Phishing Detection

Develop a program to detect if a website is phishing or not
automatically. To make this decision, a certain set of features has been defined, and values
collected in two different datasets. Dataset has 48 features with 10K instances. Column !bel/span>
specifies the label of data and (+1) means phishing samples and (0) means legitimate samples.

Data Preparation and Visualization
? Create a data uploader to upload CSV files to Google drive. For that, you can use ïde
snippet¼/span>
? Draw histogram charts for /span>NumNumericChars/span> and rlLength/span> features for phishing and
legitimate websites separately but in one graph. Use a different color to make it more
clear.
? Get a sample of 200 instances with exactly 100 phishing and 100 legitimate samples. In
the next, round feature #tExtHyperlinks/span> by two decimal places of this sample dataset,
and then draw a bar chart for this feature for phishing and legitimate samples separately.

Model Evaluation
? Split the dataset into two sets of train data and test data. Use 80% of data for training
and 20% for testing. You need to select these two sets of data randomly.
? Create four sets of training data, training labels, and testing data.
? Using train and test data, fit three different classification models we discuss in class and
predict labels for test data.
? Draw three confusion matrices for each algorithm and save them into png files
? Report the following metrics for each algorithm: Accuracy, Precision, Recall, and
F1-score for each algorithm.
? Compare and explain results from each algorithm and explain which one performs better.

Some considerations for your program:
? For this assignment, you need to use Google Colab text cells to explain your algorithms
and discuss results.
? Your figures/charts should use visible colors, appropriate font size, x- and y-axis labels,
and chart titles.
? Ensure that your prompts and output are crisp, professional, and well-formatted. For
example, ensure that you have used spaces appropriately and checked your spelling.
Ensure that graphs are appropriately titled and that axes are appropriately labeled.
? Adding comments to your code is encouraged. You may decide how best to comment on
your code. At a minimum, please use a comment at the start of your code to describe its
basic functionality.