Comment Analysis using TfidfVectorizer and Kmeans Clustering
This task simplying used TfidfVectorizer to encode comments from web page and applied kmeans for clustering those comments to discover the underlying structure (i.e group comments that are similar together).
Hakkımda
Senior Machine Learning Engineer with 5+ years experience completing several machine learning projects in the areas of Computer Vision, NLP, Speech Recognition, 3D Medical Imaging, Predictive Analytics, Conversational AI (Chatbots), and Data Visualization. - Led teams of data scientist and machine learning engineers. - Designed and integrated machine learning solutions into web applications services. - Implemented machine learning systems following standard software development lifecycle (dev, staging, and production environments) - Maintained and tracked machine learning projects using issue tracking and software versioning tools such as JIRA, GIthub Detailed experience: - Developing statistical machine learning models - NLP and NLU - Deep Learning - Computer vision - Speech Recognition - Data analytics and Visualisation - Dash (Plotly) - Exposing and consuming RESTful API Skills: - Programming: Python - Tools: R, Matlab - Frameworks: TensorFlow, Keras, Pytorch, Apache Spark - Libraries: Scikit-Learn, Numpy, Pandas, NLTK, CNTK, Matplotlib, Dash (Plotly), SciPy - Databases: MySQL, PostgreSQL, NoSQL, BigQuery, Redis - Version control and Issue Tracking: GIT, JIRA Others: - AWS - Google Cloud Platform - Apache, Nginx, Gunicorn - Web scraping
