make release-tag: Merge branch 'master' into stable

amontanez24 · amontanez24 · commit 4b845513cf5c · 2023-08-10T16:03:13.000-05:00
diff --git a/.github/ISSUE_TEMPLATE/bug_report.md b/.github/ISSUE_TEMPLATE/bug_report.md
@@ -2,7 +2,7 @@
 name: Bug report
 about: Report an error that you found when using Copulas
 title: ''
-labels: bug, pending review
+labels: bug, new
 assignees: ''
 
 ---
diff --git a/.github/ISSUE_TEMPLATE/feature_request.md b/.github/ISSUE_TEMPLATE/feature_request.md
@@ -2,7 +2,7 @@
 name: Feature request
 about: Request a new feature that you would like to see implemented in Copulas
 title: ''
-labels: new feature, pending review
+labels: new feature, new
 assignees: ''
 
 ---
diff --git a/.github/ISSUE_TEMPLATE/question.md b/.github/ISSUE_TEMPLATE/question.md
@@ -2,7 +2,7 @@
 name: Question
 about: Doubts about Copulas usage
 title: ''
-labels: question, pending review
+labels: question, new
 assignees: ''
 
 ---
diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
@@ -3,16 +3,17 @@ name: Generate Docs
 on:
   push:
     branches: [ stable ]
+  workflow_dispatch:
 
 jobs:
   docs:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v2
-    - name: Set up Python 3.8
+    - name: Set up Python 3.9
       uses: actions/setup-python@v2
       with:
-        python-version: 3.8
+        python-version: 3.9
     - name: Build
       run: |
         sudo apt-get install pandoc
diff --git a/.github/workflows/end_to_end.yml b/.github/workflows/end_to_end.yml
@@ -10,7 +10,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ['3.7', '3.8', '3.9', '3.10', '3.11']
+        python-version: ['3.8', '3.9', '3.10', '3.11']
         os: [ubuntu-latest, macos-latest, windows-latest]
     steps:
     - uses: actions/checkout@v1
diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
@@ -10,10 +10,10 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v1
-    - name: Set up Python 3.8
+    - name: Set up Python 3.9
       uses: actions/setup-python@v2
       with:
-        python-version: 3.8
+        python-version: 3.9
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
diff --git a/.github/workflows/minimum.yml b/.github/workflows/minimum.yml
@@ -10,7 +10,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ['3.7', '3.8', '3.9', '3.10', '3.11']
+        python-version: ['3.8', '3.9', '3.10', '3.11']
         os: [ubuntu-latest, macos-latest, windows-latest]
     steps:
     - uses: actions/checkout@v1
diff --git a/.github/workflows/numerical.yml b/.github/workflows/numerical.yml
@@ -10,7 +10,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ['3.7', '3.8', '3.9', '3.10', '3.11']
+        python-version: ['3.8', '3.9', '3.10', '3.11']
         os: [ubuntu-latest, macos-latest, windows-latest]
     steps:
     - uses: actions/checkout@v1
diff --git a/.github/workflows/readme.yml b/.github/workflows/readme.yml
@@ -10,7 +10,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ['3.7', '3.8', '3.9', '3.10', '3.11']
+        python-version: ['3.8', '3.9', '3.10', '3.11']
         os: [ubuntu-latest, macos-latest]
     steps:
     - uses: actions/checkout@v1
diff --git a/.github/workflows/tutorials.yml b/.github/workflows/tutorials.yml
@@ -10,7 +10,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ['3.7', '3.8', '3.9', '3.10', '3.11']
+        python-version: ['3.8', '3.9', '3.10', '3.11']
     steps:
     - uses: actions/checkout@v1
     - name: Set up Python ${{ matrix.python-version }}
diff --git a/.github/workflows/unit.yml b/.github/workflows/unit.yml
@@ -10,7 +10,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ['3.7', '3.8', '3.9', '3.10', '3.11']
+        python-version: ['3.8', '3.9', '3.10', '3.11']
         os: [ubuntu-latest, macos-latest, windows-latest]
     steps:
     - uses: actions/checkout@v1
diff --git a/AUTHORS.rst b/AUTHORS.rst
@@ -1 +1,4 @@
+Authors
+=======
+
 See: https://github.com/sdv-dev/Copulas/graphs/contributors
diff --git a/HISTORY.md b/HISTORY.md
@@ -1,5 +1,28 @@
 # History
 
