search

kmboehm / onco-fusion

Other
25 stars 5 forks source link

I can not find preprocessed_hne_df.csv and preprocessed_tissuetype_hne_df.csv in data/dataframes #2

Closed CoderJackZhu closed 1 year ago

CoderJackZhu commented 1 year ago

I can not find preprocessed_hne_df.csv and preprocessed_tissuetype_hne_df.csv in data/dataframes. I wander if there does not exist in provided data zip file? And could you please provided these files or what should I do to get them by my work.

kmboehm commented 1 year ago

These files are generated by the preprocess.py script. Specifically, preprocessed_hne_df.csv is derived from data/dataframes/hne_df.csv by line 16 of hne-feature-extraction/1_infer_tissue_types_and_extract_features.sh, and preprocessed_tissuetype_hne_df.csv is derived from data/dataframes/tissuetype_hne_df.csv by line 19 of tissue-type-training/cross_validate_on_annotations.sh. Hope this helps.

CoderJackZhu commented 1 year ago

Thanks for your detailed reply. I am glad to receive your answer and understand this problem. This code is a little challenging to comprehend and I am trying to conquer it.