Use group$\_1.$csv data in the canvas. The dataset is collection of $300$ support

tickets manually labeled for semantic similarity, obtained from an IT support company in the Florian$$polis

$($Brazil$)$ region. Each ticket is represented by an unstructured text field, which is typed by the user that

opened the call. The labeling process was performed in $2022$ by three IT support professionals. The corpus

contains tickets in many languages, mainly English, German, Portuguese and Spanish. For this task, you

must use only the English language support tickets.

First preprocess the data using tokenization $($you can use x$.$split$()$ in python$)$ and lower casing $($can use

x$.$lower$())$ the documents. Create a term$-$frequency document matrix and calculate document similarity

matrix using:

a$.$ Euclidean Distance,

b$.$ Manhattan Distance

c$.$ Cosine Similarity.

For this task, you may use term$-$frequency matrix like CountVectorizer in python. However, to

calculate the similarity matrix you must not use any direct package. The output of this question should be

three matrices. And mention five documents by rank that are the most similar document to id $98287$ using

the three different distance formula and give comparative analysis.