avichals Goto Github PK

analytical-debate-messi-vs-ronaldo

Using data scraped from the web to analyze footballers' performance with the help of statistics and visualizations. Aiming to answer the question: Messi vs Ronaldo!

avichals

avichalsharma.github.io

My Portfolio Website.

book-recommendation-using-knn

Created a book recommendation algorithm using K-Nearest Neighbors using the Book-Crossings dataset, containing 1.1 million ratings of 270,000 books by 90,000 users.

cat-dog-image-classifier

Used TensorFlow 2.0 and Keras to create a convolutional neural network that correctly classifies images of cats and dogs 82% of the time.

customer-personality-analysis

Identifying various trends, patterns, and correlations in customer personality and behavior to provide recommendations on how to improve customer retention, strategize for better market capitalization, and target specific customer/product segments.

ecommerce-webapp

A fullstack eCommerce Webapp using Flask, HTML, CSS, Javascript and MySQL, for students to buy stationary.

email-spam-filtering

An email spam classification system based on Multinomial Naive Bayes, it uses NLP techniques to pre-process a dataset of spam/ham emails and trains a logistic regression model to be able to predict whether new emails are spam/ham. Evaluation of model accuracy is based on precision, recall, and F1-score metrics.

flight-price-predictor

Prediction of flight prices using the best fit regression model.

health-costs-calculator

Prediction of healthcare costs using a neural network.

house-pricing-model

Predictive machine learning model with 79 explanatory variables describing (almost) every aspect of residential homes in Ames, Iowa.

iris-decision-tree

This code is an implementation of a decision tree algorithm for classifying the Iris flower dataset. It loads the dataset, trains a decision tree classifier, visualizes the decision tree graphically, and allows the user to input new measurements for prediction of the Iris species.

job-application-system

End-to End system development and deployment through replit and render, using HTML/CSS and Flask (Python) and connecting to MySQL Workbench databases.

josaa-model

Python program to extract results from given JOSAA '22 counselling database.

license-plate-detection

Using OpenCV and PyTesseract to read the license plate of a car.

login-page

Designed a simple login/sign up page using HTML, CSS and JS.

recommendation-system

The project is a Python implementation of a recommendation system using Collaborative Filtering, a technique for making personalized recommendations by analyzing the preferences and behavior of users. The system analyses user and movie data to provide accurate suggestions to users based on predictions made by the model.

rock-paper-scissors

The algorithm implements a strategy based on tracking the opponent's play history and making decisions based on the frequency of different play sequences.

salary-predictor

Salary prediction using best fit regression model and interactive Streamlit user interface for prediction based on job role, location and experience.

score-prediction-system

End-to-End Python Machine Learning model and HTML web application for prediction of test scores based on decision variables deployed using AWS Elastic Beanstalk.

spaceship-titanic-prediction

Prediction model on whether a passenger was transported to an alternate dimension during the Spaceship Titanic's collision with a spacetime anomaly using TensorFlow's RandomForestModel and some visualizations.

speech-emotion-recognition

Developed a deep learning model using Multi-Layer Perceptron to recognize and classify speech signals into 6 distinct emotions. Extracted 160 audio features, enabling the model to detect emotions with around 75% accuracy on the training set. Implemented the model on a Streamlit dashboard.

text-classifier-neural-network

A Neural network that will classify SMS messages as either "ham" or "spam" using LSTM in a Keras Sequential model with 99.6% accuracy and 1.6% loss.

text-sentiment-analysis

Performing text sentiment analysis on numerous websites and determining their text sentiment scores using NLP and python programming.

titanic-machine-learning-model

Created a machine learning model that predicts which passengers survived the Titanic shipwreck.

transportation-simplex

This project aims at providing the optimal solution for minimum transportation costing based on two decision variables along with a pictorial overview of the problem. The project uses Excel for dataset cleaning and manipulation as well as python programming for simplex solution and finally, SAS Visual Analytics for visualization.