renanBritz / ml_airline_customer_satisfaction

Airline passenger satisfaction prediction

This is a project for classify airline passenger satisfaction. It was carried out as an evaluated task from a Machine Learning discipline from UFRGS (Universidade Federal do Rio Grande do Sul)

Dataset origin : https://www.kaggle.com/datasets/teejmahal20/airline-passenger-satisfaction

Installation

Here is presented the setup on a Windows OS, but the procedure for a Unix system shall be the same or very close.

1. Download and InstallAnaconda : https://docs.anaconda.com/anaconda/install/windows/

2. Setup a virtual environment On a conda terminal type:

    conda env create -f environment.yml
   

3. Activate the virtual environment

    conda activate ML_Analysis
   

4. Launch Jupyter Lab

    jupyter lab
   

Data analysis pipeline

The Jupyter Notebook is ready as it is, it contains all the steps to perform the analysis.

There is a first step for the data cleansing and preparation, which should not be anything more to do.

We invite you to test another hyperparameters for the models here implemented as well different strategies for validation and metrics.