CPSC6430 Project 2: Choosing a Model for Predicting on Unseen Data solution


Original Work ?


5/5 - (4 votes)

For Project 2 you will create a regression program and choose a model to predict the women’s
Olympic 100-meter race record time for year 2022. We will code the year of each race as we did
in lecture 2.3. A text file with the data is available on Canvas for the years 1928 through 2008
when the Olympics were held. The first line of the text file indicating there’re m lines of data
and a n number of features (in this case, one).
Your project assignment is to compare three different models, linear, quadratic, and cubic.
hw(x) = w0 + w1x
hw(x) = w0 + w1x + w2x2
hw(x) = w0 + w1x + w2x2 + w3x3
using 5-fold cross validation.
Then you should present a chart, similar to the one in the lecture (see below), of all your test
results and a plot of your training andtest J’s with respect to the polynomial degree.
Linear Quadratic Cubic
Mean for Training
Mean for Testing
Based on your data and plot, you should then:
• Argue which model (linear, quadratic, or cubic) you expect will best predict the times for
the women’s Olympic 100-meter race in the future.
• Compute weights using the complete data set with your best model.
• Using those weights, write a Python program that takes a year as input, then outputs
the winning women’s Olympic 100-meter race time for that year.
Important Note:
You cannot use python machine learning package that can have the k-fold validation algorithm
as embedded function, for instance, sklearn package.
You are required to submit a project report, including:
• The J value chart as shown in the table above.
• A plot of your training and test J’s with respect to the polynomial degree
• Argue which model (linear, quadratic, or cubic) you will choose
• The final hypothesis function hw(x)
• Predict the women’s Olympic 100-meter race record time for this winter Olympic (2022)
• Full screenshot of your python console.
• A copy of your code
Your report should be named yourlastname_yourfirstname_P2.docx or .doc or .pdf. Your
Python program should be named yourlastname_yourfirstname_P2.py, then zipped together
with your project report and uploaded to Canvas