Metadata-Version: 2.4
Name: thetaflow
Version: 0.0.40
Summary: Bridging the gap between Statistical Inference and Neural Networks
Author-email: Natan Hilario da Silva <natan.hilario@usp.br>
Project-URL: Homepage, https://github.com/nhilariosilva/thetaflow
Project-URL: Bug Tracker, https://github.com/nhilariosilva/thetaflow/issues
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Mathematics
Requires-Python: ==3.11.*
Description-Content-Type: text/markdown
Requires-Dist: tensorflow>=2.16.0
Requires-Dist: keras>=3.0.0
Requires-Dist: tf-keras
Requires-Dist: tensorflow_probability>=0.24.0
Requires-Dist: numpy<2.2.0,>=2.0.0
Requires-Dist: matplotlib==3.10.8
Requires-Dist: scipy>=1.10.0
Requires-Dist: pandas>=2.0.0
Requires-Dist: plotly>=5.0.0
Requires-Dist: tqdm>=4.60.0
Requires-Dist: ml-dtypes>=0.4.0

# Thetaflow

Bridging the gap between Statistical Inference and Deep Learning.

Thetaflow is a Python package built on top of TensorFlow/Keras designed to fully integrate statistical modeling with neural network components. It allows researchers and data scientists to define any statistical model where parameters can be:

Dynamic: Modeled as outputs of a complex neural network.
Static: Treated as independent, learnable weights (standard statistical coefficients).

It generalizes Maximum Likelihood Estimation (MLE) for a massive class of models, acting as a flexible optimizer that brings the power of backpropagation to rigorous statistical inference.

Key Features

- Flexible Parameter Definition: seamless mixing of deep learning outputs and scalar statistical parameters.
- Custom Likelihoods: Define any probability density function (PDF) or mass function (PMF) as your objective.
- TensorFlow/Keras Backend: leverages hardware acceleration (GPU/TPU) and automatic differentiation for complex optimization landscapes.
- General Optimizer: Solves for the Maximum Likelihood Estimate (MLE) across arbitrary model architectures.

## Installation

The easiest and recommended way to install `thetaflow` is directly from PyPI using `pip`:

```bash
pip install thetaflow
```

## Examples

An example application applying the standard simple linear regression model can be seen in the examples directory. I plan on adding further documentation! :)
