chetank190 Goto Github PK

-fake-news-headlines-classification-with-nearest-neighbours-

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”.

are_you_still_using_elbow_method

attention-ocr

A Tensorflow model for text recognition (CNN + seq2seq with visual attention) available as a Python package and compatible with Google Cloud ML Engine.

auto-image-orientation-correction

This model can automatically correct the orientation of the input image if it's rotated to 0, 90,180, 270 and 360 degrees.

big-data-research-project

Research on Drug recommendation system based on sentimental analysis

chronic-pain-experience-of-pwid

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.

daily-dose-of-data-science

A collection of code snippets from the publication Daily Dose of Data Science on Substack: https://avichawla.substack.com.

dailyshortcutchetan

R library for personal use.

data-cleaning-project

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

Data Structure and Algorithms

dogcatsclassifier_bigdataproject

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.

drug-recommendation-system-based-on-sentiment-analysis

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.

dswhiz

electrical_demand_toronto

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.

fake-news-classification-using-knn

gender-discrimination-analysis-using-r-programming

house-price-prediction-using-r-programming

image-rotation

kickstarter-campaign-business-brief

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.

lead-exposure-in-playgrounds-

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?

linear-regression-and-anova

Analysis with Linear regression and ANOVA using R programming

neural-enhance

Super Resolution for images using deep learning.

ontario-peak-power-forecasting

optical_char_recog

OCR for Screen GA

programmingassignment2

Repository for Programming Assignment 2 for R Programming on Coursera

python-for-data-science-and-ai

Python for Data Science and AI is done in Jupyter notebook for learning and educational purpose.

pythonic-accountant

ricnn

tsx-composite-price-prediction