[pull] master from stanfordmlgroup:master

.github/CODEOWNERS

@@ -0,0 +1 @@
+* ryan-wolbeck alejandroschuler tonyduan

.github/workflows/pythonpackage.yml

@@ -1,34 +1,27 @@
-name: Python package
+name: Python lint and test
 
-on: [push]
+on:
+  push:
+  pull_request:
+    branches:
+      - master
 
 jobs:
   build:
-
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.6, 3.7]
+        python-version: ['3.9', '3.10', '3.11', '3.12', '3.13']
 
     steps:
-    - uses: actions/checkout@v2
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v1
-      with:
-        python-version: ${{ matrix.python-version }}
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install -r requirements.txt
-        pip install -e .
-    - name: Lint with flake8
-      run: |
-        pip install flake8
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
-    - name: Test with pytest
-      run: |
-        pip install pytest
-        pytest
+      - uses: actions/checkout@v2
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v1
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: make install
+      - name: Run linters
+        run: make lint
+      - name: Run tests
+        run: make test

.gitignore

@@ -1,3 +1,6 @@
+# Pycharm
+.idea/
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
@@ -13,6 +16,8 @@ dist/
 downloads/
 eggs/
 .eggs/
+examples/user-guide/_build/
+examples/user-guide/.sass-cache/
 lib/
 lib64/
 parts/
@@ -107,3 +112,4 @@ venv.bak/
 *.pkl
 
 .DS_Store
+poetry.lock

.pre-commit-config.yaml

@@ -0,0 +1,45 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+
+default_stages: [pre-commit, manual]
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml # Checks yaml files for parsable syntax.
+      - id: check-json # Checks json files for parsable syntax.
+      - id: check-added-large-files # Checks for large files that bloat the git repository
+      - id: check-case-conflict # Check for files that would conflict in case-insensitive filesystems
+      - id: check-merge-conflict # Check for files that contain merge conflict strings.
+      - id: debug-statements # Check for debugger imports and py37+ `breakpoint()` calls in python source.
+  - repo: https://github.com/psf/black
+    rev: 24.10.0
+    hooks:
+      - id: black
+  - repo: local
+    hooks:
+      - id: isort
+        name: isort
+        types: [file, python]
+        language: system
+        entry: isort
+      - id: flake8
+        name: Flake8
+        types: [file, python]
+        language: system
+        files: ^ngboost
+        entry: flake8
+      - id: pylint-ngboost
+        name: pylint on ngboost*
+        types: [file, python]
+        language: system
+        files: ^ngboost
+        entry: pylint --disable=invalid-name,no-member,missing-docstring,no-self-argument,arguments-differ
+      - id: pylint-tests
+        name: pylint on tests*
+        language: system
+        files: ^tests
+        entry: pylint --disable=invalid-name,missing-docstring,too-many-function-args,unused-variable,fixme

LICENSE

@@ -199,4 +199,4 @@
    distributed under the License is distributed on an "AS IS" BASIS,
    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    See the License for the specific language governing permissions and
-   limitations under the License.
+   limitations under the License.

MANIFEST.in

@@ -0,0 +1 @@
+include LICENSE

Makefile

@@ -1,8 +1,18 @@
-all:
-	python3 -m pylint ngboost
-pkg:
-	python3 setup.py sdist bdist_wheel
+
+install:
+	pip install poetry==2.0.1 && poetry install
+
+package:
+	poetry build
+
+publish: package
+	source .env && poetry config pypi-token.pypi $$PYPI_TOKEN && poetry publish
+
+lint:
+	poetry run pre-commit run --hook-stage manual --all-files
+
+test:
+	poetry run pytest --slow -v
+
 clean:
-	rm -r build dist ngboost.egg-info
-upload:
-	twine upload dist/*
+	rm -rf dist/*

README.md

@@ -1,26 +1,45 @@
-![Python package](https://github.com/stanfordmlgroup/ngboost/workflows/Python%20package/badge.svg)
-
 # NGBoost: Natural Gradient Boosting for Probabilistic Prediction
 
-ngboost is a Python library that implements Natural Gradient Boosting, as described in ["NGBoost: Natural Gradient Boosting for Probabilistic Prediction"](https://stanfordmlgroup.github.io/projects/ngboost/). It is built on top of [Scikit-Learn](https://scikit-learn.org/stable/), and is designed to be scalable and modular with respect to choice of proper scoring rule, distribution, and base learners.
+<h4 align="center">
 
-Installation:
+![Python package](https://img.shields.io/pypi/v/ngboost)
+[![GitHub Repo Size](https://img.shields.io/github/repo-size/stanfordmlgroup/ngboost?label=Repo+Size)](https://github.com/stanfordmlgroup/ngboost/graphs/contributors)
+[![Github License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![PyPI](https://img.shields.io/pypi/v/ngboost?logo=pypi&logoColor=white)](https://pypi.org/project/ngboost)
+[![PyPI Downloads](https://img.shields.io/pypi/dm/ngboost?logo=icloud&logoColor=white)](https://pypistats.org/packages/ngboost)
 
