Metadata-Version: 2.1
Name: labml-python-autocomplete
Version: 0.0.2
Summary: A simple model that learns to predict Python source code
Home-page: https://github.com/lab-ml/python_autocomplete
Author: Varuna Jayasiri
Author-email: vpjayasiri@gmail.com
License: UNKNOWN
Project-URL: Documentation, https://lab-ml.com/
Keywords: machine learning
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Mathematics
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development
Classifier: Topic :: Software Development :: Libraries
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Description-Content-Type: text/markdown
Requires-Dist: labml (>=0.4.74)
Requires-Dist: labml-helpers (>=0.4.70)
Requires-Dist: labml-nn (>=0.4.70torch)
Requires-Dist: einops
Requires-Dist: numpy

# Source Code Modeling

This repo trains deep learning models on source code.

### Try it yourself

1. Clone this repo
2. Install requirements from `requirements.txt`
3. Run `python_autocomplete/create_dataset.py`. 
   * It collects repos mentioned in
 [PyTorch awesome list](https://github.com/bharathgs/Awesome-pytorch-list)
   * Downloads the zip files of the repos
   * Extract the zips
   * Remove non python files
   * Collect all python code to `data/train.py` and, `data/eval.py`
4. Run `python_autocomplete/train.py` to train the model.
 *Try changing hyper-parameters like model dimensions and number of layers*.
5. Run `evaluate.py` to evaluate the model.

<p align="center">
  <img src="/python-autocomplete.png?raw=true" width="100%" title="Screenshot">
</p>


