Anna Mattessich and Keerthi Mula
Final Project, choose own data, make a model
For the project, you can largely pick what you want to do. Essentially, select some data that can be analyzed with AI and work to make a notebook that walks through the process of analyzing the data.
Your own data
Kaggle
UCI Machine Learning Repository***
NASA Earth Data
Google Dataset Search
Introduction: Describe the data and where you got the data. Describe the question being answered and the method(s) being used to answer the question.
Data pre-processing: What's needed to load the data, clean the data, normalize, etc.
Model setup: Setup one or more models
Hyperparameter tuning: Do some playing with the model hyperparameters (learning rate, optimizer, batch size, epochs, whatever makes sense)
Results: How did the model do
Discussion: Summarize what worked, what didn't etc.
From UC Irvine Machine Learning Repository
Mushroom ,Donated on 4/26/1987 ,From Audobon Society Field Guide; mushrooms described in terms of physical characteristics; classification: poisonous or edible
https://archive.ics.uci.edu/dataset/73/mushroom
"This data set includes descriptions of hypothetical samples corresponding to 23 species of gilled mushrooms in the Agaricus and Lepiota Family (pp. 500-525). Each species is identified as definitely edible, definitely poisonous, or of unknown edibility and not recommended. This latter class was combined with the poisonous one. The Guide clearly states that there is no simple rule for determining the edibility of a mushroom; no rule like ``leaflets three, let it be'' for Poisonous Oak and Ivy."
Mushroom. (1987). UCI Machine Learning Repository. https://doi.org/10.24432/C5959T.