TINTOlib 0.0.26

Converting tabular data into images

TINTOlib

TINTOlib is a state-of-the-art library that wraps the most important techniques for the construction of Synthetic Images fromTidy Data (also known as Tabular Data).

Citing TINTO: If you used TINTO in your work, please cite the SoftwareX:

@article{softwarex_TINTO,
    title = {TINTO: Converting Tidy Data into Image for Classification with 2-Dimensional Convolutional Neural Networks},
    journal = {SoftwareX},
    author = {Manuel Castillo-Cara and Reewos Talla-Chumpitaz and Raúl García-Castro and Luis Orozco-Barbosa},
    volume={22},
    pages={101391},
    year = {2023},
    issn = {2352-7110},
    doi = {https://doi.org/10.1016/j.softx.2023.101391}
}

And use-case developed in INFFUS Paper

@article{inffus_TINTO,
    title = {A novel deep learning approach using blurring image techniques for Bluetooth-based indoor localisation},
    journal = {Information Fusion},
    author = {Reewos Talla-Chumpitaz and Manuel Castillo-Cara and Luis Orozco-Barbosa and Raúl García-Castro},
    volume = {91},
    pages = {173-186},
    year = {2023},
    issn = {1566-2535},
    doi = {https://doi.org/10.1016/j.inffus.2022.10.011}
}

Features

• Input data formats (2 options):

  • Pandas Dataframe
  • Files with the following format
    • Tabular files: The input data must be in CSV, taking into account the Tidy Data format.
    • Tidy Data: The target (variable to be predicted) should be set as the last column of the dataset. Therefore, the first columns will be the features.
    • All data must be in numerical form.

• Runs on Linux, Windows and macOS systems.

• Compatible with Python 3.7 or higher.

Models

Model	Class	Features	Hyperparameters
BarGraph	BarGraph()		problem verbose pixel_width gap zoom
BIE	BIE()		problem verbose precision zoom
Combination	Combination()		problem verbose zoom
DistanceMatrix	DistanceMatrix()		problem verbose zoom
FeatureWrap	FeatureWrap()		problem verbose size bins zoom
IGTD	IGTD()		problem verbose scale fea_dist_method image_dist_method max_step val_step error switch_t min_gain random_seed zoom
REFINED	REFINED()		problem verbose hcIterations random_seed zoom n_processors
SuperTML	SuperTML()		problem columns font_size image_size verbose
TINTO	TINTO()	blur	problem algorithm pixels blur amplification distance steps option seed times verbose

Documentation

Read the documentation.

Getting Started

You can install TINTOlib using Pypi:

    pip install torchmetrics pytorch_lightning TINTOlib imblearn keras_preprocessing mpi4py

To import a specific model use

    from TINTOlib.tinto import TINTO

Create the model. If you don't set any hyperparameter, the model will use the default values (read documentation).

    model = TINTO(blur=True)

To generate the synthetic images use .generateImages(data,folder) method.

    model.generateImages(data, resultsFolderPath)

How to use TINTOlib - Google Colab crash course

Once the images have been created by TINTO, they can be imported into any project using CNNs.

In order to facilitate their use, a Jupyter Notebook has been created in which you can see how the images are read and how they can be used as input in a CNN.

• Click here to TINTOlib crash course using classification ML problems with CNNs in Google Colab
• Click here to TINTOlib crash course using classification ML problems with hybrid multimodal CNN+MLP in Google Colab
• Click here to TINTOlib crash course using regression ML problems with hybrid multimodal CNN+MLP in Google Colab

Converting Tidy Data into image

For example, the following table shows a classic example of theIRIS CSV dataset as it should look like for the run:

sepal length	sepal width	petal length	petal width	target
4.9	3.0	1.4	0.2	1
7.0	3.2	4.7	1.4	2
6.3	3.3	6.0	2.5	3

Simple example without Blurring

The following example shows how to create 20x20 images with characteristic pixels, i.e. without blurring. Also, as no other parameters are indicated, you will choose the following parameters which are set by default:

• Image size: 20x20 pixels
• Blurring: No blurring will be used.
• Seed: with the seed set to 20.

More specific example

The following example shows how to create with blurring with a more especific parameters.

The images are created with the following considerations regarding the parameters used:

• Blurring (-B): Create the images with blurring technique.
• Dimensional Reduction Algorithm (-alg): t-SNE is used.
• Blurring option (-oB): Create de images with maximum value of overlaping pixel
• Image size (-px): 30x30 pixels
• Blurring steps (-sB): Expand 5 pixels the blurring.

License

TINTOlib is available under the Apache License 2.0.

Authors

• Manuel Castillo-Cara
• Raúl García-Castro
• Borja Reinoso [e-mail]
• David González Fernández

Contributors