47

GitHub - vpj/python_autocomplete: A simple neural network for python autocomplet...

 4 years ago
source link: https://github.com/vpj/python_autocomplete
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.

readme.md

master branch is underdevelopment. Checkout simple_lstm branch to try it out.

This a toy project we started to see how well a simple LSTM model can autocomplete python code.

It gives quite decent results by saving above 30% key strokes in most files, and close to 50% in some. We calculated key strokes saved by making a single (best) prediction and selecting it with a single key.

We do a beam search to find predictions, upto ~10 characters ahead. So far it's too inefficient, if you are wondering about editor integration.

We train and predict on after cleaning comments, strings and blank lines in python code. The model is trained after tokenizing python code. It seems more efficient than character level prediction with byte-pair encoding.

A saved model is included in this repo. It is trained on tensorflow/models.

Here's a sample evaluation on a source file from validation set. Green characters are when a autocompletion started; i.e. user presses TAB to select the completion. The green character and and the following characters highlighted in gray are autocompleted. As you can see, it starts and ends completions arbitarily. That is a suggestion could be 'tensorfl' and not the complete identifier 'tensorflow' which can be a little annoying in a real usage scenario. We can limit them to finish on end of tokens to fix that. Also you can notice that it completes across operators as well. Increasing the length of the beam search will let it complete longer pieces of code.

python-autocomplete.png?raw=true

Try it yourself

  1. Checkout simple_lstm branch.

  2. Setup lab

  3. Copy data to ./data/source

  4. Run extract_code.py to collect all python files, encode and merge them into all.py

  5. Run evaluate.py to evaluate the model.

  6. Run train.py to train the model


About Joyk


Aggregate valuable and interesting links.
Joyk means Joy of geeK