Shreya's repositories
datasciencecoursera
Data Science with R coursera repo
Tweet-Classifier
UnderGrad Final Project
yelp-scrapping
yelp-scrapping done for RA work
ABC
pytorch implementation of ABC : Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning
Class-Imbalanced-Semi-Supervised-Learning
Class-Imbalanced Semi-Supervised Learning code
Cracking-the-Data-Science-Interview
Cracking the Data Science Interview
Data-Science-Interview-Resources
A repository listing out the potential sources which will help you in preparing for a Data Science/Machine Learning interview. New resources added frequently.
data-science-interviews
Data science interview questions and answers
datasharing
The Leek group guide to data sharing
explore
Community-curated topic and collection pages on GitHub
FixMatch-pytorch
Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"
From-0-to-Research-Scientist-resources-guide
Detailed and tailored guide for undergraduate students or anybody want to dig deep into the field of AI with solid foundation.
iter-together-FINISHED
Code accompanying a 180 minute tutorial on June 3rd, 2020 about Python package structure, installation with pip, unit testing, automation, CLI building, and more.
mean-teacher
A state-of-the-art semi-supervised method for image recognition
numpy
The fundamental package for scientific computing with Python.
OSD-Git101-Workshop-2022
sample
Prediction-of-Clinical-Risk-Factors-of-Diabetes-Using-ML-Resolving-Class-Imbalance
Being the most common and rapidly growing disease, Diabetes affecting a huge number of people from all span of ages each year that reduces the lifespan. Having a high affecting rate, it increases the significance of initial diagnosis. Diabetes brings other complicated complications like cardiovascular disease, kidney failure, stroke, damaging the vital organs etc. Early diagnosis of diabetes reduces the likelihood of transiting it into a chronic and severe state. The identification and analysis of risk factors of different spinal attributes help to identify the prevalence of diabetes in medical diagnosis. The prevalence measure and identification of diabetes in the early stages reduce the chances of future complications. In this research, the collective NHANES dataset of 1999-2000 to 2015-2016 was used and the purposes of this research were to analyze and ascertain the potential risk factors correlated with diabetes by using Logistic Regression, ANOVA and also to identify the abnormalities by using multiple supervised machine learning algorithms. Class imbalance, outlier problems were handled and experimental results show that age, blood-related diabetes, cholesterol and BMI are the most significant risk factors that associated with diabetes. Along with this, the highest accuracy score .90 was achieved with the random forest classification method.
PseudoLabeling
Official implementation of "Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning"
RCoursera
Test
Red-GAN
Code for corresponding MIDL2020 paper
Rtest
Testing R
shreya-singh-tech.github.io
My Website
temperature_scaling
A simple way to calibrate your neural network.
TorchSSL
A PyTorch-based library for semi-supervised learning (NeurIPS'21)
UDA_pytorch
UDA(Unsupervised Data Augmentation) implemented by pytorch
vision
Datasets, Transforms and Models specific to Computer Vision