- Experience leveraging Python, Matplotlib, Plotly, Seaborn, Scikitlearn, Tensorflow, Keras, Pytorch, TFLearn to build, visualize and fine tune Confidential models for prediction and classification.
- Applied Java to write multiple applications including the backend to a HR management software.
- SQL and variants experience with performing data operations for business consumption and Confidential tasks.
- Built interactive maps to visualize and storytell with geo tagged data. For example, created a geographical mapping of sentiment extracted from tweets based on keyword of choice.
- Used Shell Scripting extensively to build and execute SQL scripts, to manage cloud environments, to setup and maint ain deep learning models on AWS, to manage Hadoop clusters and tasks.
- Experience parsing data through APIs, web scraping and online catalogs for training Confidential models.
- Cleaned structured and unstructured data, scaled and normalized data using Pandas as well as automated data processing with python.
- Implemented software development life cycles and Agile methodologies as part of a team.
- Worked in a fast - paced dynamic environment to meet software development deadlines.
- Organized and led teams to tackle business challenges, document and present findings to leadership and other stakeholders.
Data Engineering Intern
- Learned and a pplied Big Data and Hadoop technologies through hands-on classroom activities and case studies
- Prepared large sets of data for further processing using the following technologies: Java, Oracle DB, JDBC, Excel (ODBC), Hadoop, MapReduce, Data Transfer (Sqoop), Pig and Hive
- Gained experience on how to extract, scrub and manipulate real-time and warehouse data using SQL & Java
- Put new knowledge to properly define business problems and design tests that yield valid solutions
- Acquired experience with Project Management (Agile, Scrum) and Software Development Life Cycle (SDLC)
- Cleaned unstructured data for data analysis and Confidential tasks and pipelines
- Demonstrated data storytelling through extraction and visualization of data insights from different databases
- Managed online teams to collaborate and complete data science projects on schedule
- Utilized different visualization programming libraries to tell an immersive data story of murder rates in the Confidential from 2001 to 2018
- Used Python and the Twitter API to get raw data and preprocesse d it for a data science task
- Used Natural Language Processing ML libraries to train a Bayesian model for sentiment analysis with an accuracy of 7 6 % which is better than human performance
- Cleaned data from various sources for further data analysis
- Arranged and participated in group coding activities to facilitate learning and satisfactory project completion
- Used a Deep Neural Network to build an image classification Confidential model from the ground up for my capstone project and achieved a 97.89% accuracy at recognizing traffic signs.
- Applied Reinforcement Learning to train a smart vehicle to navigate a simulated environment in the shortest amount of time whilst observing all traffic laws and not causing any accidents
- Used Decision Trees algorithms to correctly predict the price of houses for a neighborhood in Boston
- Used transferred learning to classify images of dogs and correctly identify the dog breed in the test images
- Logged shipments and package data as well as participated in daily loss prevention data logs
- Delivered customer satisfaction and problem-solved scenarios such as missing or damaged packages by accessing proprietary company databases with sensitive customer information
- Opened and closed the physical store and covered leadership responsibilities