Training Data preparation

[GuptaVishu2002]

Hi, would it be possible to describe how to prepare training data (custom) or provide the csv files used to preprocess the datasets in train_model.ipynb, as the preprocessing seems to require several columns other than the ones provided in example_input.csv? Thank You.

[ch4perone]

Hi, the preprocessing steps can be found in the lib_loader directory. For example, you can look at the publicly available data from MSnLib, MSDial and CASMI. In particular, for MSnLib, you should be able to download the data, adjust the file path, and run the script to obtain a csv with the required metadata. All details are in the msnlib_loader.ipynb file. In the future, I may be able to provide a mock-up training example. Alas, due to other projects, I won't get to that very soon.

[ch4perone]

For processing the latest MSnLib version (msnlib_loader.ipynb), you may also want to check out the dev branch.