-```
-pip install --upgrade git+https://github.com/stanfordmlgroup/ngboost.git
+</h4>
+
+ngboost is a Python library that implements Natural Gradient Boosting, as described in ["NGBoost: Natural Gradient Boosting for Probabilistic Prediction"](https://stanfordmlgroup.github.io/projects/ngboost/). It is built on top of [Scikit-Learn](https://scikit-learn.org/stable/), and is designed to be scalable and modular with respect to choice of proper scoring rule, distribution, and base learner. A didactic introduction to the methodology underlying NGBoost is available in this [slide deck](https://docs.google.com/presentation/d/1Tn23Su0ygR6z11jy3xVNiLGv0ggiUQue/edit?usp=share_link&ouid=102290675300480810195&rtpof=true&sd=true).
+
+## Installation
+
+```sh
+via pip
+
+pip install --upgrade ngboost
+
+via conda-forge
+
+conda install -c conda-forge ngboost
 ```
 
-Probabilistic regression example on the Boston housing dataset:
+## Usage
 
+Probabilistic regression example on the Boston housing dataset:
 
 ```python
 from ngboost import NGBRegressor
 
-from sklearn.datasets import load_boston
+from sklearn.datasets import fetch_california_housing
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import mean_squared_error
 
-X, Y = load_boston(True)
+# Load California housing dataset
+cal = fetch_california_housing()
+X, Y = cal.data, cal.target
+
 X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2)
 
 ngb = NGBRegressor().fit(X_train, Y_train)
@@ -36,6 +55,14 @@ test_NLL = -Y_dists.logpdf(Y_test).mean()
 print('Test NLL', test_NLL)
 ```
 
-More information about available distributions, scoring rules, learners, how to tune NGBoost models, and model interpretation is available in our [vignette](https://github.com/stanfordmlgroup/ngboost/blob/master/examples/vignette.ipynb). Please see our [developer guide](https://github.com/stanfordmlgroup/ngboost/blob/master/examples/dev_vignette.ipynb) for more information on how to add new distributions or scores to NGBoost.
+Details on available distributions, scoring rules, learners, tuning, and model interpretation are available in our [user guide](https://stanfordmlgroup.github.io/ngboost/intro.html), which also includes numerous usage examples and information on how to add new distributions or scores to NGBoost.
+
+## License
+
+[Apache License 2.0](https://github.com/stanfordmlgroup/ngboost/blob/master/LICENSE).
+
+## Reference
 
-A [slide deck](https://drive.google.com/file/d/183BWFAdFms81MKy6hSku8qI97OwS_JH_/view?usp=sharing) with an accessible presentation of how NGBoost works is also available.
+Tony Duan, Anand Avati, Daisy Yi Ding, Khanh K. Thai, Sanjay Basu, Andrew Y. Ng, Alejandro Schuler. 2019.
+NGBoost: Natural Gradient Boosting for Probabilistic Prediction.
+[arXiv](https://arxiv.org/abs/1910.03225)

RELEASE_NOTES.md

@@ -0,0 +1,70 @@
+# RELEASE NOTES
+
+## Version 0.5.8
+
+* Fix numpy2 natural gradient compatibility
+
+## Version 0.5.7
+
+* Support for Python 3.13
+* Update to dev dependencies
+
+## Version 0.5.6
+
+* Add support for Weibull and HalfNormal Distributions
+
+## Version 0.5.5
+
+* Upgrade sklearn > 1.6
+
+## Version 0.5.4
+
+* Update to partial fit to respect validation data
+
+## Version 0.5.3
+
+* Allow NAN as input
+* Poetry update
+
+## Version 0.5.2
+
+* Support for Numpy 2.0
+* Value error fix
+* Linting updates
+
+## Version 0.5.1
+
+* Adds support for NormalFixedMean distribution
+* Updates to makefile for easier publishing
+
+## Version 0.5.0
+
+* Drops support for python 3.7 and 3.8
+* Now supports Python 3.11 and 3.12
+* Fixed issue with np.bool
+* Optimized memory usage in pred-dist
+* Removed declared pandas dependency
+* Significant improvements to run times on tests during development
+* Minor enhancements to github actions
+
+## Version 0.4.2
+
+* Fix deprecated numpy type alias. This was causing a warning with NumPy >=1.20 and an error with NumPy >=1.24
+* Remove pandas as a declared dependency
+
+## Version 0.4.1
+
+### Added `partial_fit` method for incremental learning
+
+NGBoost now includes a new `partial_fit` method that allows for incremental learning. This method appends new base models to the existing ones, which can be useful when new data becomes available over time or when the data is too large to fit in memory all at once.
+
+The `partial_fit` method takes similar parameters to the `fit` method, including predictors `X`, outcomes `Y`, and validation sets `X_val` and `Y_val`. It also supports custom weights for the training and validation sets, as well as early stopping and custom loss monitoring.
+
+Please note that the `partial_fit` method is not yet fully tested and may not work as expected in all cases. Use it with caution and thoroughly test its behavior in your specific use case before relying on it in production.
+
+## Version 0.4.0
+
+* Added support for the gamma distribution
+* Added sklearn support to `set_params`
+* Fixed off-by-one issue for max trees
+* Upgraded version of `black` formatter to 22.8.0