This project aims to identify "normal" or "danger" objects in conveyor belt of an airport
Explore the docs »
View Demo
·
Report Bug
·
Request Feature
Table of Contents
You need to install the following packets using pip
- pip
pip install pandas pip install fpdf pip install sklearn pip install matplotlib pip install yellowbrick
Run main.py
and see a PDF report in the ./output/info (one for each selected classifier is generated).
All the plots are stored in the ./output/plot :
Dataset is made by the measures of three different sensors, 'RMs' 'LMs' 'UMs' placed respectively in the right, in the left and up.
Format is the following
RMs | LMs | UMs | Class |
---|---|---|---|
1.98242 | 2.017493 | 2.015046 | Object |
Configuration file entries are:
- csv_path : the path of csv dataset folder; can be also one single file
- classes : list of the two classes identifier since the classifier is binary
- classifiers : list containing all the classifiers we want to use. All possibilities are:
["Naive-Bayes", "LinearSVC", "KNN", "DecisionTree", "LogisticRegression", "LDA", "SVM"] - csv_cols : list of features; must contains only 2 values
- csv_labels : list of labels
- normal : list of normal objects
- danger : list of danger objects
- plot_path : the path of the plot output
- info_path : the path of the pdf output
See the open issues for a list of proposed features (and known issues).
Contributions are what make the open source community such an amazing place to be learn, inspire, and create.
Any contributions you make are greatly appreciated.
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature
) - Commit your Changes (
git commit -m 'Add some AmazingFeature'
) - Push to the Branch (
git push origin feature/AmazingFeature
) - Open a Pull Request
This project is licensed under the MIT License - see the LICENSE file for details