Introduction to Outlier Detection Methods - Wolfram Livecoding Session скачать в хорошем качестве

Introduction to Outlier Detection Methods - Wolfram Livecoding Session

Andreas Lauschke, a senior mathematical programmer, live-demos key Wolfram Language features useful in data science. In the sixth session, Andreas introduces some methods for outlier detection. This is part 1 of 2. A close look will be taken at box plots as well as caveats (i.e. when not to use box plots). Datasets used include atmospheric, health and the 2016 US presidential election. The k-nearest neighbor concept, which plays a very important role in artificial intelligence and machine learning, is introduced. Notebook materials are available at: https://www.notebookarchive.org/id/20... You can directly interact with Andreas through Wolfram Community: https://wolfr.am/GDrFGeWF More information about Wolfram’s approach to data science can be found at: https://www.wolfram.com/featureset/da... Watch the full series of data science videos by Andreas Lauschke: Session #1: https://wolfr.am/HlmE40MT Session #2: https://wolfr.am/HlmMydgB Session #3: https://wolfr.am/HlmMzmFX Session #4: https://wolfr.am/HlmMAxJT Session #5: https://wolfr.am/HlmMBJb8