chetank190 Goto Github PK
Name: Chetan Kumar
Type: User
Twitter: _dswhiz
Location: Toronto, Canada
Name: Chetan Kumar
Type: User
Twitter: _dswhiz
Location: Toronto, Canada
We will use a dataset of 1298 “fake news” headlines (which mostly include headlines of articles classified as biased, etc.) and 1968 “real” news headlines, where the “fake news” headlines are from https://www.kaggle.com/mrisdal/fake-news/data and “real news” headlines are from https://www.kaggle.com/therohk/million-headlines. The data were cleaned by removing words from titles not part of the headlines, removing special characters and restricting real news headlines after October 2016 using the word ”trump”.
A Tensorflow model for text recognition (CNN + seq2seq with visual attention) available as a Python package and compatible with Google Cloud ML Engine.
This model can automatically correct the orientation of the input image if it's rotated to 0, 90,180, 270 and 360 degrees.
Research on Drug recommendation system based on sentimental analysis
The purpose of this study was to describe access and use of pain medication, both opioid and non opioid, among PWID living with chronic pain followed in a long-standing community-based cohort in Montreal.
A collection of code snippets from the publication Daily Dose of Data Science on Substack: https://avichawla.substack.com.
R library for personal use.
The purpose of this project is to demonstrate ability to collect, work with, and clean a data set. The goal is to prepare tidy data that can be used for later analysis.
Data Structure and Algorithms
Our project revolves about using deep learning techniques to classify the images of Cats and Dogs. Our classification system uses a Convolutional Neural Network (CNN), which takes an image as input, assigns weights and biases to each aspect of the image, and then uses that information to classify the image. On a very high level, for each image, the prediction is compared with its existing label, and the error between the prediction and the truth is computed. By modifying the parameters of the network, the error is minimized via backpropagation, thus increasing the prediction ability of the network. The main objective here is to teach the model the various distinguishing features of cats and dogs. Upon completion of the training of the model, it will be able to differentiate between images of cats and dogs. We have used the Keras library for training the classifier. We are also exploring the state-of-the-art CNN models to examine the challenges involved in assembling a series of CNN layers to perform a specific function using a data pipeline. The individual layers each perform distinct tasks, so in order to develop a real-world CNN application, it is often necessary to experiment before finding the ideal layer combination.
Performed Sentiment Analysis using basic Natural Language Processing to recommend drugs for a particular medical condition. Using NLTK, created pipeline and applied ML algorithms like LinearSVC, LogisticRegression. LinearSVC has the highest accuracy of 92.89 percentage.
I performed a detailed analysis of various factors that affect the electricity demand in Toronto. I also use a simple linear model tree to forecast the demand.
We are the executive team of a small board game company and we need your help setting up our first Kickstarter campaign. The team has decided that we will need a minimum of $15,000 USD to get this project off the ground. We have ambitions of expanding the business and would like to maximize our funding for this campaign.
Is the amount of lead present in playground surface influenced by the socioeconomic status of the neighborhood and the type of surface of the playground?
Analysis with Linear regression and ANOVA using R programming
Super Resolution for images using deep learning.
OCR for Screen GA
Repository for Programming Assignment 2 for R Programming on Coursera
Python for Data Science and AI is done in Jupyter notebook for learning and educational purpose.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.