sg-data-analyst

Medium Article

Explore Singapore Datasets with SG Data Analyst 🤖

Based on your query, SG Data Analyst will find the most relevant datasets from data.gov.sg and data.gov.sg's API.

Using Langchain's Pandas DataFrame Agent, SG Data Analyst will then perform exploratory data analysis on the datasets and gather insights to answer your query.

Quickstart

1. Install requirements

pip install -r requirements.txt

2. Add your OpenAI API key to the environment

• It's best to have access to GPT-4, gpt-4-0613 in particular since we rely on the OpenAI functions API
• Alternatively, gpt-3.5-turbo-0613 or gpt-3.5-turbo-16k-0613 should work as well, though not as well as GPT-4
• Changes can be made in config.py

export OPENAI_API_KEY=<your-api-key>

Alternatively, you can add your API key to a .env file in the root directory of this project. Refer to dev.env for the format.

3. Run the streamlit app

streamlit run app.py

4. Try it out!

😃: What are some observations in university education?

👨‍🔬: Some observations in university education based on the data include:

1. The data covers a wide range of fields of study, including 'Accountancy', 'Architecture, Building & Real Estate', 'Business & Administration', 'Dentistry', 'Education', 'Engineering Sciences', 'Fine & Applied Arts', 'Health Sciences', 'Humanities & Social Sciences', 'Information Technology', 'Law', 'Mass Communication', 'Medicine', 'Natural, Physical & Mathematical Sciences', 'Services', and 'Natural & Mathematical Sciences'.
2. The data includes information on both male and female students, as well as a combined category for both sexes.
3. The data covers a wide range of years, from 1982 to 2021.