# Skills detection from the text — Data

来源：https://www.kaggle.com/competitions/detect-skills-from-text/data

采集时间：2026-10-20T08:56:29Z

# Files

## skills.csv 
This file represents the unique skills that you should try to link to texts. The file has 3 columns:

* ``skill_id`` - the unique identifier of the skill (should be used in the list of skills that you provide as the result variable).
* ``skill_name`` - The name of the skill (in Estonian).
* `skill_description` - The description of the skill (in Estonian).

## texts_about_skills.csv
This file includes the raw texts that need to be mapped with the skills. The file has 2 columns:
* `text_id` - the unique identifier of the text (these identifiers are used both in train and test files).
* `text` - the raw text from where you should find the skills (in Estonian).

## train.csv 
Training set that should be used to build your machine learning models. The training set includes both the text identificator and the ground truth about the ``skills`` that correspond to the text:
* ``text_id`` – the id of the text,
* ``skills`` – space separated list of skill ids that correspond to this text.

## test.csv 
Test set should be used to see how well your model performs on unseen data. The test set includes the ``text_id`` but not the ``skills`` that correspond to the text. It is your job to predict the skills using the model you built on the training data!

## sample_submission.csv
An example of what the submission file should look like. For every row in the test data, submission files should contain two columns: ``text_id`` (representing the id of the text) and ``skills`` (a **space separated list of the skills** corresponding to the text). Example format:

``text_id, skills``

``text0, s0``

``text108, s11 s22 s31 s41``

``Etc.``


In the example above, we say that text with id **text108** includes four skills **s11 s22 s31 and s41**. All unique skills are described in ``skills.csv`` (read more under data section).