# Document Classification with a Perceptron — Data

来源：https://www.kaggle.com/competitions/docum-classif/data

采集时间：2026-10-19T22:33:05Z

This file contains, in matlab format, 

- A matrix Xts of dimension 43586x13960 where each row corresponds to a word and each column to a document. 

- A vector yts of dimension 13960x1 that provides the class into which each column of Xts belongs to. There are 20 classes so that yts(i) in {1,2,...20} for all i. 

- A matrix Xvr of dimension 43586x5989 which is the validation test for which you have to provide predictions. 

I have also attached an example of a submission file where all 5989 documents are predicted to belong to the first topic. 

**IMPORTANT: Due an issue in Matlab, I have replaced all categories from 1,2,...20 to 101,201,...2001 (*100+1).**