============================ August 9, 2004 By Fei Yuan ============================ Problem: Protein Homology ( KDD cup 2004 ) Files are stored in the directory: /home/grad/fyuan/public_html/kdd, /home/grad/fyuan/public_html/data Data files: Total row number: 145751 Response file: kdd_act.txt Descriptor file: kdd training data set: kdd_train.txt (74 variables) Operations on the data: August 9, 2004 By Fei Yuan: Response variable was stored seperatedly in "kdd_act.txt"; explanatory variables were stored into "kdd_train.txt". Variables have been labelled as following: BlockID ExampleID y x1 - x74 Helper files: Fold file: kdd_fold.txt Code for generating folds: kdd_organize_data.R Code for organizing data: kdd_organize_data.R Explanatory file: kdd_explanation.txt