Data Scientist - Software Developer Resume
4.00/5 (Submit Your Rating)
Kansas City, MO
SUMMARY
- More than 5 years experience in programming utilizing Python, Centos 7, PostgreSQL, Pandas, Numpy, Scikit - learn, PostGIS, Django, Javascript, C++, mySQL, R, Machine learning data scientist
PROFESSIONAL EXPERIENCE
Confidential - Kansas City, MO
Data Scientist - Software Developer
Responsibilities:
- Build the interactive and dynamic descriptive statistic, to let farmer directly interact with their agronomic data collected seamlessly, as well as construct their own daily reports and diagnostic alerts
- Expert in python Geometry and PostGIS database - Geospatial monitoring and analysis
- Setup PostgreSQL database in both Linux and Windows servers
- Familiar with Postgres 9.5, pg shard, and Greenplum open source in Machine Learning utilizes pandas lib
- Master in field-geom concept using both Python and PostGIS in aggregating display and statistics
- Design/ modify PostgreSQL database efficiently using geom-POST GIS and Binary to reduce the - data's storage and improve data performance
- Support by providing statistic report and histogram across databases for agronomic data
- Build python from PostGIS built-in functions for web’s team to manipulate field geom input
- Built back end for web's team create-update and import field boundary to the prod's database
- Familiar with building firmware operation system in Python
- Familiar with SQLITE3 and library
- Collect weather data from Gov's API, and partition the table by date to optimize performance
- Do pcapng's fire-wall traffic data log and restoration when it needs
- Build application to compare and restore missing data between different databases
- Build function to help modify, update and insert field to database from web's interface
- Design Django's Models, Views and APIs web's application
- Optimize existing Python Data Analysis functions using loop, inheritance, and encapsulation
- Program automation's script and create backup images to setup and install Linux- Centos 7 and its - Dependencies for Apache Servers for Postgresql database
- Build machine learning framework to do the analysis and prediction
- Apply seamless and accurate (99.5%) prediction (crop-type) concurrently with business operation and other python' scripts
- Build/Design business operate python applications such system management controller to execute and scheduling executing using queue table
- Build/Design clustering GPS point to generate polygon field, matching/filter GPS point from satellite to C.L.U (Common Land Unit ) from 2008 field, zipcode, and US's county area extremely fast using PostGIS and gist index
- Set up the physical server (raid-0, raid-10, virtual disk), mount/ resize disk. Using Clonezilla to recover the operational server for less than 30 minutes
- Install centos 7 and open source software dependencies
- Set up apache HTTPd for the web server
- Set up PostgreSQL database with Post GIS extension and geometry functions
- Maximize database performance using functions, triggers, indexes, partition
Confidential - Kansas City, MO
Python Developer
Responsibilities:
- Assist in the Bioinformatics research with data analysis and programming tasks
- Apply Agile development to document all the pipeline processes as medical laboratory standard requirement
- Work in a Unix/Linux environment and cluster computing
- Run microbial automation analysis using Python Script and Qiime from IlluminaHigSeq data
- Develop, install and run ChIP-seq analysis
- Work with EQTL, GATK pipeline and AlleleSeq (Allele-Specific Expression and Binding in a Network Framework) in dpSNP
- Apply statistics and machine learning algorithms to select the features of significant and accurately predict the outcome result
Confidential
Python Developer
Responsibilities:
- Provide the leading edge technology in IPython - Kernel functions for meta-data analysis, Bio-Statistic, and Machine Learning Data Scientist
- Set up the mySQL server and virtual machine in Linux, Ubuntu to run intensive computational analysis
- Provide the highest accuracy in automation pipeline microbiome analysis using AWS Amazon
- Design visual GUIs interface for interaction and examine the microbiome analysis result as well as finding the logic of disease
- Practice testing through the entire development cycle to produce reliable and maintainable APIs functions
- Build www. Confidential using Django
- Develop and test front-end code that meets accessibility and web browser standards
- Utilize responsive design to support usability in desktop, mobile and tablet environments
- Advocating web development best practices, with a focus on consistency and usability
- Resolve cross-browser rendering issues and bugs
- Maintain and support existing systems and programs
- Provide estimations for front-end development tasks
- Good understanding of end to end business processes
- Reuse available open-source libraries
Confidential
Responsibilities:
- Run analysis report using mySQL and python to generate report in csv and xls format among database servers
- Using Anaconda for data-mining and visual interaction with the matlibplot and pandas libraries
- Using AWS and EC2 node to run computationally intensive microbiome analysis
- Using Nitrous.io to run Django web application using MySQL and sqlite3 as database
- Applying advanced Data Scientist skill and Artificial Intelligence to predict disease state
- Enthusiastic to keep learning and growing, in technical aptitude, business understanding, and personal effectiveness
- Take ownership of work, overcome obstacles and take it through to get the job done