search

chloechsu / nanoparticle

Machine learning project for predicting nanoparticle geometry from emissivity spectra.
MIT License
5 stars 4 forks source link

Can't find simulated_data #2

Closed Mind-Insight closed 1 month ago

Mind-Insight commented 1 month ago

@smglsn12 @chloechsu I tried to build yours project, but I can't find simulated data in the link, that you gave in repo

smglsn12 commented 1 month ago

Thank you for reaching out! This is a clarity issue on my part, the file "Cu_reproducable_alignment_df_extracted_110222.joblib" is a dataframe containing the simulated data. Use the paper_files notebook to load this dataframe! After running the 4th cell, you can call "test_rf_obj.spectra_df" to see the full dataframe, or you can just load it directly without using the analysis object defined in the 4th cell.

If you're looking for the raw feff output, that is contained in the "dataset generation" folder. The raw feff files are broken into whether the feff file came from the materials project (zip files Z=29, missing_Cu_L2_results and missing_Cu_L3_results) or whether they were simulated for this project (Stable_and_exp_Cu_with_results).

I'll add some notes to the readme explaining these locations! Sorry for the confusion. Please reach out again if you have any other questions!

Best, Sam

On Mon, Sep 23, 2024 at 9:25 AM Timofey @.***> wrote:

@smglsn12 https://github.com/smglsn12 @chloechsu https://github.com/chloechsu I tried to build yours project, but I can't find simulated data in the link, that you gave in repo

— Reply to this email directly, view it on GitHub https://github.com/chloechsu/nanoparticle/issues/2#issuecomment-2368780374, or unsubscribe https://github.com/notifications/unsubscribe-auth/AMEP47EWWVNZ5WT4QH27NVLZYA6IDAVCNFSM6AAAAABOWODWAKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDGNRYG44DAMZXGQ . You are receiving this because you were mentioned.Message ID: @.***>

Mind-Insight commented 1 month ago

Thank you so much for responding to me! I am a student, and there are many things I don't understand yet. Now I have this question:

Thanks again for your help, I will definitely give you a special thanks in my work and will recommend your project

smglsn12 commented 1 month ago

Hello! I must apologize, I thought this issue was raised in a different repository (I just released a different module with a paper published late last week and I've been fielding a lot of questions about that - I didn't do my due diligence replying to you and just assumed it was that project! I'm sorry about this). The repo you're looking at is a class project I did (with Chloe Hsu) at the start of my PhD. IT's about 5 years old and I haven't looked at it in quite some time. I'll poke around and see if I can find what happened to the dataset for this if it's not available in the repo!

Best, Sam

On Mon, Sep 23, 2024 at 11:19 AM Timofey @.***> wrote:

Thank you so much for responding to me! I am a student, and there are many things I don't understand yet. Now I have this question:

  • Could you please explain more about how to get simulated data. I am missing the files you refer to, namely “Cu_reproducible_alignment_df_extracted_110222.joblib”. I am also missing the cache folder (as I understand it should be generated by train_RF_and_gen_data.py)

Thanks again for your help, I will definitely give you a special thanks in my work and will recommend your project

— Reply to this email directly, view it on GitHub https://github.com/chloechsu/nanoparticle/issues/2#issuecomment-2369035446, or unsubscribe https://github.com/notifications/unsubscribe-auth/AMEP47E66IT55DCY3RUZAU3ZYBLSXAVCNFSM6AAAAABOWODWAKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDGNRZGAZTKNBUGY . You are receiving this because you were mentioned.Message ID: @.***>

Mind-Insight commented 1 month ago

Thank you so much for your reply, I will be very grateful to you if you do help with the problem.

smglsn12 commented 1 month ago

The data you're looking for should be here: mhmodzoka/DT_inverse_design: Predicting spectral emissivity of particles from a given material and geometry using decision trees and random forest. (github.com) https://github.com/mhmodzoka/DT_inverse_design I'm also a little curious to know how you found this repo and what you're looking to use it for!

I'll update the readme to link to a version of our reference paper that specifies where the data is located!

Best, Sam

On Tue, Sep 24, 2024 at 1:18 AM Timofey @.***> wrote:

Thank you so much for your reply, I will be very grateful to you if you do help with the problem.

— Reply to this email directly, view it on GitHub https://github.com/chloechsu/nanoparticle/issues/2#issuecomment-2370585891, or unsubscribe https://github.com/notifications/unsubscribe-auth/AMEP47AGEX6NHOOVVM2YQ6DZYEN3TAVCNFSM6AAAAABOWODWAKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDGNZQGU4DKOBZGE . You are receiving this because you were mentioned.Message ID: @.***>

Mind-Insight commented 1 month ago

thank you very much, I was able to get your project up and running. I was interested in this topic and found your project on the Internet, I wanted to study its work better and in general to see what will be the result of code execution, as I myself will have to write something similar in the future. Thank you very much again for your help in launching the application, I really appreciate it.