There is a newer version of this record available.

Dataset Open Access

A Code Token Type Taxonomy-enhanced dataset with pre-computed token types for Python150k

Le, Kim Tuyen; Rashidi, Gabriel; Andrzejak, Artur


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/8f229008-3a22-4f5d-83d1-b201885d0c74/CT3-dataset-20210729.zip"
      }, 
      "checksum": "md5:f0bd6c8b0e13ccf1ef039f46640a6c5a", 
      "bucket": "8f229008-3a22-4f5d-83d1-b201885d0c74", 
      "key": "CT3-dataset-20210729.zip", 
      "type": "zip", 
      "size": 1050354220
    }
  ], 
  "owners": [
    222463
  ], 
  "doi": "10.5281/zenodo.5148586", 
  "stats": {
    "version_unique_downloads": 2.0, 
    "unique_views": 16.0, 
    "views": 20.0, 
    "version_views": 48.0, 
    "unique_downloads": 0.0, 
    "version_unique_views": 35.0, 
    "volume": 0.0, 
    "version_downloads": 2.0, 
    "downloads": 0.0, 
    "version_volume": 2127232230.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.5148586", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.5148585", 
    "bucket": "https://zenodo.org/api/files/8f229008-3a22-4f5d-83d1-b201885d0c74", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.5148585.svg", 
    "html": "https://zenodo.org/record/5148586", 
    "latest_html": "https://zenodo.org/record/5733013", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.5148586.svg", 
    "latest": "https://zenodo.org/api/records/5733013"
  }, 
  "conceptdoi": "10.5281/zenodo.5148585", 
  "created": "2021-07-30T14:30:07.230122+00:00", 
  "updated": "2021-11-28T21:24:46.506531+00:00", 
  "conceptrecid": "5148585", 
  "revision": 3, 
  "id": 5148586, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.5148586", 
    "description": "<p>Code Token Type Taxonomy (CT3) is a methodology for refined evaluation of ML-based code completion approaches.</p>\n\n<p>We published the&nbsp;CT3-enhanced dataset with pre-computed token types for each token in the <a href=\"https://www.sri.inf.ethz.ch/py150\">Python150k dataset</a>.</p>\n\n<p>The dataset was obtained from&nbsp;an empirical study of the below paper:</p>\n\n<p>Kim Tuyen Le, Gabriel Rashidi, and Artur Andrzejak. A Methodology for Refined Evaluation of ML-based Code Completion Approaches. In <em>KDD Workshop on Programming Language Processing (PLP)</em>, August 14-18, 2021 (Virtual).</p>\n\n<p>Please read the README.txt file for detailed information of structuring the enhanced dataset.</p>", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "title": "A Code Token Type Taxonomy-enhanced dataset with pre-computed token types for Python150k", 
    "relations": {
      "version": [
        {
          "count": 2, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "5148585"
          }, 
          "is_last": false, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "5733013"
          }
        }
      ]
    }, 
    "references": [], 
    "keywords": [
      "code completion", 
      "accuracy evaluation", 
      "code token types"
    ], 
    "publication_date": "2021-07-30", 
    "creators": [
      {
        "affiliation": "Heidelberg University", 
        "name": "Le, Kim Tuyen"
      }, 
      {
        "affiliation": "Heidelberg University", 
        "name": "Rashidi, Gabriel"
      }, 
      {
        "affiliation": "Heidelberg University", 
        "name": "Andrzejak, Artur"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.5148585", 
        "relation": "isVersionOf"
      }
    ]
  }
}
48
2
views
downloads
All versions This version
Views 4820
Downloads 20
Data volume 2.1 GB0 Bytes
Unique views 3516
Unique downloads 20

Share

Cite as