Sweater Weather - Express.js, Node.js & Sequelize

This solo project is a remake of the Ruby project Sweater Weather: https://github.com/carriewalsh/sweater_weather. It is a backend API that provides weather data for a yet-to-be-made frontend.

Express application hosted on Heroku that utilizes a machine learning model trained with over 300,000 data points to predict test outcomes for 5,000 mock students based on eating and sleeping habits for each student.

Application Highlights:

• Professional workflow as seen through:
  • Strong PR documentation as can be seen here
  • Code review with other classmates seen here
  • MVC/RESTful design patterns including serializers and services for better encapsulation principles

Contributing

• Blake Enyart - Django app, data visualization (chart.js, seaborn, matplotlib), machine learning implementation

Location of Apps in Production

• Here to Learn - Rails based central app designed for user interface
• Django application - Django based machine learning microservice
• Surveys - Sinatra based database microservice

Tech Stack

Data Visualization

Local Configuration for Further Development

Use the following code to setup the code locally:

python3 -m venv env
source env/bin/activate
pip install -r requirements.txt
psql
CREATE DATABASE heretolearn_production;
CREATE USER heretolearn WITH PASSWORD 'badgers';
GRANT ALL PRIVILEGES ON DATABASE heretolearn_production TO heretolearn;
\q
python manage.py migrate
python manage.py runserver

Navigate to localhost:8000 from your browser to see the app in development mode

Django App Demo

Use the following endpoint to see the production app return data from the Sinatra app, make a prediction, and render data and prediction in JSON format:

https://lit-fortress-28598.herokuapp.com/machinelearning/results/?student_id=5