-%{version}.tar.gz
BuildRequires: %{python_module Cython >= 3.0.10 with %python-Cython < 4}
BuildRequires: %{python_module devel >= 3.9}
-BuildRequires: %{python_module numpy-devel >= 1.22.3}
+BuildRequires: %{python_module meson-python}
+BuildRequires: %{python_module numpy-devel >= 2.0.0}
BuildRequires: %{python_module pip}
-BuildRequires: %{python_module scipy >= 1.8}
+BuildRequires: %{python_module scipy >= 1.13}
BuildRequires: %{python_module setuptools >= 0.69.0.2}
BuildRequires: %{python_module setuptools_scm >= 8}
BuildRequires: %{python_module wheel}
BuildRequires: fdupes
BuildRequires: gcc-fortran
BuildRequires: python-rpm-macros
-Requires: python-numpy >= 1.22.3
+Requires: python-numpy >= 1.23.5
Requires: python-packaging >= 21.3
Requires: python-pandas >= 1.4
Requires: python-patsy >= 0.5.6
@@ -60,6 +61,7 @@
# SECTION test requirements
BuildRequires: %{python_module Jinja2}
BuildRequires: %{python_module pytest >= 7.0.1}
+BuildRequires: %{python_module pytest-randomly}
BuildRequires: %{python_module pytest-xdist}
# /SECTION
%endif
@@ -78,14 +80,12 @@
%autosetup -p1 -n statsmodels-%{version}
rm -rf statsmodels/.pytest_cache
-find . -type f -name "*.py" -exec sed -i -e '1{/env python/ d}' -e 's/\r$//'
{} \;
-find . -type f -exec chmod a-x {} \;
+find . -type f -name "*.py" -not -path '*/_build/*' -exec sed -i -e '1{/env
python/ d}' -e 's/\r$//' {} \;
+find . -type f -not -path '*/_build/*' -exec chmod a-x {} \;
find . -type f -name "*.ipynb" -exec sed -i 's/\r$//' {} \;
find . -type f -name "*.csv" -exec sed -i 's/\r$//' {} \;
sed -i 's/\r$//' COPYRIGHTS.txt
sed -i 's/\r$//' LICENSE.txt
-sed -i 's/\r$//' README.rst
-sed -i 's/\r$//' README_l1.txt
%build
%if !%{with test}
@@ -106,7 +106,7 @@
testdir=/tmp/%{name}-testdir
rm -rf $testdir
mkdir $testdir
-cp setup.cfg $testdir
+cp pyproject.toml $testdir
pushd $testdir
# test results not packaged:
https://github.com/statsmodels/statsmodels/issues/8928, test_stl see below
donttest="test_mstl"
@@ -126,7 +126,7 @@
%if !%{with test}
%files %{python_files}
-%doc README.rst README_l1.txt
+%doc README.md
%doc examples/
%license COPYRIGHTS.txt LICENSE.txt
%{python_sitearch}/statsmodels/
++++++ statsmodels-0.14.6.tar.gz -> statsmodels-0.15.0.tar.gz ++++++
/work/SRC/openSUSE:Factory/python-statsmodels/statsmodels-0.14.6.tar.gz
/work/SRC/openSUSE:Factory/.python-statsmodels.new.383539/statsmodels-0.15.0.tar.gz
differ: char 5, line 1
