search

wang363 / Raman-model-transfer

1 stars 0 forks source link

Questions about the use of data #1

Open hmyao22 opened 3 months ago

hmyao22 commented 3 months ago

Hello Zilong, thank you for your excellent work and sharing of data. I would like to ask you about how to use train.csv. I don't understand what its different rows represent. Which rows are the measurement data obtained by the two instruments in?

In addition, I think you have made an outstanding contribution to the Raman community. I hope to have further exchanges with you. My email address is yhm22@mails.tsinghua.edu.cn. I hope to get in touch with you if it is convenient!

wang363 commented 3 months ago

Hello, thank you for your reminder. I have re-uploaded the dataset, including train.csv and test.csv. These two files contain data collected from two different instruments. Each file includes data on 58 different compounds, with 100 data points for each, totaling 5800 columns. The Raman shifts of the compounds range from 200 to 2200 (cm^-1), resulting in 1801 rows. However, this is part of my graduation project, so the complete code might not be uploaded until a year later. If you have any other questions, feel free to leave a message.

hmyao22 commented 3 months ago

Hello, thank you for your reminder. I have re-uploaded the dataset, including train.csv and test.csv. These two files contain data collected from two different instruments. Each file includes data on 58 different compounds, with 100 data points for each, totaling 5800 columns. The Raman shifts of the compounds range from 200 to 2200 (cm^-1), resulting in 1801 rows. However, this is part of my graduation project, so the complete code might not be uploaded until a year later. If you have any other questions, feel free to leave a message.

Thank you very much for your reply. It would be great if I could add your WeChat at your convenience. My number is 19911813371.

hmyao22 commented 3 months ago

Also, as you pointed out, there are 58 different compounds in the data set, can you provide the names of those compounds?

wang363 commented 3 months ago

In the file val.csv, the Chinese names of the chemicals are included, but they might appear as garbled text due to UTF-8 encoding issues. I have re-uploaded Chemical name.xlsx, which contains the chemical names corresponding to the data in the dataset in order.