+## v0.9.1 - 2023-08-10
+
+This release fixes problems with the documentation site and drops support for Python 3.7.
+
+### Maintenance
+
+* Drop support for Python 3.7 - Issue [#355](https://github.com/sdv-dev/Copulas/issues/355) by @amontanez24
+
+### Documentation
+
+* Formatting is broken on the main docs page - Issue [#341](https://github.com/sdv-dev/Copulas/issues/341) by @amontanez24
+
+## v0.9.0 - 2023-04-26
+
+This release adds support for pandas 2.0 and above. Additionally adds a functionality to find
+version add-ons and renames ``covariance`` to ``correlation``.
+
+### Maintenance
+
+* Remove upper bound for pandas - Issue[#349](https://github.com/sdv-dev/Copulas/issues/349) by @pvk-developer
+* Rename covariance to correlation - PR[#346](https://github.com/sdv-dev/Copulas/pull/346) by @frances-h
+* Add functionality to find version add-on - Issue[#349](https://github.com/sdv-dev/Copulas/issues/349) by @frances-h
+
 ## v0.8.0 - 2023-01-06
 
 This release adds support for python 3.10 and 3.11. Additionally, it drops support for python 3.6.
@@ -12,7 +35,7 @@ This release adds support for python 3.10 and 3.11. Additionally, it drops suppo
 
 ## v0.7.0 - 2022-05-10
 
-This release adds `gaussian` as a fallback distribution in case the user specified one fails. It also improves the `fit` of the `beta` distribution by properly estimatig the `loc` and `scale` parameters.
+This release adds `gaussian` as a fallback distribution in case the user specified one fails. It also improves the `fit` of the `beta` distribution by properly estimating the `loc` and `scale` parameters.
 
 ### General Improvements
 
diff --git a/INSTALL.md b/INSTALL.md
@@ -3,7 +3,7 @@
 ## Requirements
 
 **Copulas** has been developed and tested on
-[Python 3.7, 3.8, 3.9, 3.10 and 3.11](https://www.python.org/downloads/)
+[Python 3.8, 3.9, 3.10 and 3.11](https://www.python.org/downloads/)
 
 Also, although it is not strictly required, the usage of a [virtualenv](
 https://virtualenv.pypa.io/en/latest/) is highly recommended in order to avoid
diff --git a/README.md b/README.md
@@ -1,6 +1,4 @@
-<div align="center">
-<br/>
-<p align="center">
+<p style="text-align:center">
     <i>This repository is part of <a href="https://sdv.dev">The Synthetic Data Vault Project</a>, a project from <a href="https://datacebo.com">DataCebo</a>.</i>
 </p>
 
@@ -11,16 +9,12 @@
 [![Coverage Status](https://codecov.io/gh/sdv-dev/Copulas/branch/master/graph/badge.svg)](https://codecov.io/gh/sdv-dev/Copulas)
 [![Slack](https://img.shields.io/badge/Community-Slack-blue?style=plastic&logo=slack)](https://bit.ly/sdv-slack-invite)
 
-<div align="left">
 <br/>
-<p align="center">
+<p align="center" style="text-align:center">
 <a href="https://github.com/sdv-dev/Copulas">
-<img align="center" width=40% src="https://github.com/sdv-dev/SDV/blob/master/docs/images/Copulas-DataCebo.png"></img>
+<img width=40% src="https://github.com/sdv-dev/SDV/blob/master/docs/images/Copulas-DataCebo.png?raw=true"></img>
 </a>
 </p>
-</div>
-
-</div>
 
 # Overview
 
diff --git a/copulas/__init__.py b/copulas/__init__.py
@@ -4,7 +4,7 @@
 
 __author__ = 'DataCebo, Inc.'
 __email__ = 'info@sdv.dev'
-__version__ = '0.8.0'
+__version__ = '0.9.1.dev1'
 
 import contextlib
 import importlib
@@ -13,6 +13,10 @@
 import numpy as np
 import pandas as pd
 
