Marking scheme
You will get “excellent”, or 100% for this lab report if everything
is perfect. You will get “good”, or 75% if there are minor issues such
as
- Using explicit loops when it is not really needed (which is very
rare)
- Using base R for data wrangling or plotting instead of
tidyverse pipelines when a tidyverse solution was
explicitly taught in the lab.
- Re-inventing the wheel, i.e., implementing your own versions of
built-in functions from scratch.
- Not answering verbal questions to the point
- Writing fragile code that unnecessarily depends on the ordering of
data, such as the order of columns, rows, or factor levels, when
variables or levels could be referred to explicitly by name. *Poor or
non-reproducible presentation of the report, such as giving answers as
comments inside R code, manually copying computed values into the text
instead of using inline R code, or otherwise failing to clearly
integrate explanations, code, and output.
You will get “average”, or 50% if there are serious issues in your
report, such as
- Not doing data normalization when it is needed
- Not splitting the data into training and test sets for training ML
models
- Missing one question entirely
You will get “poor”, or 25% if you barely attempt this report.
Examples of this are
- Submitting your report without the output of R codes
- Just doing one of two questions out of the four
- Giving nonsensical answers to all questions
You will get “not done”, or 0% if you do not attempt this report, if
you fail to declare AI usage when you have actually used generative AI,
or if you copy another student’s answer.
It is okay to use generative AI and it is okay to discuss these
questions with your peers, but in the end of the day, this is indivudual
work and you are responsible for it.