Group Project for Data Science 100 @ UBC
- Using knn classification techniques, predict weather patterns using several quantitative variables.
- Weather categories: clear, rain, snow
Weather predictions play a pivotal role in various aspects of people's daily lives, encompassing everyday activities such as commuting to work or school, as well as impacting critical sectors like agriculture and tourism. Consequently, the ability to forecast weather accurately, utilizing key atmospheric indicators such as temperature and humidity, promises significant convenience for our lives. In this context, our group's focus lies in weather category prediction, employing two primary variables: temperature and atmospheric pressure. Our weather dataset comprises seven forecasted variables, including temperature, precipitation, humidity, wind speed and direction, atmospheric pressure, cloud cover, and UV index. However, for our project, we will concentrate on two of these variables. Additionally, our dataset features a target variable column representing weather categories, encompassing seven primary classifications: clear, rain, snow, cloudy, haze, fog, and drizzle. It's worth noting that some combined weather categories will not be utilized in our project. Instead, our analysis will center around five distinct categories: clear, rain, snow, haze, and fog.