+from copulas._addons import _find_addons
+
+_find_addons(group='copulas_modules', parent_globals=globals())
+
 EPSILON = np.finfo(np.float32).eps
 
 
diff --git a/copulas/_addons.py b/copulas/_addons.py
@@ -0,0 +1,26 @@
+"""Copulas add-ons functionality."""
+import warnings
+
+from pkg_resources import iter_entry_points
+
+
+def _find_addons(group, parent_globals):
+    """Find and load add-ons based on the given group.
+
+    Args:
+        group (str):
+            The name of the entry points group to load.
+        parent_globals (dict):
+            The caller's global scope. Modules will be added
+            to the parent's global scope through their name.
+    """
+    for entry_point in iter_entry_points(group=group):
+        try:
+            module = entry_point.load()
+        except Exception:
+            msg = f'Failed to load "{entry_point.name}" from "{entry_point.module}".'
+            warnings.warn(msg)
+            continue
+
+        if entry_point.name not in parent_globals:
+            parent_globals[entry_point.name] = module
diff --git a/copulas/multivariate/gaussian.py b/copulas/multivariate/gaussian.py
@@ -28,7 +28,7 @@ class GaussianMultivariate(Multivariate):
             distribution names.
     """
 
-    covariance = None
+    correlation = None
     columns = None
     univariates = None
 
@@ -65,29 +65,29 @@ def _transform_to_normal(self, X):
 
         return stats.norm.ppf(np.column_stack(U))
 
-    def _get_covariance(self, X):
-        """Compute covariance matrix with transformed data.
+    def _get_correlation(self, X):
+        """Compute correlation matrix with transformed data.
 
         Args:
             X (numpy.ndarray):
-                Data for which the covariance needs to be computed.
+                Data for which the correlation needs to be computed.
 
         Returns:
             numpy.ndarray:
-                computed covariance matrix.
+                computed correlation matrix.
         """
         result = self._transform_to_normal(X)
-        covariance = pd.DataFrame(data=result).corr().to_numpy()
-        covariance = np.nan_to_num(covariance, nan=0.0)
+        correlation = pd.DataFrame(data=result).corr().to_numpy()
+        correlation = np.nan_to_num(correlation, nan=0.0)
         # If singular, add some noise to the diagonal
-        if np.linalg.cond(covariance) > 1.0 / sys.float_info.epsilon:
-            covariance = covariance + np.identity(covariance.shape[0]) * EPSILON
+        if np.linalg.cond(correlation) > 1.0 / sys.float_info.epsilon:
+            correlation = correlation + np.identity(correlation.shape[0]) * EPSILON
 
-        return pd.DataFrame(covariance, index=self.columns, columns=self.columns)
+        return pd.DataFrame(correlation, index=self.columns, columns=self.columns)
 
     @check_valid_values
     def fit(self, X):
-        """Compute the distribution for each variable and then its covariance matrix.
+        """Compute the distribution for each variable and then its correlation matrix.
 
         Arguments:
             X (pandas.DataFrame):
@@ -126,8 +126,8 @@ def fit(self, X):
         self.columns = columns
         self.univariates = univariates
 
-        LOGGER.debug('Computing covariance')
-        self.covariance = self._get_covariance(X)
+        LOGGER.debug('Computing correlation')
+        self.correlation = self._get_correlation(X)
         self.fitted = True
 
         LOGGER.debug('GaussianMultivariate fitted successfully')
@@ -149,7 +149,7 @@ def probability_density(self, X):
         """
         self.check_fit()
         transformed = self._transform_to_normal(X)
-        return stats.multivariate_normal.pdf(transformed, cov=self.covariance)
+        return stats.multivariate_normal.pdf(transformed, cov=self.correlation)
 
     def cumulative_distribution(self, X):
         """Compute the cumulative distribution value for each point in X.
@@ -168,7 +168,7 @@ def cumulative_distribution(self, X):
         """
         self.check_fit()
         transformed = self._transform_to_normal(X)
-        return stats.multivariate_normal.cdf(transformed, cov=self.covariance)
+        return stats.multivariate_normal.cdf(transformed, cov=self.correlation)
 
     def _get_conditional_distribution(self, conditions):
         """Compute the parameters of a conditional multivariate normal distribution.
@@ -192,12 +192,12 @@ def _get_conditional_distribution(self, conditions):
                     names of the columns that will be sampled conditionally.
         """
         columns2 = conditions.index
-        columns1 = self.covariance.columns.difference(columns2)
+        columns1 = self.correlation.columns.difference(columns2)
 
