Greetings! This is an Open Source Repository by the GDSC VIT-B's ML Team for the tenure 2023-2024. This repository consists of multiple ML and DL projects to learn from. We are always open to contributions and innovative ideas!
Here's a list of the showcased projects in this repo:
This project walks you through building your own AI Voice Assistant!
Built using the MNIST Dataset, this project explores both ANN (Artificial Neural Network) and CNN (Convolutional Neural Network) approaches to recognize handwritten digits.
This is a beginner level project to learn Deep Learning.
Inspired from Digit Recognizer Competition , CNN performed better and Results can be seen below:
TA model on classifying Electrics Vehicles on Clean Alternative Fuel Vehicle (CAFV) Eligibility, based on the kaggle dataset Electric Vehicle Population data.
We used XGBClassifier, RandomForestClassifier, Logistic Regression and DecisionTreeClassifier.
One of the most beginner friendly and usually the first of many, this project predicts the Survivability of Passengers aboard the Titanic.
Based on the Kaggle Dataset on Titanic.
We used RandomForestClassifier to achieve an accuracy of 80.6%, with an AUC of 78.7%.
This project aims to predict the likelihood of heart disease in patients based on various health indicators and medical data.
The prediction model analyzes the input features and provide a probability or classification indicating the presence or absence of heart disease.
The Model is built using Machine Learning techniques such as logistic regression, decision trees, random forests, or neural networks.
This project focuses on developing a spam mail detection system using machine learning algorithms.
The goal is to classify incoming emails as either spam or non-spam based on their content and characteristics.
By automatically filtering out spam emails, this system can improve email communication efficiency and security.
The spam mail detection model is built using natural language processing (NLP) techniques and machine learning algorithms such as Logistic Regression.
The model learns to distinguish between spam and ham emails based on the textual content and other features.
This project implements a book recommendation system based on user ratings data.
The system utilizes collaborative filtering techniques to recommend books to users based on their preferences and behavior.
Users who have rated more than 200 books and books with at least 50 ratings are selected to build the recommendation model.
A pivot table is created where each row represents a book and each column represents a user, with ratings as the values.
Cosine similarity is computed between books based on user ratings, resulting in a similarity matrix.
A function is implemented to recommend similar books to a given book.
It takes the book title as input and returns a list of recommended books based on similarity scores.
This project aims to perform sentiment analysis on Twitter data using machine learning techniques.
The sentiment analysis task involves predicting the sentiment (positive, negative, or neutral) of tweets.
The Data is first preprocessed to our requirements by Vectorization and implementing other Basic NLP Preprocessing Techniques.
We then use a Bag of Words approach for our processing to be complete.
We train a Logistic Regression Model for the Sentiment Analysis.
Need help? Feel free to contact me @ [email protected]
Aditya Paul, ML Lead @ GDSC VIT-B © 2023-24
Contributions by Paulie-Aditya:
Contributions by Arihant-Bhandari:
Contributions by SayantikaLaskar:
Contributions by Suhani2407: