Prediction Service

About • How it works • Documentation • Authors • License

ℹ️ About

API Restful to add and predict data temperature and humidity, using stack with Python, Flask and MLPRegressor for predict model.

🚀 How it works

👉 Pre-requisites

Before you begin, you will need to have the following tools installed on your machine: Git, Python and Pip. In addition, it is good to have an editor to work with the code like VSCode.

🏁 Start

# Clone this repository
$ git clone https://github.com/BiaChacon/prediction-service.git

# Access the project folder cmd/terminal
$ cd prediction-service

First, create an .env file locally. You can duplicate .env.example and name the new .env copy. Note that you need to fill the env DB_URL variable with your MongoDB connection string.

🎲 Running the server

# install the dependencies
$ pip install requirements.txt

# Run the application
$ python app.py

# The server will start at port: 5000 - go to http://localhost:5001

🖥️ Client

👉 Pre-requisites

Is running the Weather API

# go to the project folder
$ cd client

#Run the application
$ python client.py

📈 Results analysis

Analysis of prediction results according to times of increment of new data to the model.

X = 5 minutes
Y = 1 hour
Z = 6 hours

🗎 Documentation

🚀 Postman Collection

👩🏽‍💻 Authors

_{Bia Chacon}
💻

📝 License

This project is under MIT. See at here LICENSE for more information.