Merge branch 'main' into add-bayes-glm-model

statsmodels · Apr 27, 2024 · 40f2b72 · 40f2b72
2 parents a8b71db + c22837f
commit 40f2b72
Show file tree

Hide file tree

Showing 611 changed files with 4,973 additions and 2,197 deletions.
diff --git a/.github/workflows/codeql.yml b/.github/workflows/codeql.yml
@@ -31,7 +31,7 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v2
+      uses: github/codeql-action/init@v3
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -45,7 +45,7 @@ jobs:
     # Autobuild attempts to build any compiled languages  (C/C++, C#, Go, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@v2
+      uses: github/codeql-action/autobuild@v3
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
@@ -58,6 +58,6 @@ jobs:
     #   ./location_of_script_within_repo/buildscript.sh
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v2
+      uses: github/codeql-action/analyze@v3
       with:
         category: "/language:${{matrix.language}}"
diff --git a/.github/workflows/generate-documentation.yml b/.github/workflows/generate-documentation.yml
@@ -50,7 +50,7 @@ jobs:
     - name: Install pandoc
       uses: r-lib/actions/setup-pandoc@v2
     - name: Install graphviz
-      uses: ts-graphviz/setup-graphviz@v1
+      uses: ts-graphviz/setup-graphviz@v2
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v5
       with:

diff --git a/.gitignore b/.gitignore
@@ -70,6 +70,7 @@ coverage_html_report/
 
 # VS Code
 .vscode/
+.vs/
 
 # Project specific
 statsmodels/version.py

diff --git a/INSTALL.txt b/INSTALL.txt
@@ -1,23 +1,23 @@
 Dependencies
 ------------
 
-python >= 3.8
+python >= 3.9
 
     www.python.org
 
-numpy >= 1.18
+numpy >= 1.22
 
     www.numpy.org
 
-scipy >= 1.4
+scipy >= 1.7
 
     www.scipy.org
 
-pandas >= 1.0
+pandas >= 1.3
 
     pandas.pydata.org
 
-patsy >= 0.5.2
+patsy >= 0.5.5
 
     patsy.readthedocs.org
 

diff --git a/archive/docs/fix_longtable.py b/archive/docs/fix_longtable.py
@@ -7,7 +7,7 @@
 read_file_path = os.path.join(BUILDDIR,'latex','statsmodels.tex')
 write_file_path = os.path.join(BUILDDIR, 'latex','statsmodels_tmp.tex')
 
-read_file = open(read_file_path, 'r', encoding="utf-8")
+read_file = open(read_file_path, encoding="utf-8")
 write_file = open(write_file_path, 'w', encoding="utf-8")
 
 for line in read_file:

diff --git a/azure-pipelines.yml b/azure-pipelines.yml
@@ -20,17 +20,17 @@ variables:
 
 jobs:
 
-- template: tools/ci/azure/azure_template_windows.yml
+- template: tools/ci/azure/azure_template_posix.yml
   parameters:
-    name: Windows
-    vmImage: windows-latest
+    name: Linux
+    vmImage: ubuntu-latest
 
 - template: tools/ci/azure/azure_template_posix.yml
   parameters:
     name: macOS
     vmImage: macOS-latest
 
-- template: tools/ci/azure/azure_template_posix.yml
+- template: tools/ci/azure/azure_template_windows.yml
   parameters:
-    name: Linux
-    vmImage: ubuntu-latest
+    name: Windows
+    vmImage: windows-latest
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 #
 # statsmodels documentation build configuration file, created by
 # sphinx-quickstart on Sat Jan 22 11:17:58 2011.
@@ -296,8 +295,8 @@
 # (source start file, target name, title, author,
 # documentclass [howto/manual]).
 latex_documents = [
-    ('index', 'statsmodels.tex', u'statsmodels Documentation',
-     u'Josef Perktold, Skipper Seabold', 'manual'),
+    ('index', 'statsmodels.tex', 'statsmodels Documentation',
+     'Josef Perktold, Skipper Seabold', 'manual'),
 ]
 
