A proof-of-concept jupyter extension which converts english queries into relevant python code

Overview

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

Installation

NOTE: We have renamed the plugin from mopp to jupyter-text2code. Uninstall mopp before installing new jupyter-text2code version.

pip uninstall mopp

CPU-only install:

For Mac and other Ubuntu installations not having a nvidia GPU, we need to explicitly set an environment variable at time of install.

export JUPYTER_TEXT2CODE_MODE="cpu"

GPU install dependencies:

sudo apt-get install libopenblas-dev libomp-dev

Installation commands:

git clone https://github.com/deepklarity/jupyter-text2code.git
cd jupyter-text2code
pip install .
jupyter nbextension enable jupyter-text2code/main

Uninstallation:

pip uninstall jupyter-text2code

Usage Instructions:

  • Start Jupyter notebook server by running the following command: jupyter notebook
  • If you don't see Nbextensions tab in Jupyter notebook run the following command:jupyter contrib nbextension install --user
  • You can open the sample notebooks/ctds.ipynb notebook for testing
  • 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

Docker containers for jupyter-text2code

We have published CPU and GPU images to docker hub with all dependencies pre-installed.

Visit https://hub.docker.com/r/deepklarity/jupyter-text2code/ to download the images and usage instructions.
CPU image size: 1.51 GB
GPU image size: 2.56 GB

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:

  • Publish Docker image
  • 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:

Owner
DeepKlarity
DeepKlarity
iNaturalist observations along hiking trails

This tool reads the route of a hike and generates a table of iNaturalist observations along the trails. It also shows the observations and the route of the hike on a map. Moreover, it saves waypoints

7 Nov 11, 2022
Location field and widget for Django. It supports Google Maps, OpenStreetMap and Mapbox

django-location-field Let users pick locations using a map widget and store its latitude and longitude. Stable version: django-location-field==2.1.0 D

Caio Ariede 481 Dec 29, 2022
Create Siege configuration files from Cloud Optimized GeoTIFF.

cogeo-siege Documentation: Source Code: https://github.com/developmentseed/cogeo-siege Description Create siege configuration files from Cloud Optimiz

Development Seed 3 Dec 01, 2022
Fiona reads and writes geographic data files

Fiona Fiona reads and writes geographic data files and thereby helps Python programmers integrate geographic information systems with other computer s

987 Jan 04, 2023
Search and download Copernicus Sentinel satellite images

sentinelsat Sentinelsat makes searching, downloading and retrieving the metadata of Sentinel satellite images from the Copernicus Open Access Hub easy

837 Dec 28, 2022
FDTD simulator that generates s-parameters from OFF geometry files using a GPU

Emport Overview This repo provides a FDTD (Finite Differences Time Domain) simulator called emport for solving RF circuits. Emport outputs its simulat

4 Dec 15, 2022
A compilation of several single-beam bathymetry surveys of the Caribbean

Caribbean - Single-beam bathymetry This dataset is a compilation of several single-beam bathymetry surveys of the Caribbean ocean displaying a wide ra

Fatiando a Terra Datasets 0 Jan 20, 2022
Google Maps keeps old satellite imagery around for a while – this tool collects what's available for a user-specified region in the form of a GIF.

google-maps-at-88-mph The folks maintaining Google Maps regularly update the satellite imagery it serves its users, but outdated versions of the image

Noah Doersing 111 Sep 27, 2022
Geospatial Image Processing for Python

GIPPY Gippy is a Python library for image processing of geospatial raster data. The core of the library is implemented as a C++ library, libgip, with

GIPIT 83 Aug 19, 2022
Track International space station with python

NASA-ISS-tracker Track International space station with python Modules import json import turtle import urllib.request import time import webbrowser i

Nikhil Yadav 8 Aug 12, 2021
Pure python WMS

Ogcserver Python WMS implementation using Mapnik. Depends Mapnik = 0.7.0 (and python bindings) Pillow PasteScript WebOb You will need to install Map

Mapnik 130 Dec 28, 2022
Get-countries-info - A python code that fetches data of any country

Country-info A python code getting countries information including country's map

CODE 2 Feb 21, 2022
WIP: extracting Geometry utilities from datacube-core

odc.geo This is still work in progress. This repository contains geometry related code extracted from Open Datacube. For details and motivation see OD

Open Data Cube 34 Jan 09, 2023
Mmdb-server - An open source fast API server to lookup IP addresses for their geographic location

mmdb-server mmdb-server is an open source fast API server to lookup IP addresses

Alexandre Dulaunoy 67 Nov 25, 2022
python toolbox for visualizing geographical data and making maps

geoplotlib is a python toolbox for visualizing geographical data and making maps data = read_csv('data/bus.csv') geoplotlib.dot(data) geoplotlib.show(

Andrea Cuttone 976 Dec 11, 2022
A library to access OpenStreetMap related services

OSMPythonTools The python package OSMPythonTools provides easy access to OpenStreetMap (OSM) related services, among them an Overpass endpoint, Nomina

Franz-Benjamin Mocnik 342 Dec 31, 2022
Pandas Network Analysis: fast accessibility metrics and shortest paths, using contraction hierarchies :world_map:

Pandana Pandana is a Python library for network analysis that uses contraction hierarchies to calculate super-fast travel accessibility metrics and sh

Urban Data Science Toolkit 321 Jan 05, 2023
Python bindings to libpostal for fast international address parsing/normalization

pypostal These are the official Python bindings to https://github.com/openvenues/libpostal, a fast statistical parser/normalizer for street addresses

openvenues 651 Dec 16, 2022
Asynchronous Client for the worlds fastest in-memory geo-database Tile38

This is an asynchonous Python client for Tile38 that allows for fast and easy interaction with the worlds fastest in-memory geodatabase Tile38.

Ben 53 Dec 29, 2022
PySAL: Python Spatial Analysis Library Meta-Package

Python Spatial Analysis Library PySAL, the Python spatial analysis library, is an open source cross-platform library for geospatial data science with

Python Spatial Analysis Library 1.1k Dec 18, 2022