-        sigma11 = self.covariance.loc[columns1, columns1].to_numpy()
-        sigma12 = self.covariance.loc[columns1, columns2].to_numpy()
-        sigma21 = self.covariance.loc[columns2, columns1].to_numpy()
-        sigma22 = self.covariance.loc[columns2, columns2].to_numpy()
+        sigma11 = self.correlation.loc[columns1, columns1].to_numpy()
+        sigma12 = self.correlation.loc[columns1, columns2].to_numpy()
+        sigma21 = self.correlation.loc[columns2, columns1].to_numpy()
+        sigma22 = self.correlation.loc[columns2, columns2].to_numpy()
 
         mu1 = np.zeros(len(columns1))
         mu2 = np.zeros(len(columns2))
@@ -220,7 +220,7 @@ def _get_normal_samples(self, num_rows, conditions):
         a standard normal multivariate conditioned on the given condition values.
         """
         if conditions is None:
-            covariance = self.covariance
+            covariance = self.correlation
             columns = self.columns
             means = np.zeros(len(columns))
         else:
@@ -277,11 +277,9 @@ def to_dict(self):
         """
         self.check_fit()
         univariates = [univariate.to_dict() for univariate in self.univariates]
-        warnings.warn('`covariance` will be renamed to `correlation` in v0.4.0',
-                      DeprecationWarning)
 
         return {
-            'covariance': self.covariance.to_numpy().tolist(),
+            'correlation': self.correlation.to_numpy().tolist(),
             'univariates': univariates,
             'columns': self.columns,
             'type': get_qualified_name(self),
@@ -308,10 +306,8 @@ def from_dict(cls, copula_dict):
         for parameters in copula_dict['univariates']:
             instance.univariates.append(Univariate.from_dict(parameters))
 
-        covariance = copula_dict['covariance']
-        instance.covariance = pd.DataFrame(covariance, index=columns, columns=columns)
+        correlation = copula_dict['correlation']
+        instance.correlation = pd.DataFrame(correlation, index=columns, columns=columns)
         instance.fitted = True
-        warnings.warn('`covariance` will be renamed to `correlation` in v0.4.0',
-                      DeprecationWarning)
 
         return instance
diff --git a/copulas/multivariate/vine.py b/copulas/multivariate/vine.py
@@ -71,8 +71,8 @@ class VineCopula(Multivariate):
     def __init__(self, vine_type, random_state=None):
         if sys.version_info > (3, 8):
             warnings.warn(
-                'Vines have not been fully tested on Python 3.8 and might '
-                'produce wrong results. Please use Python 3.5, 3.6 or 3.7'
+                'Vines have not been fully tested on Python >= 3.8 and might '
+                'produce wrong results.'
             )
 
         self.random_state = validate_random_state(random_state)
diff --git a/docs/index.rst b/docs/index.rst
@@ -1,5 +1,5 @@
 .. mdinclude:: ../README.md
-   :end-line: 62
+   :end-line: 48
 
 .. toctree::
    :hidden:
diff --git a/setup.cfg b/setup.cfg
@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.8.0
+current_version = 0.9.1.dev1
 commit = True
 tag = True
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?
diff --git a/setup.py b/setup.py
diff --git a/tests/unit/multivariate/test_gaussian.py b/tests/unit/multivariate/test_gaussian.py
diff --git a/tests/unit/test__addons.py b/tests/unit/test__addons.py
diff --git a/tox.ini b/tox.ini
diff --git a/tutorials/03_Multivariate_Distributions.ipynb b/tutorials/03_Multivariate_Distributions.ipynb
