{
  "fetched_at": "2026-10-20T04:32:53Z",
  "source_url": "https://www.kaggle.com/competitions/aia-dnn-classification-pokemongo-fourth/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": "詳見 Overview 說明\n<h2>File descriptions</h2>\n<ul>\n<li><strong>train.csv</strong> - the training set</li>\n<li><strong>test.csv</strong> - the test set</li>\n<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format</li>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "\n<p>大家一起練習用 DNN 分類寶可夢吧！\n===========\n\n題目類型 - 分類問題：\n-----\n\nclass 總共有 6 種不同的寶可夢，分別為 class 0, 1, 2, 3, 4 or 5 ，其中\n<p> class 0 = [ Sandshrew](https://bulbapedia.bulbagarden.net/wiki/Sandshrew_(Pok%C3%A9mon))\nNo.27\n<p> class 1 = [Tentacool](https://bulbapedia.bulbagarden.net/wiki/Tentacool_(Pok%C3%A9mon))\nNo.72\n<p> class 2 =  [ Slowpoke](https://bulbapedia.bulbagarden.net/wiki/Slowpoke_(Pok%C3%A9mon))\nNo.79\n<p> class 3 = [ Magnemite](https://bulbapedia.bulbagarden.net/wiki/Magnemite_(Pok%C3%A9mon))\nNo.81\n<p> class 4 = [ Voltorb](https://bulbapedia.bulbagarden.net/wiki/Voltorb_(Pok%C3%A9mon))\nNo.100\n<p> class 5 = [Exeggcute](https://bulbapedia.bulbagarden.net/wiki/Exeggcute_(Pok%C3%A9mon))\nNo.102\n<p># 資料包括之欄位如下:\n\n* appearedTimeOfDay - time of the day of a sighting (night, evening, afternoon, morning)\n\n* appearedHour/appearedMinute - local hour/minute of a sighting (numeric)\n* terrainType - terrain where pokemon appeared described with help of GLCF Modis Land Cover (numeric)\n* closeToWater - did pokemon appear close (100m or less) to water (Boolean, same source as above)\n* city - the city of a sighting (nominal)\n* continent (not always parsed right) - the continent of a sighting (nominal)\n* weather - weather type during a sighting (Foggy Clear, PartlyCloudy, MostlyCloudy, Overcast, *Rain, BreezyandOvercast, LightRain, Drizzle, BreezyandPartlyCloudy, HeavyRain, ** BreezyandMostlyCloudy, Breezy, Windy, WindyandFoggy, Humid, Dry, WindyandPartlyCloudy, DryandMostlyCloudy, DryandPartlyCloudy, DrizzleandBreezy, LightRainandBreezy, HumidandPartlyCloudy, HumidandOvercast, RainandWindy)\n* temperature - temperature in celsius at the location of a sighting (numeric)\n* windSpeed - speed of the wind in km/h at the location of a sighting (numeric)\n* pressure - atmospheric pressure in bar at the location of a sighting (numeric)\n* weatherIcon - a compact representation of the weather at the location of a sighting (fog, clear-night, partly-cloudy-night, partly-cloudy-day, cloudy, clear-day, rain, wind)\n* population density - what is the population density per square km of a sighting (numeric, Source)\n* urban-rural - how urban is location where pokemon appeared (Boolean, built on Population density, <200 for rural, >=200 and <400 for midUrban, >=400 and <800 for subUrban, >800 for urban)\n* gymDistanceKm, pokestopDistanceKm - how far is the nearest gym/pokestop in km from a sighting? (numeric, extracted from this dataset)\n* gymIn100m-pokestopIn5000m - is there a gym/pokestop in 100/200/etc meters? (Boolean)\n* cooc 1-cooc 151 - co-occurrence with any other pokemon (pokemon ids range between 1 and 151) within 100m distance and within the last 24 hours (Boolean)[ List of Pokémon by National Pokédex number](https://bulbapedia.bulbagarden.net/wiki/List_of_Pok%C3%A9mon_by_National_Pok%C3%A9dex_number)\n## * class - says which pokemon it is, to be predicted.\n\n\n\n\n##問題：\n預測每筆 data 的寶可夢類別 (0, 1, 2, 3, 4 or 5)\n\n##練習方向：\n* Data preprocessing and feature engineering\n* DNN model construction and hyper-parameter tuning\n* Metrics: Accuracy\n\n#通過條件： 超越 Public baseline\n##上傳次數：\n一天可以上傳20次，上傳時，Team Name請以您的學號命名，如AT073001。\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is [ Accuracy-Score](https://en.wikipedia.org/wiki/Accuracy_and_precision).",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}