Data Scientist
Quadratyx
Total years of experience :6 years, 8 Months
Machine Learning Classification Project involves the following responsibilities:
⬧ Analyzing and visualizing exploratory data.
⬧ Utilizing PySpark for pre-processing data
⬧ Create a representative sample of data for training purposes.
⬧ Train and evaluate models.
⬧ Generate KPI Matrics Generation.
Health Care Projects involves following responsibilities:
⬧ Analysis the Health Care data and visualizing
⬧ Create mysql/Nosql query for fetching data from DB
⬧ Using pandas for EDA and preprocessing
⬧ Model Training using Catboost and XGboost Algorithm
⬧ Model Evaluate using Growdtruth data
⬧ Create Api using Django
Generative AI (Document Chat Engine)
⬧ Generate chatbot using Hugging Face Fine Tuning Model and Local /hugging
face embedding model.
⬧ Generate Chatbot using Open Ai Model and Llama Indexing.
⬧ Generate Meta data using Open Ai and Llama Indexing
Developed and executed machine learning and deep learning projects.
⬧ Implemented NLP object detection projects.
⬧ Proficient in data science and machine learning, tools including data mining, data visualization, and text mining.
⬧ Skilled in data visualization using tools like matplotlib and Tableau.
⬧ Knowledgeable in deep learning frameworks such as Tensorflow, Keras, and PyTorch.
⬧ Experienced in normalizing US addresses.
⬧ Proficient in image processing techniques.
Developed a Malayalam part-of-speech tagger and editor using Flask, Python, MySQL, and PHP.
⬧ Implemented Malayalam to English transliteration using Conditional Random Fields (CRF).
⬧ Generated Malayalam Word2Vec representations.
⬧ Extracted information from OCR output for both English and Malayalam.
⬧ Used tools like Gensim, FastText, and Python word2vec for word2vec extraction.
⬧ Created a chatbot using Chatterbot and rule-based methods.
⬧ Skilled in using tools such as Weka and CRF++.