sanapagarkar Goto Github PK

advertisement-optimizer

Applied Reinforcement Learning Techniques, Upper Confidence Bound and Thompson Sampling, to find the most marketable advertisement.

automobile-price-prediction

blog

braintrainer

A fun math game for kids to learn and practice their basic mathematics that keeps count of their score.

connect3

A two-player game for everyone to pass their time. The player who succeeds to connect 3 badges first, wins.

consumer-dynamic-segregator

Developed Unsupervised Learning, clustering technique, K-Means, and Agglomerative Hierarchical Clustering to form multiple groups of customers based on annual income and spending scores.

customer-churn-prediction-model

Created a Sequential Model, demonstrated one hot encoding on categorical features of the dataset followed by feature scaling, used Adam optimization algorithm, to predict whether a customer leaves or stays in the bank based on various features.

customer-classification-model

Developed Supervised Classification Models, Logistic Regression, K-Nearest Neighbours, SVM, Kernel SVM, Naive Bayes, Decision Tree, and Random Forest Classification models to classify customers into categories for purchase of product based on salary and age, demonstrated feature scaling on the dataset.

deploy-mlm-flask-heroku

digit-recognizer

Built an artificial neural network for digit recognition from scratch applying the feedforward and backpropagation algorithms using numpy, used sigmoid function for the hidden layer followed by softmax function with cross-entropy function for the output layer to get an accuracy of 87.4%.

doc-sharing

flappy-bird-clone

A clone of the game, Flappy Bird in which the user plays by tapping on the screen trying to move through all pipes without collision while saving the bird from falling out of the screen.

gitws

guess-the-celebrity

A fun multiple choice game app to test your knowledge of the recognized and respected faces of pop culture.

hiker-s-watch

An app that provides hikers with all the information needed about the place they are exploring.

image-recognizer

Developed a Sequential model, added convolutional and pooling layers to compress the image dataset and to obtain important features used to distinguish between cats and dogs using Keras library.

memorable-places-app

An app to display a list of all the memorable places the user chooses to add using Google maps.

news-app

An app to show a list of news headlines and the corresponding news articles. (Online and Offline)

notes-app

An android app that keeps a list of all your important notes you have made and let's you customize your list.

online-bookstore

An online website for reading enthusiasts to get their favourite books at home. The website allows the customer to rent it as and when they like.

profile

Repo for github workshop 2017

profit-prediction

Developed Supervised Regression Model, Multiple Linear Regression to predict the profit of startups based on various other features, performed one hot encoding on categorical features of the dataset.

review-classifier

Used Gaussian Naive Bayes classifier to classify reviews for a restaurant, used re library functions to clean text and list ‘stopwords’ from nltk to discard irrelevant words, followed by stemming and created a corpus of relevant words.

salary-predictor

Developed Supervised Regression Models, Simple Linear, Polynomial, Support Vector, Decision Tree, and Random Forest Regression models to relate employees’ salaries with their position in the company, demonstrated feature scaling on the dataset.

standard-library-in-x

Notes and readings for STL workshop

tourists--best-friend

An app to help tourists know some common phrases in the local language to communicate with the people there.

twitter-clone

A clone of a platform that allows to people to share their thoughts.

whatsapp-clone

A clone of an app that provides a platform for people to convere.