{
  "fetched_at": "2026-10-19T09:10:33Z",
  "source_url": "https://www.kaggle.com/competitions/csci-ml-s19-pa2/data",
  "pages": [
    {
      "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
    },
    {
      "name": "data-description",
      "content": "<p>This page shows up underneath the data files. </p>\n<h2>File descriptions</h2>\n<ul>\n<li><strong>wiki_labeled.zip</strong> (MD5sum: 8af376e8a0f9898d8d3dd5653351070e) - the labeled dataset (in zip archive format), and should be used to train and test the model. The wiki_labeled/ directory will contains 60327 facial images kept in 100 folders, naming 00-99. Dimension of each image is 100 pixels by 100 pixels. </li>\n<li><strong>wiki_labeled.mat</strong> (md5sum: d5b65bb4c4d414a230b60b8025ece276) file, containing meta information of each of the 60327 images. It contains the following information about each of the 60327 images:</li>\n<ul>\n    <li> ID: identification number of the subject (starting from 2002)</li>\n    <li> dob: the date of birth of the subject. (It is Matlab’s datenum value calculated based on total number of days since January 0, 0000.)</li>\n    <li>dob_str: the DD-MMM-YYYY format dob value.</li>\n    <li> photo_taken: when the photo was taken (only the year  value)</li>\n    <li> full_path: directory path, including filename of the image</li>\n    <li> gender: Gender of the subject (0: female, 1: male, NaN if unknown)</li>\n    <li> name: name of the subject</li>\n    <li> face_location: location of the face.</li>\n    <li> face_score: detector score (the higher the better). Inf implies that no face was found in the image, and the face_location then just returns the entire image.</li>\n    <li> second_face_score: detector score of the face with the second highest score. This is useful to ignore images with more than one face. second_face_score is NaN (not a number) if no second face was detected.</li>\n    <li> age: age of the person (in years), and was calculated based on the “dob” value and the “photo_taken” values.</li>\n</ul>\n<li><strong>wiki_judge_images.zip</strong>(md5sum: 551a46ee18286824ad03d9110750da01) containing 2001 facial images (1.png, 2.png, …, 2001.png) of resolution 100x100. This is the judge/test dataset for you based on what you are going to apply your learned model to predict ages of the 2001 subjects.</li>\n<li><strong>wiki_judgeX.mat</strong>(md5sum: b7382fd03b8fc05575bb5701c0eec25b) contains some meta information about the 2001 images. However, the information does not include “age” field.</li>\n\n<li><strong>sample_submission.csv</strong> - a sample submission file in the correct format. Please disregard the values in the age field. They are all made up values.</li>\n</ul>\nHint: To read/extract information from the mat file above, please use the loadmat library from scipy.io in python . [  from scipy.io import loadmat ] \n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>In this assignment you are going to develop a program that would be able to guess age (in years) of a person given his/her photo.</p>\n<p>Roughly speaking, it is expected that you will first do the principal component analysis (PCA) to perform dimensionality reduction on the given dataset. Then, train a linear regression model on the reduced-dimension dataset to learn their age. Done!I</p>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is [RMSE](\"https://www.statisticshowto.datasciencecentral.com/rmse/), Root Mean Square Error. \n\nRMSE is defined as: \n<p>\\[ RMSE = \\sqrt{MSE} = \\sqrt{\\dfrac{1}{m}\\sum_{i=1}^m\\left(y_i-h_w(x_i)\\right)^2} \\]</p>\nwhere, there are m samples, y<sub>i</sub> is the true/known target label for the i<sup>th</sup> sample, and h<sub>w</sub>(x<sub>i</sub>) is the predicted target for the input sample x<sub>i</sub>.\n<hr />\n\n<h2>Submission Format</h2>\n<p><strong>For every author in the dataset</strong>, submission files should contain two columns: ID and age </p>\n<p>The file should contain a header and have the following format:</p>\n<pre>ID,age<br />1,38.8<br /><span style=\"font-size: 14px; line-height: 1.4em;\">2,25<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\">etc.</span></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}