search

YifanDengWHU / DDIMDL

65 stars 16 forks source link

table 2 results in paper #13

Open waqarkaleemkhan opened 3 years ago

waqarkaleemkhan commented 3 years ago

When I run your code I get two results files first one is smile+target+enzyme_each_DDIMDL.csv and the second one is smile+target+enzyme_all_DDIMDL.csv I did understand the second file results which are overall results of the paper but can you please tell what is the results of first file is these are results of each and every 65 events. My second question can you please tell me from where did you get the results of table 2 in your paper I am attaching the table pic below. tab

YifanDengWHU commented 3 years ago

Sorry for the late response. For the first file, the result for each event is calculated by regarding the corresponding event as positive examples and other events as negative examples. For the second question, the result in this table is extracted from "all_xxx.csv".

waqarkaleemkhan commented 3 years ago

@YifanDengWHU thanks for your response I understand your first answer about each event but I didn't understand your second answer the file generated with the name "smile+target+enzyme_all_DDIMDL.csv" have 11 values which are the accuracy, auc, aupr, f1 etc in macro and micro measures which are overall results of the code like 0.88 is accuracy so how did you extract the table results from that file. I will attach the screenshot of both csv files can you please elaborate more The below screenshot have 11 values ddim1

and the second pic have 65 values ddim2

can you please explain these two files and from which one you extract the table 2 values and is the pic one with 11 values are the overall results of paper like it is the results of target,enzyme,smiles as a whole results in terms of acc, auc, aupr, f1 etc

YifanDengWHU commented 3 years ago

Sorry for replying late, I'm quite busy these days. As for the table 2 values in the paper, it is extracted from the "smile+target+enzyme_all_DDIMDL.csv". The 11 values correspond to acc, micro_AUPR, macro_AUPR, micro_AUC, macro_AUC, micro_F1, macro_F1, micro_Precision, macro_Precision, micro_recall, macro_Recall. (You can see them in the code). As for the other csv file, we extracted its AUPR and AUC (which are the second and the third columns) and made Fig. 5 (c) and (d) according to these values.