Projects
Twitter Streaming Data Pipeline using Python on Airflow, Amazon EC2, and Amazon S3
I embarked on a project building a Twitter Streaming Data Pipeline. Using Twitter API, Tweepy, and Python, I extracted tweets, transformed them into structured Pandas data frames, orchestrated the process on Apache Airflow via an Amazon EC2 instance, and securely stored results in an Amazon S3 bucket. This seamless pipeline demonstrates efficient data engineering for real-time insights. Click here to learn more.
Creation of a data streaming pipeline utilizing Kafka, Amazon EC2, S3, Athena, and Glue.
The Stock Market Kafka Real-Time Data Engineering Project successfully designed and executed an end-to-end data pipeline using Apache Kafka. Incorporating Python, AWS services, Glue, and Athena, it captured, processed, and analyzed real-time stock market data. The architecture ensured seamless data flow, and key technologies like Kafka, S3, and EC2 played essential roles. This achievement stands as a testament to collaboration, innovation, and our commitment to data-driven insights. Click here to explore my work.
Fashion Trend Prediction for E-commerce using EfficientNetB1-B7
I executed a project predicting e-commerce fashion trends using EfficientNetB1-B7 and a clustered fashion dataset. Gathered and preprocessed data, performed K-means clustering, and trained an EfficientNet model. Evaluated predictions' accuracy, visualized trends, and assessed model performance. This approach offers accurate trend forecasting with computational efficiency for practical industrial use, enhancing fashion decision-making. Click here to see the details.
