This assignment is worth $50\%$ of the final score, divided $\frac{50}{50}$ between the technical part

$($i$.$e$.,$ code$)$ and the presentation. The goal of this assignment is to implement a solution

to the chosen environmental problem and present it to the class. This assignment has

the Hackathon format.

Datasets:

For this challenge, you have two options.

$(1)$ Rain Radardataset: follow the link for further information on the data. Suggestion: Use

either the Tairua or the Opitonui as your target. Extra train ing, you will need to generate

your target column by using preprocessing tech niques. The dataset contains the current

reading and you will need to forecast the same value a few timestamps in the future.

hint$1$: Most traditional libraries have a 'shift' function that can help you create the target

value. hint$2$: Do not try very large horizons. Try with horizons smaller than $12h.$

$(2)$ South Wales solar power plant: this dataset contains weather informa tion

andtheaverageSolar Irradiance in W$.$ Thegoalofthis dataset is to forecast the SlrW Avg

column. You also need to generate the target column. hint$3$: In this case, a few of the

algorithms work quite well with $)$

File format:

Converting the dataset to the format you intend to use is part of the challenge. Both

datasets are already in CSV format, but you might want to clean it

Libraries and tools:

You are free to use any preprocessing method$/$tool you want. For the model, you are free

to use the libraries we used so far $($i$.$e$.,$ MOA and river$)$ or another library $($CapyMOA$).$

Groups using CapyMOA will be graded accordingly, as we assume there is a learning

curve. Independently of the library you use, your method has to be online. Groups using

standard batch algorithms will have their grades significantly reduced.