Juan M. Banda Email and Phone Number

Data Ninja with extensive structured and unstructured big data expertise.As a scientist I work with large volumes of image data extracting and transforming computer vision image features into large content-based image retrieval systems for NASA Solar Dynamics Observatory mission. Not only limited to image data, I am well versed in extracting terms and clinical concepts from millions of unstructured Electronic Health Records, to build predictive models (electronic phenotyping) and mine for potential multi-drug interactionsAs an engineer at heart, I am responsible from everything from producing ETL scripts for migration of research databases and producing production-quality code from research prototypes. I have built web front-ends for image retrieval research systems and API’s for retrievalEvery day I find my self writing SQL code, bash scripts, Python wrappers, R code as well as designing databases to support other researchers. I am proficient curating datasets that combine multiple data sources and data formats for research usage. Being linked data, flat text files, CSV files, database tables, etc. on a daily basis I whip them into shape to answer research questionsI participate in all stages from data acquisition, cleaning, loading and modeling as well as distribution and accessibility via API’s or linked datasets. With my skills ranging from production level code in SQL, R, Matlab, Python, Php, Java, Visual Basic to mid-level proficiency of languages like C/C++, Perl, Pascal, FoxPro, Cobol, etc. I provide great value to an organization by helping with legacy code migrations, research algorithm high-performance implementations, to productization of research prototypes. I am very proficient using research tools like R and Matlab, scientific libraries like Numpy, Scipy, Data Mining packages like Weka and Computer Vision libraries like openCV. I have mid-level experience using tools like Lucene and Elastic Search as well as Hadoop and MapReduce.