Skills
● Functional programming: First language is R, intermediate in Python
● Applied data science: Assessing whether algorithms and methods fit the problem and then calibrating and chaining them together for a certain goal rather than inventing the wheel
● Practical experience in applied statistics, exploratory data analysis, network analysis, classification with machine learning techniques, natural language processing (especially NER), data mining, record linkage
● Web scraping and text mining: automated retrieval and parsing of structured and unstructured data
● Implementation of software packages for data analysis, ad hoc scripts, pipelines, automated reports (including generation of natural language text)
● Development of Shiny webapps
● Building data pipelines: extracting, transforming and loading data from all common data formats (flatfiles, json, databases, APIs, ...)
● Professional preparation and communication of results in words and graphics to internal stakeholders and/or the general public
● Creating static and interactive data visualizations with dierent tools, e.g. Datawrapper, ggplot2 or JavaScript libraries, following best practice principles
● Creation and maintenance of open source software packages, such as generativeart (>600 stars on Github) or destatiscleanr
Projekthistorie
Remove NA - Prototype Fund Projekt: https://github.com/cutterkom/remove-na-lgbtiq-queer-knowledge-graph
- Entity Linking
- Linked Open Data Modeling
- Shiny Apps
- Erstellen einer Datenpipeline
- Scoring- und Ratingsystem
- Qualitätssicherung