 # The name of an image file (relative to this directory) to place at the top of
@@ -333,18 +332,18 @@
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
 man_pages = [
-    ('index', 'statsmodels', u'statsmodels Documentation',
-     [u'Josef Perktold, Skipper Seabold, Jonathan Taylor'], 1)
+    ('index', 'statsmodels', 'statsmodels Documentation',
+     ['Josef Perktold, Skipper Seabold, Jonathan Taylor'], 1)
 ]
 
 # Options for Epub output
 
 # Bibliographic Dublin Core info.
-epub_title = u'statsmodels'
-epub_author = u'Josef Perktold, Skipper Seabold'
-epub_publisher = u'Josef Perktold, Skipper Seabold'
-epub_copyright = u'2009-2023, Josef Perktold, Skipper Seabold, ' \
-                 u'Jonathan Taylor, statsmodels-developers'
+epub_title = 'statsmodels'
+epub_author = 'Josef Perktold, Skipper Seabold'
+epub_publisher = 'Josef Perktold, Skipper Seabold'
+epub_copyright = '2009-2023, Josef Perktold, Skipper Seabold, ' \
+                 'Jonathan Taylor, statsmodels-developers'
 
 # The language of the text. It defaults to the language option
 # or en if the language is not set.

diff --git a/docs/source/install.rst b/docs/source/install.rst
@@ -126,11 +126,11 @@ Dependencies
 
 The current minimum dependencies are:
 
-* `Python <https://www.python.org>`__ >= 3.8
-* `NumPy <https://www.scipy.org/>`__ >= 1.18
-* `SciPy <https://www.scipy.org/>`__ >= 1.4
-* `Pandas <https://pandas.pydata.org/>`__ >= 1.0
-* `Patsy <https://patsy.readthedocs.io/en/latest/>`__ >= 0.5.2
+* `Python <https://www.python.org>`__ >= 3.9
+* `NumPy <https://www.scipy.org/>`__ >= 1.22
+* `SciPy <https://www.scipy.org/>`__ >= 1.7
+* `Pandas <https://pandas.pydata.org/>`__ >= 1.3
+* `Patsy <https://patsy.readthedocs.io/en/latest/>`__ >= 0.5.5
 
 Cython is required to build from a git checkout but not to run or install from PyPI:
 

diff --git a/docs/source/optimization.rst b/docs/source/optimization.rst
@@ -47,7 +47,7 @@ associated with that specific optimizer:
       gtol : float
           Stop when norm of gradient is less than gtol.
       norm : float
-          Order of norm (np.Inf is max, -np.Inf is min)
+          Order of norm (np.inf is max, -np.inf is min)
       epsilon
           If fprime is approximated, use this value for the step
           size. Only relevant if LikelihoodModel.score is None.
@@ -87,7 +87,7 @@ associated with that specific optimizer:
       gtol : float
           Stop when norm of gradient is less than gtol.
       norm : float
-          Order of norm (np.Inf is max, -np.Inf is min)
+          Order of norm (np.inf is max, -np.inf is min)
       epsilon : float
           If fprime is approximated, use this value for the step
           size. Can be scalar or vector.  Only relevant if

diff --git a/docs/source/plots/graphics-mean_diff_plot.py b/docs/source/plots/graphics-mean_diff_plot.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # Test Bland-Altman
 """
 

diff --git a/docs/source/plots/graphics_boxplot_beanplot.py b/docs/source/plots/graphics_boxplot_beanplot.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """
 
 Created on Fri May 04 00:22:40 2012

diff --git a/docs/source/plots/graphics_boxplot_violinplot.py b/docs/source/plots/graphics_boxplot_violinplot.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """
 
