Automated Metadata Quality Report from CodeMetaSoft

[SergioZSZ]

This issue was created automatically after running metadata quality checks. Several warnings or pitfalls were detected and may be worth reviewing.

This automated issue includes:

• Detected metadata pitfalls and warnings
• A suggested codemeta.json when no codemeta.json was detected
• Suggestions for fixing each issue

Context

This analysis is performed by the CodeMetaSoft project to help improve research software metadata quality.

This is a first initiative aimed at identifying and reporting metadata quality issues across research software repositories.
At this stage, we only provide diagnostics and recommendations.
In future iterations, we plan to propose automated fixes for the detected issues to further simplify the improvement process and reduce manual effort.

Each pitfall and warning is identified by a unique code (e.g. P001 for pitfalls, W004 for warnings) that corresponds to specific metadata quality issues.
You can find more details about these checks and how to address them in the RSMetacheck catalog.

Metadata Quality Report

Repository: https://github.com/oeg-upm/TINTOlib-Crash_Course
Analysis Date: 2026-06-22
sw-metadata-bot version: 0.5.0
RSMetacheck version: 0.3.1

📄 Missing codemeta.json

No root codemeta.json file was detected in the repository. A generated suggestion is provided below.

{
  "@context": "https://w3id.org/codemeta/3.0",
  "@type": [
    "SoftwareSourceCode",
    "SoftwareApplication"
  ],
  "license": {
    "name": "Apache License 2.0",
    "url": "https://spdx.org/licenses/Apache-2.0",
    "identifier": "https://spdx.org/licenses/Apache-2.0"
  },
  "codeRepository": "https://github.com/oeg-upm/TINTOlib-Crash_Course",
  "issueTracker": "https://api.github.com/repos/oeg-upm/TINTOlib-Crash_Course/issues",
  "dateCreated": "2024-10-21",
  "dateModified": "2026-06-14",
  "downloadUrl": "https://github.com/oeg-upm/TINTOlib-Crash_Course/releases",
  "name": "TINTOlib-Crash_Course",
  "logo": "https://raw.githubusercontent.com/oeg-upm/TINTOlib-Crash_Course/main/3_Images/logo.svg",
  "programmingLanguage": [
    "Jupyter Notebook"
  ],
  "softwareRequirements": [
    {
      "name": "bitstring",
      "@type": "SoftwareApplication",
      "version": "==4.3.0"
    },
    {
      "name": "matplotlib",
      "@type": "SoftwareApplication",
      "version": "==3.9.4"
    },
    {
      "name": "numpy",
      "@type": "SoftwareApplication",
      "version": "==2.0.2"
    },
    {
      "name": "pandas",
      "@type": "SoftwareApplication",
      "version": "==2.2.3"
    },
    {
      "name": "scikit-learn",
      "@type": "SoftwareApplication",
      "version": "==1.6.1"
    },
    {
      "name": "opencv-python",
      "@type": "SoftwareApplication",
      "version": "==4.11.0.86"
    },
    {
      "name": "mpi4py",
      "@type": "SoftwareApplication",
      "version": "==4.0.3"
    },
    {
      "name": "torch-lr-finder",
      "@type": "SoftwareApplication",
      "version": "==0.2.2"
    },
    {
      "name": "einops",
      "@type": "SoftwareApplication",
      "version": "==0.8.1"
    },
    {
      "name": "torchinfo",
      "@type": "SoftwareApplication",
      "version": "==1.8.0"
    },
    {
      "name": "keras_preprocessing",
      "@type": "SoftwareApplication",
      "version": "==1.1.2"
    }
  ],
  "buildInstructions": [
    "https://tintolib.readthedocs.io/en/latest/"
  ],
  "author": [
    {
      "@type": "Organization",
      "identifier": "oeg-upm",
      "@id": "https://github.com/oeg-upm"
    }
  ],
  "referencePublication": [
    {
      "@type": "ScholarlyArticle",
      "identifier": "10.1109/JSTSP.2025.3555067",
      "name": "MIMO-Based Indoor Localisation with Hybrid Neural Networks: Leveraging Synthetic Images from Tidy Data for Enhanced Deep Learning",
      "author": [
        {
          "@type": "Person",
          "familyName": "Castillo-Cara",
          "givenName": "Manuel"
        },
        {
          "@type": "Person",
          "familyName": "Mart\u00ednez-G\u00f3mez",
          "givenName": "Jesus"
        },
        {
          "@type": "Person",
          "familyName": "Ballesteros-Jerez",
          "givenName": "Javier"
        },
        {
          "@type": "Person",
          "familyName": "Garc\u00eda-Varea",
          "givenName": "Ismael"
        },
        {
          "@type": "Person",
          "familyName": "Garc\u00eda-Castro",
          "givenName": "Ra\u00fal"
        },
        {
          "@type": "Person",
          "familyName": "Orozco-Barbosa",
          "givenName": "Luis"
        }
      ],
      "datePublished": "2025",
      "pagination": "1-13"
    },
    {
      "@type": "ScholarlyArticle",
      "identifier": "https://doi.org/10.1016/j.softx.2023.101391",
      "name": "TINTO: Converting Tidy Data into Image for Classification with 2-Dimensional Convolutional Neural Networks",
      "author": [
        {
          "@type": "Person",
          "familyName": "Castillo-Cara",
          "givenName": "Manuel"
        },
        {
          "@type": "Person",
          "familyName": "Talla-Chumpitaz",
          "givenName": "Reewos"
        },
        {
          "@type": "Person",
          "familyName": "Garc\u00eda-Castro",
          "givenName": "Ra\u00fal"
        },
        {
          "@type": "Person",
          "familyName": "Orozco-Barbosa",
          "givenName": "Luis"
        }
      ],
      "issn": "2352-7110",
      "datePublished": "2023",
      "pagination": "101391"
    }
  ],
  "creditText": [
    "Liu, J., Gonz\u00e1lez-Fern\u00e1ndez, D., Castillo-Cara, M., Garc\u00eda-Castro, R. (tintolib: a python library for transforming tabular data into synthetic images for deep neural networks). https://doi.org/10.1016/j.softx.2025.102444. Available at: https://github.com/oeg-upm/TINTOlib-Crash_Course"
  ],
  "readme": "https://raw.githubusercontent.com/oeg-upm/TINTOlib-Crash_Course/main/README.md",
  "description": [
    "This repository provides a comprehensive crash course on using [TINTOlib](https://tintolib.readthedocs.io/en/latest/), a Python library designed to transform tabular data into synthetic images for machine learning tasks. It includes videotutorials, slides and Jupyter notebooks that demonstrate how to apply state-of-the-art vision models like Vision Transformers (ViTs) and Convolutional Neural Networks (CNNs) to problems such as regression and classification, using [TINTOlib](https://tintolib.readthedocs.io/en/latest/) for data transformation.\n\nThe repository also features Hybrid Neural Networks (HyNNs), where one branch is an MLP designed to process tabular data, while another branch\u2014either CNN or ViT\u2014handles the synthetic images. This architecture leverages the strengths of both data formats for enhanced performance on complex machine learning tasks. Ideal for those looking to integrate image-based deep learning techniques into tabular data problems.\n"
  ]
}

---

This report was generated automatically by sw-metadata-bot on your main default branch.

If you're not interested in participating, please comment "unsubscribe" and we will remove your repository from our list.
If you would like the pitfalls and warnings to be fixed automatically, please comment "auto-fix" and we will prioritize adding this feature in future iterations.