Umang Gupta's repositories
Chatmore-Chat-app
Created a customised real time chat app with both public and private chat capabilities using Node.js, MongoDB,Socket.IO,JavaScript,HTML and Bootstrap 4.
CRUD-App-
I made a Crud App using Node.js,Express.js and Mongoose.js. I built out a book Schema for creating,reading,updating and deleting books. Used Express Scripts to create routes that will form the basis for a restful API. Used POSTMAN to perform actions on the routes All the book details were altered as JSON objects. I created and used Google Chrome to confirm the changes made on the local host server port 8080.
Email-Feedback-
I made a chrome extension using Javascript, Jquery, CSS, HTML and Bootstrap which gives feedback on the content of the email. All the erros are recieved as JSON objects from the server.
FIFA-2018-Predictor-
I used Machine Learning to make a Logistic Regression model using scikit-learn, pandas, numpy, seaborn and matplotlib to predict the results of FIFA 2018 World Cup.
FlickPick
Deployed various Machine Learning models to classify the NLTK corpus movie reviews as positive or negative through Natual Language Processing and Sentiment Analysis. The models used include tf-idf, Count Vectorizer, Logistic Regression ,Support Vector Machine and the Naive Bayes probability model.
Predicting-Email-Grammatical-Flow-
Trained and optimized a Classification Machine Learning model to predict the grammatical flow of email using state of the art techniques : 1. Word2Vec 2. tf-idf 3. bag-of-words. The models used include Logistic Regression and Support Vector Mechanics with 250-300 features.
AntiDistracto
Platform to prevent distracted driving and help drowsy drivers 🚗(Top 10 @ HackTheValley 4)
Breast-Cancer-Detection-
The goal is to use Machine Learning to classify the Cancer as Benign or Malignant. I got a 96.4% accuracy by using the KNearest Neighbors strategy.
ReciPy
Python-based application to help you decide what to do with the left over groceries in your fridge!
Finding-Waldo
Template Matching OpenCV algorithm to find Waldo
GUI-Claculator-Python-
Pyhton Tkinter
Image-Classification-
I deployed a Convolutional Neural Network(ALL-CNN) for Object recognition. It obtains state of the art performance at object recognition on the CIFAR 10 image dataset in 2015.
Login-App
I made a Login App using Express.js, building Mongoose Schemas , perform validation checks in mongoose and installing mongoose plugins. The plugins and validation checks were used to update the data acquired from the login and adding it to the database.
Shopify-Image-Repo
Backend Developer Intern Challenge
Titanic-Survival-Kaggle-Contest
I participated in the ongoing Kaggle Competetion and predicted with a 76.5% accuracy if a person will survive the iconic Titanic shipwreck.