Simplify

Simplify stands for a smart intelligent system that can code like a human being for a data science application. It enables data scientists to perform all the tedious and time-consuming tasks such as EDA (exploratory data analysis), data cleaning, data pre-processing, data visualization, modeling, and evaluation in the data-science life cycle, by only conveying the logic of the task in natural language (English query) and the system will automatically give out all the relevant python code snippets, or in other words the user just needs to type what they want in the form of a natural language query (English), and our system will automatically give out all the relevant code snippets in python for it.

Dataset Stats

Parameter	Statistics
Total Number of Users Queries	525
Total Number of Unique Intents	20
Total Number of Unique Entity	10
Total Number of Unique Python Code Snippets	100

Intent Classification

Comparison among Several Approachs for Intent Classification.

Sr. No	Method	Accuracy	Paper	Year
1.	Sum of Word Embedding (Citation Word Embedding)	88.60%	Paper	Jan 2021
3.	Facebook InferSent	87.34%	Paper	Jul 2018
2.	Semantic Subword Hashing	78.48%	Paper	Sep 2019
4.	TF-IDF (Citation Word Embedding)	74.68%	Paper	Jan 2021

Custom-NER-using-Spacy

Custom Named Entity Recognition annotated using NER Annotated by tecoholic and Spacy for training the model

Get Started

Download glove embeddings folder and place it inside "./simplify/intent_word_emb" folder

Download entity recognition model folder and place it inside "./simplify/models" folder

Activate your environment

conda activate codify_env

Run Python Server

python server.py

Run React App

cd client/

npm start

Credits

• NER Annotator - https://github.com/tecoholic/ner-annotator
• spacy - https://github.com/explosion/spaCy
• Custom NER for Extracting Disease Entities Blog - https://medium.com/analytics-vidhya/custom-ner-for-extracting-disease-entities-c620aca2e1bb