satRday Johannesburg 2019
| title | author | length |
|---|---|---|
| Panel Discussion : Ethics in Data Science | Robert Bennetto, Peter Kamerman, Retha Langa, Vebashini Naidoo, Danielle Navarro | 31m |
Panelists cite concrete failures and edge cases: a word‑association corpus Small World of Words with ~90,000 participants and ~1,000,000 responses carries… | ||
| Interpreting Machine Learning Models: Why and How! | Omayma Said | 34m |
Argues that model interpretability matters for ethics, debugging and trust, and demonstrates R tools: lime and iml to explain random forests on Iris and a… | ||
| Exploring the South African School Directory with R | Megan Beckett | 14m |
Takes the Department of Basic Education’s provincial Excel master lists (about 24,000 schools), cleans and geocodes them with R using tmap’s… | ||
| Understanding the state of R in South Africa | Francois Van Heerden | 20m |
Downloads from CRAN are parsed from 1,402 log files (6 GB compressed) into a time series of 5.7 million observations (2.8M in 2018), decomposed with the stats… | ||
| Extending Power BI with R | Michael Johnson | 21m |
Power BI now runs R by enabling an R install in Options, using Get Data -> R script to expose data frames that load into Power BI's in-memory columnstore, and… | ||
| How the cloud changed the way I do analytics and research | Hanjo Odendaal | 20m |
Uses h2o, AWS spot instances, and future + reticulate to scale experiments: spins up five cloud workers from a 2‑core laptop, runs gradient boosting and random… | ||
| Become an animaniac with gganimate | Peter Kamerman | 06m |
Downloads Lancet DALY CSVs, imports into R and builds a ggplot line+point chart, then turns it into an animated GIF using gganimate with transition_reveal and… | ||
| What I learned from running Shiny in production | Luis de Sousa | 20m |
Experience running Shiny in production distilled into concrete actions and limits, not platitudes: use shinytest for UI regression checks, use shinyloadtest to… | ||
| 3 x packages with single-line calls to boost your productivity | Oscar Baruffa | 05m |
Three one-line helpers: beeper with 1–11 built-in sounds plays a notification at the end of long-running scripts; dataExplorer::create_report HTML report… | ||
| Why tidy data matters | Gerard Walsh | 05m |
Shows cleaning WHO TB data from 1995–2008 into a tidy shape using tidyr::gather and tidyr::separate, then aggregates with dplyr::group_by and summarize and… | ||
| Geo-spatial data visualization in R | Natasha Sing | 05m |
Uses R with a Google API key (Static Maps API + Geocoding API), ggmap to geocode locations and pull static basemaps, and ggplot2 to build custom state polygons… | ||
| The Dota 2 Landscape in R | Vishalin Pillay | 07m |
Downloads a curated CSV of pro matches from DAP Toto, queries the match API to pull JSON, and uses R JSON flattening and list unnesting to tidy nested match… | ||
| Petabytes of data: How to use R at scale | Jeff Fletcher | 16m |
Processes petabytes by moving work into a Spark cluster using HDFS/YARN, not by loading data into a laptop R session; a 200 terabyte CSV can be processed… | ||
| A Fiery approach to R web services | Quintin de Kok | 15m |
Claims a repeatable path from R model to realtime endpoint using ProjectTemplate, Fiery and Docker image. Shows a minimal pipeline: project skeleton auto-loads… | ||
| Zindi Competition Platform | Ekow Duker | 06m |
Zindi is a Pan‑African data science competition platform that posts real problems and datasets and crowdsources solutions. It grows from a standing start to… | ||
| Detecting marine heatwaves (MHWs) by using R-programming | Amieroh Abrahams | 06m |
Demonstrates an R workflow that detects marine heatwaves from satellite sea surface temperature, recommending 30 years of SST as the baseline and computing… | ||
| An antidote to complexity | Eckhard Briedenhann, Robert Bennetto | 19m |
Compares S3, S4 and reference classes and shows a concrete DAG implementation: a class-based DAG object that stores nodes in its own environment, plots… | ||
| YOLO in R | Vongani Maluleke | 04m |
Shows how to run YOLO from R using a GitHub package installed via devtools, instantiate a model with four arguments (task, model, weights, labels) and call an… | ||
| Three indispensable REGEX hacks | Marinus Louw | 04m |
Three practical regex techniques and a working pattern for the example file set are given: use ^ and $ as anchors to force full-string matches, use grouping… | ||
| How to write a report using R Markdown | Bianca Peterson | 10m |
Shows how to create reproducible reports with R Markdown using a YAML header for title/author/date and choosing HTML recommended output (convertible with… | ||
| Deploying a Plumber API with Docker | Andrew Collier | 07m |
Plumber makes it possible to easily transform your R functions into an API. Developing and testing the API locally is simple, but deploying it can be more of a… | ||
| EXCELsioR! | Cesaire Tobias | 16m |
Argues spreadsheets are ubiquitous data sources and shows a workflow that extracts messy balance sheets from 56 Excel files into a single tidy table using R… | ||
| How to Get Ahead in Advertising | Helge Reikerås | 21m |
Explains concrete multi-channel attribution methods implemented in R and released as a channel attribution R package, comparing Markov chain models (using a… | ||
| nothing matches | ||