Scikit-learn version - plot_confusion_matrix issue and data source step description

[palanikumarraaj]

Hi,

I have been trying your script for learning purpose. It is very useful. I would like to add and request a few points.

The original data has 20532 columns around with Cancer_type. So, you have did some pre processing and make it as your .csv file input. If possible you can please upload the same .csv input in github for easy usage for others or please provide steps or instructions to make such dataset.

The major issue is plot_confusion_matrix missing in the recent scikit-learn version 1.5.2
There is not much details about package version details in your page. It would be a good practice to provide package version details or installation details.

If possible please update with more description in ML related steps i.e. KNeighbors and so on.

Thank you

[alairdata]

Hello Palanikumar Palanichamy, Thank you for reaching out and for your kind words about the script. I’m glad you found it useful for your learning purposes! Here’s a response to your points: 1. Pre-processed CSV File: I appreciate your suggestion regarding uploading the pre-processed .csv file to GitHub. Unfortunately, due to potential data sharing restrictions, I may not be able to upload it directly. However, I can provide a detailed step-by-step guide on how to preprocess the original dataset to create a similar input file. I’ll update the repository shortly with these instructions. 2. plot_confusion_matrix Deprecation in Scikit-learn 1.5.2: Thank you for pointing this out! The function plot_confusion_matrix has indeed been deprecated in recent versions of Scikit-learn. I’ll update the script to reflect the latest implementation using ConfusionMatrixDisplay and include a note regarding compatible versions. 3. Package Version Details: I completely agree that specifying package versions is essential for reproducibility. I’ll update the repository to include a requirements.txt file or a list of package versions used in the script. 4. ML-related Step Descriptions: Your feedback about adding more descriptive explanations of the ML steps, such as KNeighbors and other algorithms, is well-received. I’ll enhance the documentation to make these steps clearer for learners. Thank you for taking the time to provide these valuable suggestions. Please feel free to share any further feedback or questions! Thank you, Princilla Abena Koranteng.

…

On Mon, Dec 2, 2024 at 11:22 AM Palanikumar Palanichamy < ***@***.***> wrote: Hi, I have been trying your script for learning purpose. It is very useful. I would like to add and request a few points. The original data has 20532 columns around with Cancer_type. So, you have did some pre processing and make it as your .csv file input. If possible you can please upload the same .csv input in github for easy usage for others or please provide steps or instructions to make such dataset. The major issue is plot_confusion_matrix missing in the recent scikit-learn version 1.5.2 There is not much details about package version details in your page. It would be a good practice to provide package version details or installation details. If possible please update with more description in ML related steps i.e. KNeighbors and so on. Thank you — Reply to this email directly, view it on GitHub <#1>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/A2FJPWLB6QMSIBMAVGILW3D2DQ7FTAVCNFSM6AAAAABS3FHVO2VHI2DSMVQWIX3LMV43ASLTON2WKOZSG4YTCNJWGE4TKNI> . You are receiving this because you are subscribed to this thread.Message ID: <alairdata/Prediction-of-Cancer-Types-using-Gene-Expession/issues/1@ github.com>

[palanikumarraaj]

Thanks a lot for your time and detailed explanation. It helps a lot.

I am looking forward to the update and more such projects from you.

Cheers!