This project is a simple Data Science analysis based on the Fast Fashion Eco Commitment Dataset available on the zenodo
public Hub.
The first objective of this study is to collect, clean and analyse spanish Zara items thought a basic Exploratory Data Analysis. Next, several models will be created during the Machine Learning Analysis with the aim of predicting whether or not a given garment item has the special Zara join life ecolabel (Binary classification).
To have a look and manipulate the main dataset, please consider the following steps:
- First, create a copy of the project:
Via https
git clone https://github.com/pmatran/join-life-detector.git
Via ssh
git clone [email protected]:pmatran/join-life-detector.git
- Then, enter in main repository
cd join-life-detector/
- Next, make sure to install all dependencies:
pip install -r requirements.txt
Start the Exploraroty Data Analysis
jupyter notebook notebooks/EDA.ipynb
Start the Machine Learning Analysis
jupyter notebook notebooks/MLA.ipynb
Start the model interactive dashboard
python dashboard.py
Start the model interactive model prediction
python app.py
If you are interested to have a quick look on raw data, some reports about datasets are availables:
Bug reports, code contributions, or improvements to the documentation are welcome from the community.
Feel free to suggest improvements by working with your own fork version of join-life-detector
. Go to the project page and hit the Fork button.
You will want to clone your fork to your machine:
git clone <url-join-life-detector> <join-life-detector-#yourname>
cd join-life-detector
- Pandas documentation
- Plotly documentation
- Scikit-learn documentation
- Pycaret documentation
- Zara Join-life ecolabel
This project was created to evaluate the analytic skills of the owner (@pmatran) by his professor at M2-IASchool (Bordeaux, FRANCE).