Lab Assignment 2

Submitted By

• Ruthvic Punyamurtula (Problems - 3,4)
• Sai Charan Kothapalli (problems - 1,2)

Resources

• youtube demo - part 1
• youtube demo - part 2
• Source Code

Introduction

This is lab assignment 2 of cs5590 - python/Deep Learning class. This lab is based on the tasks done in ICE 5, ICE 6 & ICE 7 which can be found here.

Objective

In this assignment, we used kaggle datasets & implemented

• Naïve Baye’s, SVM and KNN implementation
• K-Means Clustering
• NLP pipeline
• Multiple Linear Regression

Approaches/Methods

Used pandas Dataframe for data cleaning, used NLTK for nlp pipeline, performed silhoutte score calculation for evaluating k-means

Workflow

1. Apply Classification algorithms - Naive Bayes, SVM, KNN

Naive bayes(Output and Code include in the same image)

SVM (Output and code included in same image Graph - 1)

(Output and code included in same image Graph - 2)

KNN

2. Apply K-Means clustering

Code Snippets

Output

3. Read given text file and perform lemmatization, tokenization, tri-grams and pick top 10 trigrams

Code Snippets

Code snippets

4. Perform Multiple linear regression

Code Snippets

Output