navyashiva Goto Github PK

academic-kickstart

academic-kickstart-1

amazon-product-recommendation-system

amazon-product-recommendationsystem

automated-image-captioning-system

Automated Image Captioning System

competition-winners

The code for the prize winners in DrivenData competitions.

demo-repo-

document-similarity

Jaccard similarity and cosine similarity of the document 'UIC' with 'UIUC', 'MIT','UIS','Tesla', and 'Stanford' text documents

getoldtweets-python

A project written in Python to get old tweets, it bypass some limitations of Twitter Official API.

instagram-depression-detection

End-to-end project to predict the mental health status of Instagram users from their posts and images. Built Un-supervised LDA and Semi-supervised Topic Models using text features. Modeled Support Vector Classifier to predict the probability of depression and improved accuracy from 70% to 94.5% at 89% recall and 92% precision.

mapper-reducer

Implemented Mapper Reducer from scratch

python_opencv_trials

salary-classification-based-on-job-description

Classification of salaries based on job descriptions using text analytics and classification techniques | Achieved ~80% accuracy in classification of salaries, a 30% increase from baseline accuracy of 50%

screening-tool-for-chronic-kidney-disease-prediction

Built an interactive screening tool that predicts the risk of having a Chronic Kidney disease using a Logistic regression model having 97% recall.

simple_site

Following the tutorial to make my own website

tfidf_logistic-regression

twitter-analysis-of-covid19-over-time

Extracted user profile features, and the tweets of users from Twitter. Modeled Naive-Bayes classifier to classify tweets into individual or organization level, with an accuracy of 87%. Built Unsupervised LDA and semi-supervised Topic model and identified the themes through research and analyzed how the topics changed over time.

walmart-sales-forecasting

word-embedding