{
  "fetched_at": "2026-10-20T12:39:02Z",
  "source_url": "https://www.kaggle.com/competitions/2020irtmhw3/data",
  "pages": [
    {
      "name": "data-description",
      "content": "提供training data跟sample submission下載\n\ntest data就是1095文檔中，除了training data以外的都是\n\nFile descriptions\ntraining.txt - the training set\n訓練資料\n\nhw3_sam.csv - a sample submission file in the correct format\n上傳格式範本，Id代表docid，Value代表分到哪一類，這次作業分為13類，所以Value會介於1~13之間",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "NTU 2020 IR\n\nMultinomial NB Classifier\n注意事項：\n\n作業三要求大家自己實作 NB 分類，所以不能用現成套件來做分類！！\n如果有需要之前作業一作業二的內容，可以直接改來用。\n作業三是有標準答案的，最後的評分就是依據 F1 score，\n使用kaggle是希望讓大家可以即時知道自己模型的表現，\n所以大家可以依據 kaggle 分數來決定要不要做哪些處理，\n但記得把你們的決定寫在 report 中。\nkaggle 說明文件中，對於隊名有規定，請大家使用學號開頭，\n另外，僅限一人一隊，請不要額外創小帳去增加測試次數。\n如果有kaggle使用上的問題或其他問題再寄信給我們詢問！！\n補充說明：\n\ntfidf、Chisqure等計算，請不要使用套件，主要是希望大家可以了解原理實作出來。\n作業其實是循序漸進的，像是tfidf就可從作業二的內容改來用。",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation pages describes how submissions will be scored and how students should format their submissions. You don't need a sub-title at the top (the page title appears above). For an example of a high quality evaluation page, see the 2013 KDD Cup page, which we have copied here:</p>\n<hr>\n<p>The evaluation metric for this competition is <a href=\"https://www.kaggle.com/wiki/MeanFScore\"> Mean F1-Score</a>. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:</p>\n<p>\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]</p>\n<p>The F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.</p>\n<h2>Submission Format</h2>\n<p><strong>For every author in the dataset</strong>, submission files should contain two columns: AuthorId and DuplicateAuthorIds. DuplicateAuthorIds should be a space-delimited list. Every AuthorId counts as his/her own duplicate, and every duplicate should be listed under each of its respective ids.&nbsp;For example, if you suspect author A, B, and C are the same, you should list (A,A B C), (B,B A C), (C,C A B).</p>\n<p>The file should contain a header and have the following format:</p>\n<pre>AuthorId,DuplicateAuthorIds<br>1,1<br></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}