Common Instructions:
Please work on the term project individually. Use
Google Colab to complete the project. Once you are done, download the colab
file by clicking on File -> Download – > Download.ipynb. Rename that file
in the format AI602_YourName.ipynb.
Also, prepare a word document reporting what you
understand from the original data, what methodology/packages etc. you are using
to address the problem and the findings from your work. With Times New Roman font
and font size of 12, this should be approximately a 3-4 page document for each
dataset.
Upload the Google Colab notebook and the Word
document in the Brightspace platform by May 07 midnight. Name your Word
document in the same format as Google Colab notebook.
Things to do:
1. Demonstrate
your understanding of the given data by using different exploratory data
analysis methods
2. Plot
graphs to visualize the relationship between variables of interest
3. Write
comments to explain what you are trying to do with the code
4. Use
different metrics to show the accuracy of your model
5. Generate
plots (or, confusion matrix) to give a visual representation of the model’s
accuracy.
Dataset #1: This
dataset (AI602_TermProj_LinReg.xlsx that is attatched) consists of 9568 data points collected
from a Power Plant. Features consist of hourly average ambient temperature
(AT), ambient pressure (AP), relative humidity (RH), and exhaust vacuum (V) to
predict the net hourly electrical energy output (EP). Utilize linear
regression technique to predict the energy output.
AT – Ambient temperature
V – Exhaust vacuum
AP – Ambient pressure
RH – Relative humidity
EP – Energy output
Dataset #2:
This dataset is related to the passengers in the Titanic ship. It is already
available in the Seaborn library. You may import it using load_dataset method. Utilize
logistic regression technique to predict the survival of the passengers.
In certain cases, you may have to use dummy variables for numeric
representations. Use your best judgment to identify the relevant variables for
this exercise. For the logistic regression problem, you need to import it from the Seaborn library. The Seaborn library has numerous in-built datasets and one of them is the Titanic dataset. You can import it by using load_dataset command.
