大家一起練習用 DNN 分類寶可夢吧！
===========

題目類型 - 分類問題：
-----

class 總共有 6 種不同的寶可夢，分別為 class 0, 1, 2, 3, 4 or 5 ，其中
class 0 = [ Sandshrew](https://bulbapedia.bulbagarden.net/wiki/Sandshrew_(Pok%C3%A9mon))
No.27
class 1 = [Tentacool](https://bulbapedia.bulbagarden.net/wiki/Tentacool_(Pok%C3%A9mon))
No.72
class 2 =  [ Slowpoke](https://bulbapedia.bulbagarden.net/wiki/Slowpoke_(Pok%C3%A9mon))
No.79
class 3 = [ Magnemite](https://bulbapedia.bulbagarden.net/wiki/Magnemite_(Pok%C3%A9mon))
No.81
class 4 = [ Voltorb](https://bulbapedia.bulbagarden.net/wiki/Voltorb_(Pok%C3%A9mon))
No.100
class 5 = [Exeggcute](https://bulbapedia.bulbagarden.net/wiki/Exeggcute_(Pok%C3%A9mon))
No.102
# 資料包括之欄位如下:

* appearedTimeOfDay - time of the day of a sighting (night, evening, afternoon, morning)

* appearedHour/appearedMinute - local hour/minute of a sighting (numeric)
* terrainType - terrain where pokemon appeared described with help of GLCF Modis Land Cover (numeric)
* closeToWater - did pokemon appear close (100m or less) to water (Boolean, same source as above)
* city - the city of a sighting (nominal)
* continent (not always parsed right) - the continent of a sighting (nominal)
* 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)
* temperature - temperature in celsius at the location of a sighting (numeric)
* windSpeed - speed of the wind in km/h at the location of a sighting (numeric)
* pressure - atmospheric pressure in bar at the location of a sighting (numeric)
* 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)
* population density - what is the population density per square km of a sighting (numeric, Source)
* 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)
* gymDistanceKm, pokestopDistanceKm - how far is the nearest gym/pokestop in km from a sighting? (numeric, extracted from this dataset)
* gymIn100m-pokestopIn5000m - is there a gym/pokestop in 100/200/etc meters? (Boolean)
* 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)
## * class - says which pokemon it is, to be predicted.




##問題：
預測每筆 data 的寶可夢類別 (0, 1, 2, 3, 4 or 5)

##練習方向：
* Data preprocessing and feature engineering
* DNN model construction and hyper-parameter tuning
* Metrics: Accuracy

#通過條件： 超越 Public baseline
##上傳次數：
一天可以上傳20次，上傳時，Team Name請以您的學號命名，如AT073001。