-
Notifications
You must be signed in to change notification settings - Fork 2
Commit
- Loading branch information
There are no files selected for viewing
This file was deleted.
This file was deleted.
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -2,7 +2,7 @@ | |
Changelog | ||
========= | ||
|
||
0.0.0 (2024-02-12) | ||
0.0.0 (2024-06-11) | ||
------------------ | ||
|
||
* First release on PyPI. |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,52 +1,52 @@ | ||
======== | ||
Overview | ||
======== | ||
==================== | ||
Treeffuser | ||
==================== | ||
|
||
Diffusion but trees | ||
Treeffuser is an easy-to-use package for probabilistic prediction on tabular data with tree-based diffusion models. | ||
Its goal is to estimate distributions of the form `p(y|x)` where `x` is a feature vector, `y` is a target vector | ||
and the form of `p(y|x)` can be arbitrarily complex (e.g multimodal, heteroskedastic, non-gaussian, heavy-tailed, etc). | ||
|
||
* Free software: MIT license | ||
It is designed to adhere closely to the scikit-learn API and requires minimal user tuning. | ||
|
||
Installation | ||
============ | ||
|
||
:: | ||
|
||
pip install treeffuser | ||
|
||
You can also install the in-development version with:: | ||
Usage Example | ||
------------- | ||
|
||
pip install git+ssh://git@https://github.com/blei-lab/tree-diffuser/blei-lab/treeffuser.git@main | ||
Here's how you can use Treeffuser in your project: | ||
|
||
Documentation | ||
============= | ||
.. code-block:: python | ||
from treeffuser import LightGBMTreeffuser | ||
import numpy as np | ||
https://treeffuser.readthedocs.io/ | ||
# (n_training, n_features), (n_training, n_targets) | ||
X, y = ... # load your data | ||
# (n_test, n_features) | ||
X_test = ... # load your test data | ||
# Estimate p(y|x) with a tree-based diffusion model | ||
model = LightGBMTreeffuser() | ||
model.fit(X, y) | ||
Development | ||
=========== | ||
# Draw samples y ~ p(y|x) for each test point | ||
# (n_samples, n_test, n_targets) | ||
y_samples = model.sample(X_test, n_samples=1000) | ||
To run all the tests run:: | ||
# Compute downstream metrics | ||
mean = np.mean(y_samples, axis=0) | ||
std = np.std(y_samples, axis=0) | ||
median = np.median(y_samples, axis=0) | ||
quantile = np.quantile(y_samples, q=0 axis=0) | ||
... # other metrics | ||
tox | ||
Please refer to the docstrings for more information on the available methods and parameters. | ||
|
||
However, this is usually excessive so it is easier to use pytest with | ||
your environment. When you push tox will run automatically. | ||
|
||
Note, to combine the coverage data from all the tox environments run: | ||
|
||
.. list-table:: | ||
:widths: 10 90 | ||
:stub-columns: 1 | ||
Installation | ||
============ | ||
|
||
- - Windows | ||
- :: | ||
You can install Treeffuser via pip from PyPI with the following command:: | ||
|
||
set PYTEST_ADDOPTS=--cov-append | ||
tox | ||
pip install treeffuser | ||
|
||
- - Other | ||
- :: | ||
You can also install the in-development version with:: | ||
|
||
PYTEST_ADDOPTS=--cov-append tox | ||
pip install git+https://github.com/blei-lab/tree-diffuser.git@main |
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.
This file was deleted.