Program that can take in large amounts of .csv files in the same directory and trains a deep learning neural network model based on the best/worst students evaluated by the user. Second program then utilizes the model from the first program to produce a projected report for each individual student inputted.

Use Key NLP techniques to classify news articles into categories: Bag_of_Words (tf-Idf), word embeddings and BERT language model

🤖 Sentiment Analysis using IMDb Reviews. The project contains TfidfVectorizer for representing text in numeric form. 🎥

A machine learning model for detecting fake news

The aim - is to develop a model that will give accurate predictions for the customer's test sample, but the training sample for is not given. It should be collected by parsing

Steam recommendation system

In this project we are comparing two approaches for movie recommendation for a new user or existing user based on their age, gender, occupation.

This project is a Python-based data science end-to-end chatbot designed to autonomously handle conversations without the need for human intervention. Leveraging advanced natural language processing (NLP) techniques and machine learning algorithms, the chatbot is capable of understanding user queries, providing relevant responses.

Fake new detection using text classification as real or fake news segments. Required installations - Python 3.8, NLTK, Scikit-Learn, Jupyter. Text cleaning, tokenization, vectorization, classification model generation and evaluation.

Movie recommendation system using TfidfVectorizer, NearestNeighbors

feature extraction, Vectorization, similarity scores, finding closest match to user input, find index, enumerate similarity, give recommendations.

Amazon reviews Sentiment Analysis

A Lite Implementation of sklearn TfidfVectorizer

Movie Recommendation System based on machine learning concepts

Intents-Based Chatbot with Streamlit

For our final project, our group chose to use a dataset (from Kaggle) that contained medical transcriptions and the respective medical specialties (4998 datapoints). We chose to implement multiple supervised classification machine learning models - after heavily working on the corpora - to see if we were able to correctly classify the medical sp…

Data consists of tweets scrapped using Twitter API. Objective is sentiment labelling using a lexicon approach, performing text pre-processing (such as language detection, tokenisation, normalisation, vectorisation), building pipelines for text classification models for sentiment analysis, followed by explainability of the final classifier

Restrictions on sharing as advised by DataCamp