Skip to content

Latest commit

 

History

History
58 lines (35 loc) · 1.81 KB

README.md

File metadata and controls

58 lines (35 loc) · 1.81 KB
Raw

Machine Learning project with Flask API

It contains my ML project involving rental price recommendation based on area, rooms, bathroom, parking_space, floor, animal, furniture, hoa, and property tax. This project was accomplished during Machine Learning | Solução completa end-to-end (Python), an Udemy course. I

The command below clone this repository.

$ git clone https://github.com/Samuellucas97/ML-E2E-Course.git
$ cd ML-E2E-Course

Requirements

  • Python ( version 3.8.10 )

  • Numpy ( version 1.23.4 )

    • Use the following command to install: pip install numpy

  • Pandas ( version 1.5.1 )

    • Use the following command to install: pip install pandas

  • Seaborn ( version 0.12.1 )

    • Use the following command to install: pip install seaborn

  • Sckit-learn ( version 1.1.3 )

    • Use the following command to install: pip install sklearn

  • Yellowbrick (version 1.5 )

    • Use the following command to install: pip install yellowbrick

  • Joblib ( version 1.2.0 )

    • Use the following command to install: pip install joblib

  • Flask ( version 2.2.2 )

    • Use the following command to install: pip install flask

You could check your Sckit-learn lib version, for example, using the following commands on Python interpreter:

>>> import sklearn
>>> print('The scikit-learn version is {}.'.format(sklearn.__version__))

How to run

Since you have installed software requirements, you need to execute on the terminal the following command:

$ ./run.sh

A Flask server will be running on http://127.0.0.1:5000.

You can use the /api/predictor/ API endpoint to predict rent. We show an example about how to use this in /test/api.ipynb.