deepklarity / Jupyter Text2code
Licence: mit
A proof-of-concept jupyter extension which converts english queries into relevant python code
Stars: ✭ 897
Labels
Projects that are alternatives of or similar to Jupyter Text2code
Pydhamed
Dynamic Histogram Analysis To Determine Free Energies and Rates from Biased Simulations
Stars: ✭ 17 (-98.1%)
Mutual labels: jupyter-notebook
Computer Vision
Computer vision exercise with Python and OpenCV.
Stars: ✭ 17 (-98.1%)
Mutual labels: jupyter-notebook
Tensorflowmnist
Various neural networks on MNIST data using TensorFlow library
Stars: ✭ 17 (-98.1%)
Mutual labels: jupyter-notebook
Pulmonary nodules ai diagnosis
Tianchi medical AI competition [Season 1]: Intelligent diagnosis of pulmonary nodules. 肺部结节智能诊断
Stars: ✭ 17 (-98.1%)
Mutual labels: jupyter-notebook
Ansible Jupyter.dockerfile
Building the Docker image with Ansible and Jupyter.
Stars: ✭ 17 (-98.1%)
Mutual labels: jupyter-notebook
Machine learning denoising
A Keras implementation of the "Deep Image Prior" paper.
Stars: ✭ 17 (-98.1%)
Mutual labels: jupyter-notebook
Python fundamentals
Python fundamentals is a series of tutorials on Basic Python knowledge required to get started in the field of Data Science.
Stars: ✭ 18 (-97.99%)
Mutual labels: jupyter-notebook
Ilearndeeplearning.py
This repository contains small projects related to Neural Networks and Deep Learning in general. Subjects are closely linekd with articles I publish on Medium. I encourage you both to read as well as to check how the code works in the action.
Stars: ✭ 896 (-0.11%)
Mutual labels: jupyter-notebook
National generation capacity
Data package: national generation capacity
Stars: ✭ 17 (-98.1%)
Mutual labels: jupyter-notebook
Simplest Tensorflow Tensorboard Mnist Embedding Visualisation
Stars: ✭ 17 (-98.1%)
Mutual labels: jupyter-notebook
Integer Programming With Python
Introduction to Linear and Integer Programming Book
Stars: ✭ 17 (-98.1%)
Mutual labels: jupyter-notebook
Ml unsam
Repositorio de la materia Aprendizaje Automático (2do cuatrimestre de 2020)
Stars: ✭ 18 (-97.99%)
Mutual labels: jupyter-notebook
Foundations course
Materials for the preparatory course for new students of the Master of Autonomous Systems program
Stars: ✭ 17 (-98.1%)
Mutual labels: jupyter-notebook
Bioinformatics
Course materials for Computational Biology and Bioinformatics - BI462
Stars: ✭ 17 (-98.1%)
Mutual labels: jupyter-notebook
Symptoms Tracker
A scalable web app for tracking covid-19-related symptoms amongst confined populations
Stars: ✭ 18 (-97.99%)
Mutual labels: jupyter-notebook
E Healthify
App developed for Hack-the-Crisis India.
Stars: ✭ 18 (-97.99%)
Mutual labels: jupyter-notebook
Text2Code for Jupyter notebook
A proof-of-concept jupyter extension which converts english queries into relevant python code.
Blog post with more details:
Data analysis made easy: Text2Code for Jupyter notebook
Demo Video:
Text2Code for Jupyter notebook
Supported Operating Systems:
- Ubuntu
- macOS
Jupyter plugin Installation:
NOTE: We have renamed the plugin from mopp to jupyter-text2code. Uninstall mopp before installing new jupyter-text2code version.
pip uninstall mopp
GPU install
git clone https://github.com/deepklarity/jupyter-text2code.git
cd jupyter-text2code
pip install .
CPU-only install
For Mac and other Ubuntu installations not having a nvidia GPU, we need to explicitly set a environment variable at time of install.
git clone https://github.com/deepklarity/jupyter-text2code.git
export JUPYTER_TEXT2CODE_MODE="cpu"
cd jupyter-text2code
pip install .
Jupyter plugin Uninstallation:
pip uninstall jupyter-text2code
Usage Instructions:
- Open Jupyter notebook
- If installation happened successfully, then for the first time, Universal Sentence Encoder model will be downloaded from
tensorflow_hub
. - Click on the
Terminal
Icon which appears on the menu (to activate the extension) - Type "help" to see a list of currently supported commands in the repo
- Watch Demo video for some examples
Model training:
Generate training data:
From a list of templates present at jupyter_text2code/jupyter_text2code_serverextension/data/ner_templates.csv
, generate training data by running the following command:
cd scripts && python generate_training_data.py
This command will generate data for intent matching and NER(Named Entity Recognition).
Create intent index faiss
Use the generated data to create a intent-matcher using faiss.
cd scripts && python create_intent_index.py
Train NER model
cd scripts && python train_spacy_ner.py
Steps to add more intents:
- Add more templates in
ner_templates
with a new intent_id - Generate training data. Modify
generate_training_data.py
if different generation techniques are needed or if introducing a new entity. - Train intent index
- Train NER model
- modify
jupyter_text2code/jupyter_text2code_serverextension/__init__.py
with new intent's condition and add actual code for the intent - Reinstall plugin by running:
pip install .
TODO:
- [ ] Refactor code and make it mode modular, remove duplicate code, etc
- [ ] Add support for Windows
- [ ] Add support for more commands
- [ ] Improve intent detection and NER
- [ ] Explore sentence Paraphrasing to generate higher-quality training data
- [ ] Gather real-world variable names, library names as opposed to randomly generating them
- [ ] Try NER with a transformer-based model
- [ ] With enough data, train a language model to directly do English->code like GPT-3 does, instead of having separate stages in the pipeline
- [ ] Create a survey to collect linguistic data
- [ ] Add Speech2Code support
Authored By:
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].