 Created on Fri May 04 00:11:32 2012

diff --git a/docs/source/plots/graphics_correlation_plot_corr.py b/docs/source/plots/graphics_correlation_plot_corr.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """
 Create a plot of correlation among many variables in a grid
 

diff --git a/docs/source/plots/graphics_correlation_plot_corr_grid.py b/docs/source/plots/graphics_correlation_plot_corr_grid.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 '''
     In this example we just reuse the same correlation matrix several times.
     Of course in reality one would show a different correlation (measuring a

diff --git a/docs/source/plots/graphics_functional_fboxplot.py b/docs/source/plots/graphics_functional_fboxplot.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """
 
 Created on Fri May 04 11:10:51 2012

diff --git a/docs/source/plots/graphics_functional_hdrboxplot.py b/docs/source/plots/graphics_functional_hdrboxplot.py
@@ -1,5 +1,3 @@
-# coding: utf-8
-
 #Load the El Nino dataset.  Consists of 60 years worth of Pacific Ocean sea
 #surface temperature data.
 

diff --git a/docs/source/plots/graphics_functional_rainbowplot.py b/docs/source/plots/graphics_functional_rainbowplot.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """
 
 Created on Fri May 04 11:08:56 2012

diff --git a/docs/source/plots/graphics_gofplots_qqplot.py b/docs/source/plots/graphics_gofplots_qqplot.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """
 Created on Sun May 06 05:32:15 2012
 

diff --git a/docs/source/plots/graphics_mosaicplot_mosaic.py b/docs/source/plots/graphics_mosaicplot_mosaic.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 from itertools import product
 
 import matplotlib.pyplot as plt

diff --git a/docs/source/plots/graphics_plot_fit_ex.py b/docs/source/plots/graphics_plot_fit_ex.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """
 
 Created on Monday April 1st 2013

diff --git a/docs/source/plots/graphics_plot_grids_scatter_ellipse.py b/docs/source/plots/graphics_plot_grids_scatter_ellipse.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """
 Create of grid of scatter plots with confidence ellipses from the statecrime
 dataset

diff --git a/docs/source/plots/graphics_regression_abline.py b/docs/source/plots/graphics_regression_abline.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 '''
 Using the state crime dataset separately plot the effect of the each
 variable on the on the outcome, murder rate while accounting for the effect

diff --git a/docs/source/plots/graphics_regression_ccpr.py b/docs/source/plots/graphics_regression_ccpr.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 '''
 Using the state crime dataset plot the effect of the rate of single
 households ('single') on the murder rate while accounting for high school

diff --git a/docs/source/plots/graphics_regression_ccpr_grid.py b/docs/source/plots/graphics_regression_ccpr_grid.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 '''
 Using the state crime dataset separately plot the effect of the each
 variable on the on the outcome, murder rate while accounting for the effect

diff --git a/docs/source/plots/graphics_regression_ceres_residuals.py b/docs/source/plots/graphics_regression_ceres_residuals.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 '''
     Using a model built from the the state crime dataset, make a CERES plot
     with the rate of Poverty as the focus variable.

diff --git a/docs/source/plots/graphics_regression_influence.py b/docs/source/plots/graphics_regression_influence.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 '''
     Using a model built from the the state crime dataset, plot the influence in
     regression.  Observations with high leverage, or large residuals will be

diff --git a/docs/source/plots/graphics_regression_leverage_resid2.py b/docs/source/plots/graphics_regression_leverage_resid2.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 '''
     Using a model built from the the state crime dataset, plot the leverage
     statistics vs. normalized residuals squared.  Observations with

diff --git a/docs/source/plots/graphics_regression_partregress.py b/docs/source/plots/graphics_regression_partregress.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 '''
 Load the statewide dataset and plot partial regression of high school
 graduation on murder rate after removing the effects of rate of urbanization,

diff --git a/docs/source/plots/graphics_regression_partregress_grid.py b/docs/source/plots/graphics_regression_partregress_grid.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 '''
 Using the state crime dataset separately plot the effect of the each
 variable on the on the outcome, murder rate while accounting for the effect

diff --git a/docs/source/plots/graphics_regression_regress_exog.py b/docs/source/plots/graphics_regression_regress_exog.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 '''
 Load the Statewide Crime data set and build a model with regressors
 including the rate of high school graduation (hs_grad), population in urban

diff --git a/docs/source/plots/graphics_tsa_plot_acf.py b/docs/source/plots/graphics_tsa_plot_acf.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 '''
     Load Sunspots Data and plot the autocorrelation of the number of sunspots
     per year.

