About Harmanpreet
Data Scientist with more than 2 years of hands-on experience dealing with wide array of complex datasets across various domains.
Main areas of expertise :-
- Developing end-to-end ML pipelines on cloud
- Data Wrangling & Data Visualization
- Model Development & Training
- Statistics
- Computer Vision
- Natural Language Processing
Tech Stack:-
Programming Languages: Python, SQL, HTML, JavaScript, C
Data Visualization: Matplotlib, Seaborn, Tableau
Data Analysis: Pandas, Pandas-Profiling, Tableau Prep, Dtale
Data Extraction: BeautifulSoup, Requests, Restful-Api
Web Development: React JS, Flask, FastApi, Sqlalchemy, Streamlit
Machine Learning: Scikit-Learn, NumPy, SciPy, Pandas, Yellowbrick
Deep Learning: Pytorch, FastAI, Tensorflow, Keras
Computer Vision: OpenCV, Pillow, Scikit-Image, Imgaug
Natural Language Processing: Spacy, Gensim, Transformers, NLTK
Big Data: DataBricks, Spark, MLlib
Cloud: AWS, Google Cloud Platform (GCP)
Version Control: Git
English
Fluent
Punjabi
Native or bilingual
Hindi
Native or bilingual
Can work on-site
Sydney (up to 50km), Melbourne (up to 50km), Canberra (up to 50km)
Experience
- FiverrML EngineerRESEARCHOctober 2020 - February 2021 (5 months)Sydney, Australia-Helped a client to develop a Regression framework for ML based calibration of low cost ozone sensor using Environmental data.-Assisted in EDA (Exploratory Data Analysis) and data visualization-Supervised model development with final coefficient of regression resulted in getting doubled (0.62) from the initial baseline model
- IncitesData Scientist InternTECHMarch 2021 - Today (5 years and 3 months)Sydney, AustraliaProjects:-1. Events Manager- Created an event managing webapp for a news-publication client to help them in generating content based on local events.- Implemented the app using Flask at the backend and React JS on the frontend2. Topic Analytics- Created a Jupyter notebook to perform auto-classfication and generate topic level insights using advanced NLP techniques.- Generated topics from article body for 20K+ articles using LDA (Latent Dirichlet Allocation) and NMF (Non-Negative Matrix Factorization)- Utilised NLTK & Spacy for processing text and Scikit-Learn & Gensim for implementing the unsupervised learning algorithms.
Recommendations
These freelancer profiles also match your criteria
Agatha Frydrych
Backend Java Software Engineer
4.7
(3)
2
Baptiste Duhen
Fullstack developer
4.6
(4)
5
Amed Hamou
Senior Lead Developer
4
(2)
7
Audrey Champion
Web developer
4.3
(3)
4
Education
- Master of Information TechnologyUNSW2020Artificial Intelligence