# Extreme Classification-Dataset3 — Data

来源：https://www.kaggle.com/competitions/extreme-classification/data

采集时间：2026-10-19T09:10:22Z

The dataset folder contains 3 files -
trn_ft_mat.txt
- the training feature file
trn_lbl_mat.txt
- the training label file
tst_ft_mat.txt
- the test feature file
Feature file format -
First line specifies number of datapoints and the total number of features. Each of the following lines contains features active in that datapoint.
<#datapoints> <#features>
<feature_id:feature_value> <feature_id:feature_value> <feature_id:feature_value>
<feature_id:feature_value> <feature_id:feature_value> <feature_id:feature_value>
etc.
Label file format -
First line specifies number of datapoints and the total number of labels. Each of the following lines contains labes active in that datapoint.
<#datapoints> <#labels>
<label_id:1> <label_id:1> <label_id:1>
<label_id:1> <label_id:1>
etc.
Reading/Writing data in Matlab -
You can download the scripts from
[here](https://drive.google.com/open?id=17XO9kMlVLnoOJ_Ry1BYJWrUnGtTesagG)
to read feature and label sparse matrices from .txt files into matlab: (Note that these scripts are present in the folder named matlab)
To read a text matrix into Matlab: 
       [matrix] = read_text_mat([text matrix name]);
To write a Matlab matrix into text format:
       write_text_mat([Matlab sparse matrix], [text matrix name to be written to]);