worldbank / llm4data
LLM4Data is a Python library designed to facilitate the application of large language models (LLMs) and artificial intelligence for development data and knowledge discovery.
☆46Updated 6 months ago
Related projects: ⓘ
- This offers a Jupyter Notebook introduction on how to use Large Language Models for text analysis within the social sciences.☆55Updated 5 months ago
- Course repository for the session "Hands-on Transformers: Fine-Tune your own BERT and GPT" of the Data Science Summer School 2023☆84Updated last year
- The course introduces the use of open-source large language models (LLMs) from the Hugging Face ecosystem for research in the behavioral …☆43Updated 3 months ago
- iQual is a package that leverages natural language processing to scale up interpretative qualitative analysis. It also provides methods t…☆15Updated last year
- Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers…☆169Updated this week
- Project repository of the paper "Less Annotating, More Classifying – Addressing the Data Scarcity Issue of Supervised Machine Learning wi…☆23Updated 6 months ago
- Prototype search engine for ONS bulletins☆22Updated 5 months ago
- Python package for text mining of time-series data☆66Updated 2 weeks ago
- Tool for probabilistically linking the records of individual entities (e.g. people) within and across datasets☆107Updated 4 months ago
- A convenient way to link, deduplicate, aggregate and cluster data(frames) in Python using deep learning☆99Updated 3 months ago
- Given a job title and job description, the algorithm assigns a standard occupational classification (SOC) code to the job.☆73Updated 2 months ago
- Public repository for the research outputs of the Mapping Career Causeways project☆25Updated 3 years ago
- Jupyter notebooks and python scripts for performing the ViEWS monthly forecasts☆13Updated 3 months ago
- Hierarchical clustering of 2011-2022 Congress Twitter☆31Updated 2 years ago
- Course materials for our "Getting Started with NLP and spaCy" course at Talk Python☆28Updated 4 months ago
- Commuting zones are geographic areas where people live and work and are useful for understanding local economies, as well as how they dif…☆39Updated last year
- Innovation across ages☆64Updated last year
- Python for Public Policy course☆28Updated last week
- Materials for the 2023 SOCIAL COMQUANT "Introduction to CSS Methods with Python"☆15Updated last year
- Georeferencing large amounts of data for free.☆31Updated 11 months ago
- This repository contains the raw data, code, and sources used to create an individual level and state municipal incorporation date datase…☆23Updated 4 months ago
- ☆21Updated last year
- A Python client for the GDELT 2.0 Doc API☆91Updated 6 months ago
- Select, weight and analyze complex sample data☆57Updated 2 months ago
- Notebooks and other course materials for Emory QTM 340 (Fall 2024 - Klein)☆18Updated this week
- Catalogue of resources (R/Python/SQL/SAS/Stata/...) to reproduce the results of Eurostat Statistics Explained articles☆42Updated last week
- NLP: An Application for Public Policy, PyCon Ireland 2018☆23Updated last year
- A review of APIs.☆63Updated this week
- A full course of self-explanatory and freely available materials on CSS methods☆57Updated 2 weeks ago
- Repository containing raw data, code, and final output for the Statistical Performance Indicators project of the World bank☆35Updated this week