skotak2
Building data products and analytical platforms. Data Engineering and AI/ML enthusiast
UICSeattle, WA
Pinned Repositories
Finding-Similarities-between-the-textual-documents
Cleansing of data for text mining and finding similarities between documents using Jacard and cosine similarities. And computed TF-IDF coefficeints.
Image-Captioning-With-Visual-Attention-Mechanism
Built an encoder - decoder model for captioning an image with visual attention mechanism. Encoding of image was done with CNN and decoding is done with RNN(GRU & LSTM) based networks.
Package-Pricing-At-Mission-Hospital
Built Predictive Model to estimate the price of treatment given the clinical factors at the time of admission.
Pasrsing-Text-with-MapReduce-programming-Paradigm-with-multithreading
Understand how map reduce works for parsing a text data with parallel processing of sub tasks using multi threading
Predictive-Modelling-For-Customer-Engagement-At-VMware
Built a supervised multi-class predictive model to bucket customers based on the events and actions recorded during their interactions with the VMWare's customer engagement portals
PySpark-Operations-for-Analyzing-Customer-Tweets-of-Amazon
PySpark operations to analyze the customer reviews of Amazon Twitter. Analyze the most repeated words on the busiest day of the year.
Review-Based-Recommendation-System
Developed REST API for real-time recommendations based on unsupervised technique - KMeans, where the cluster TF-IDF scores of the reviews and analyze them.
Seq2Seq-Machine-Translation-Model-Kannada-to-English
Developed REST API to perform machine translation using Seq2Seq model. The model deployment was done using google could platform.
Topic-Modelling-For-Depression-Markers
A research study aiming to discover distinguishable pattern between pre and post diagnosis behavior of self-diagnosed individuals with depression on Twitter
Twitter-Sentiment-Analysis
Analyse the tweets and perform sentiment analysis using logistic regression
skotak2's Repositories
skotak2/Review-Based-Recommendation-System
Developed REST API for real-time recommendations based on unsupervised technique - KMeans, where the cluster TF-IDF scores of the reviews and analyze them.
skotak2/Seq2Seq-Machine-Translation-Model-Kannada-to-English
Developed REST API to perform machine translation using Seq2Seq model. The model deployment was done using google could platform.
skotak2/Image-Captioning-With-Visual-Attention-Mechanism
Built an encoder - decoder model for captioning an image with visual attention mechanism. Encoding of image was done with CNN and decoding is done with RNN(GRU & LSTM) based networks.
skotak2/Predictive-Modelling-For-Customer-Engagement-At-VMware
Built a supervised multi-class predictive model to bucket customers based on the events and actions recorded during their interactions with the VMWare's customer engagement portals
skotak2/Finding-Similarities-between-the-textual-documents
Cleansing of data for text mining and finding similarities between documents using Jacard and cosine similarities. And computed TF-IDF coefficeints.
skotak2/Pasrsing-Text-with-MapReduce-programming-Paradigm-with-multithreading
Understand how map reduce works for parsing a text data with parallel processing of sub tasks using multi threading
skotak2/PySpark-Operations-for-Analyzing-Customer-Tweets-of-Amazon
PySpark operations to analyze the customer reviews of Amazon Twitter. Analyze the most repeated words on the busiest day of the year.
skotak2/Topic-Modelling-For-Depression-Markers
A research study aiming to discover distinguishable pattern between pre and post diagnosis behavior of self-diagnosed individuals with depression on Twitter
skotak2/Twitter-Sentiment-Analysis
Analyse the tweets and perform sentiment analysis using logistic regression
skotak2/Package-Pricing-At-Mission-Hospital
Built Predictive Model to estimate the price of treatment given the clinical factors at the time of admission.
skotak2/academic-kickstart
skotak2/apache-spark-streaming-with-twitter
Live streaming of tweets using Spark context and analyzing the sentiment of the tweets
skotak2/Factors-Causing-Chronic-Kidney-Disease
Built the relationship model between factors causing chronic kidney disease. Identified the individuals who could be affected.
skotak2/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.
skotak2/suhaskotaki.github.io
skotak2/Udacity-Data-Engineering-Projects
Few projects related to Data Engineering including Data Modeling, Infrastructure setup on cloud, Data Warehousing and Data Lake development.
skotak2/Word-Embedding
Word embedding