diff --git a/docs/source/plots/graphics_tsa_plot_pacf.py b/docs/source/plots/graphics_tsa_plot_pacf.py
@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 '''
     Load Sunspots Data and plot the partial autocorrelation of the number of
     sunspots per year.

diff --git a/examples/notebooks/ets.ipynb b/examples/notebooks/ets.ipynb
@@ -123,7 +123,7 @@
     "    549.8338,\n",
     "    542.3405,\n",
     "]\n",
-    "oil = pd.Series(oildata, index=pd.date_range(\"1965\", \"2013\", freq=\"AS\"))\n",
+    "oil = pd.Series(oildata, index=pd.date_range(\"1965\", \"2013\", freq=\"YS\"))\n",
     "oil.plot()\n",
     "plt.ylabel(\"Annual oil production in Saudi Arabia (Mt)\")"
    ]

diff --git a/examples/notebooks/exponential_smoothing.ipynb b/examples/notebooks/exponential_smoothing.ipynb
@@ -54,7 +54,7 @@
     "    514.2689,\n",
     "    494.211,\n",
     "]\n",
-    "index = pd.date_range(start=\"1996\", end=\"2008\", freq=\"A\")\n",
+    "index = pd.date_range(start=\"1996\", end=\"2008\", freq=\"Y\")\n",
     "oildata = pd.Series(data, index)\n",
     "\n",
     "data = [\n",
@@ -74,7 +74,7 @@
     "    41.3864,\n",
     "    41.5966,\n",
     "]\n",
-    "index = pd.date_range(start=\"1990\", end=\"2005\", freq=\"A\")\n",
+    "index = pd.date_range(start=\"1990\", end=\"2005\", freq=\"Y\")\n",
     "air = pd.Series(data, index)\n",
     "\n",
     "data = [\n",
@@ -110,11 +110,11 @@
     "    408.2705,\n",
     "    414.2428,\n",
     "]\n",
-    "index = pd.date_range(start=\"1970\", end=\"2001\", freq=\"A\")\n",
+    "index = pd.date_range(start=\"1970\", end=\"2001\", freq=\"Y\")\n",
     "livestock2 = pd.Series(data, index)\n",
     "\n",
     "data = [407.9979, 403.4608, 413.8249, 428.105, 445.3387, 452.9942, 455.7402]\n",
-    "index = pd.date_range(start=\"2001\", end=\"2008\", freq=\"A\")\n",
+    "index = pd.date_range(start=\"2001\", end=\"2008\", freq=\"Y\")\n",
     "livestock3 = pd.Series(data, index)\n",
     "\n",
     "data = [\n",

diff --git a/examples/notebooks/glm.ipynb b/examples/notebooks/glm.ipynb
@@ -159,7 +159,7 @@
     "means75.iloc[0] = lowinc_75per = stats.scoreatpercentile(data.exog.iloc[:,0], 75)\n",
     "resp_25 = res.predict(means25)\n",
     "resp_75 = res.predict(means75)\n",
-    "diff = resp_75 - resp_25"
+    "diff = resp_75 - resp_25\n"
    ]
   },
   {
@@ -174,9 +174,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "print(\"%2.4f%%\" % (diff*100))"
-   ]
+   "source": "print(\"%2.4f%%\" % (diff.iloc[0]*100))"
   },
   {
    "cell_type": "markdown",