GRMK11
Aspiring Data Scientist ,completed data science program at Edwisor. holds an MBA majored in marketing two plus year experience in sales & Marketing
Pinned Repositories
Edwisor-Project
Analysis of Healthcare company services through its data
GRMK11.github.io
PowerBeats
Personalised-Medicine-project
Basically, the problem is all about personalised treatment regarding personalised treatment for cancer through genetic testing. Genetic map is unique for every individual. Mutations in genes leads to cancer. So our problem in precise is all about classifying clinically actionable mutations that led predefined treatment for cancer. Challenge lies in distinguishing mutilations that contribute to cancer growth. Currently this interpretation of genetic mutations is being done manually. This is a very time-consuming task where a clinical pathologist has to manually review and classify every single genetic mutation based on evidence from text-based clinical literature. We need to develop a Machine Learning algorithm that, using this knowledge base as a baseline, automatically classifies genetic variations.
surgical-mask-detection-system
Banking-Sector
The problem is all about categorising the bank customers into different categories having strong similarity within the group .with the dataset containing bank transactions data. Some of the data elements are transaction id, customer id ,transaction amount , mode of transactions, etc.Need to come up with algorithms that can segment users into different categories.So the problem is of unsupervised learning in nature.
Detect-Facial-Features
Code example demonstrating how to detect eyes, nose, lips, and jaw with dlib, OpenCV, and Python
Face-Detection-Recognition-Using-OpenCV-in-Python
Using OpenCV in Python to detect face and features like eyes, nose and mouth and also training custom classifier to recognize a face.
opencv_contrib
Repository for OpenCV's extra modules
Sentiment-Analysis-and-Map-Viz-of-Tweets-
This project “Prognostication of Box Office Talk using Twitter Corpus” predicts the success of the movie using state of mind of the people that could possibly be achieved by sentiment analysis. The analysis is done with Naive Bayes Classifier which is a supervised text classification algorithm attaining 81 percent of F-Score. This work is also incorporated with visualization of data in R language which stands one among the best in representing the analysis in pictorial format and a map visualization that portrays the location of the tweets with the user name whom it has come from.
TFIDF-Vectorization
( Scratch development ) Term Frequency Inverse Document Frequency is a vectorization technique used widely in Natural Language Processing. The vectorization effectively gives importance to rare words and important words.
GRMK11's Repositories
GRMK11/surgical-mask-detection-system
GRMK11/opencv_contrib
Repository for OpenCV's extra modules
GRMK11/GRMK11.github.io
PowerBeats
GRMK11/TFIDF-Vectorization
( Scratch development ) Term Frequency Inverse Document Frequency is a vectorization technique used widely in Natural Language Processing. The vectorization effectively gives importance to rare words and important words.
GRMK11/twitter-sentiment-visualisation
:earth_africa: The R&D of a sentiment analysis module, and the implementation of it on real-time social media data, to generate a series of live visual representations of sentiment towards a specific topic or by location in order to find trends.
GRMK11/Face-Detection-Recognition-Using-OpenCV-in-Python
Using OpenCV in Python to detect face and features like eyes, nose and mouth and also training custom classifier to recognize a face.
GRMK11/Banking-Sector
The problem is all about categorising the bank customers into different categories having strong similarity within the group .with the dataset containing bank transactions data. Some of the data elements are transaction id, customer id ,transaction amount , mode of transactions, etc.Need to come up with algorithms that can segment users into different categories.So the problem is of unsupervised learning in nature.
GRMK11/Edwisor-Project
Analysis of Healthcare company services through its data
GRMK11/Personalised-Medicine-project
Basically, the problem is all about personalised treatment regarding personalised treatment for cancer through genetic testing. Genetic map is unique for every individual. Mutations in genes leads to cancer. So our problem in precise is all about classifying clinically actionable mutations that led predefined treatment for cancer. Challenge lies in distinguishing mutilations that contribute to cancer growth. Currently this interpretation of genetic mutations is being done manually. This is a very time-consuming task where a clinical pathologist has to manually review and classify every single genetic mutation based on evidence from text-based clinical literature. We need to develop a Machine Learning algorithm that, using this knowledge base as a baseline, automatically classifies genetic variations.
GRMK11/Detect-Facial-Features
Code example demonstrating how to detect eyes, nose, lips, and jaw with dlib, OpenCV, and Python
GRMK11/Sentiment-Analysis-and-Map-Viz-of-Tweets-
This project “Prognostication of Box Office Talk using Twitter Corpus” predicts the success of the movie using state of mind of the people that could possibly be achieved by sentiment analysis. The analysis is done with Naive Bayes Classifier which is a supervised text classification algorithm attaining 81 percent of F-Score. This work is also incorporated with visualization of data in R language which stands one among the best in representing the analysis in pictorial format and a map visualization that portrays the location of the tweets with the user name whom it has come from.