0% found this document useful (0 votes)
3 views3 pages

Data Science With R Workflow

Uploaded by

edersondacosta
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
3 views3 pages

Data Science With R Workflow

Uploaded by

edersondacosta
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Data Science with R

Workflow
Learn R following the tidyverse & tidymodels workflow
for business analysis in the R For Business Analysis (DS4B 101-R)
course through Business Science University.

Click the links for


Documentation

ggplot2 (CS)
plotly (CS)

dplyr (CS)
Visualize
stringr (CS)
lubridate (CS)
forcats (CS)
Base R (CS)
Transform purrr (CS)
Import Tidy (iteration) Communicate

RMarkdown (CS)
readr (CS)
tibble (CS) Shiny (CS)
readxl / writexl Model
tidyr (CS) Plumber APIs (CS)
Databases / SQL
rvest
tidymodels
recipes tune
RStudio IDE (CS) fs (file system) reticulate (CS) rsample yardstick
parsnip dials
CS = Cheat Sheet

Important Resources
R For Data Science Book: [Link]
Rmarkdown: Book and Cookbook
More Cheatsheets: [Link]
tidyverse packages: [Link]
Connecting to databases: [Link]
Reproducible Environments: [Link]

Business Science University


Learn the Tidyverse & Tidymodels [Link]

version: 4.0
Data Science with
Web Applications & the "Shinyverse"

Advanced
Components
Start Concepts Testing Publish
& Themes
(Optional)

Shiny (CS) Widgets crosstalk profvis [Link]


Flexdashboard shinyWidgets shinyrouter shinytest Shiny Server
htmlWidgets Async (promises) shinyloadtest Connect (Enterprise)
shinyjs Golem (CS)
bslib
thematic

Flexdashboard Apps Shiny Apps


Flexdashboard is an RMarkdown-based dashboard tool that can be Shiny is an R-Package that enables web app development from R.
used to integrate shiny components at runtime. Development is fast Contains R functions for common HTML structures, UI Controls
and efficient, but layouts are not as open to modification as building (Components/Widgets), and web framework tools. The framework if
an app using Shiny. highly flexible, but users require more knowledge of HTML & CSS.

Shiny Themes & Dashboards Web Frameworks & Tools


Bootstrap 3
Flexdashboard Shiny Gallery Bootstrap 4
Gallery Bootstrap Bootswatch
shinythemes & Themes
Themes shinydashboard bslib
Layouts shinydashboardPlus thematic

Semantic Bootstrap 4 Font Awesome


Fonts & Icons Google Fonts
[Link]
[Link] bs4Dash

Shiny App - AWS Multi-User App Argon ShinyMobile (CS) Chrome Browser Chrome DevTools
Built in Expert Apps Course (Demo Our App Gallery)
argonR
argonDash
Start Learning Today with 5-Course R-Track Bundle!

Business Science University


Learn Shiny Apps, AWS, & Docker [Link]
Data Science with Text Analysis & NLP Machine Learning
Special Topics AutoML: H2O (CS)
Text Mining with R (Book): tidytext
NLP: textrecipes, Book (SMLTAR) ML (Tidymodels): [Link]
parsnip - ML
recipes - Feature Engineering
Time Series Analysis tune - Hyperparameter Tuning
rsample - Resampling
Time Series Data Wrangling: timetk yardstick - Accuracy Metrics
Time Series Visualization: timetk ML (pre-Tidymodels): caret (CS)
Feature Engineering: timetk Network Analysis MLR: mlr & mlr3 (CS)
Convert between classes: timetk & tsbox MLVerse: mlverse
Generating Future Series: timetk Network Data Transformations (Tidy): tidygraph

Forecasting
Network Data Transformations: igraph Deep Learning
Prophet, ARIMA, Boost, ML: modeltime Network Viz R Interface to TensorFlow
Keras (CS), TF Estimators, TensorFlow (Core)
Ensembles: [Link] Torch for R
Resampling & Backtesting: [Link] Static:
Deep Learning: [Link] ggraph - Graph plotting utilities for ggplot2
H2O AutoML: modeltime.h2o Interactive (JavaScript):
networkD3 - D3 Networks in R
Speed & Scale
Anomaly Detection plotly (CS) - [Link] (network graphs) in R
Faster than dplyr & pandas: [Link] (CS)
Identify anomalies: anomalize, timetk Dplyr SQL & DT backends: dtplyr, dbplyr
Parallel Processing w/ purrr: furrr
Larger than RAM: sparklyr (CS), Disk Frame
Geospatial Analysis
Exploratory (EDA)
DataExplorer, skimr, correlationfunnel, janitor
Geocoding (getting lat/long, bboxes, & sf's):
ggmap - Google API (requires key)
Interoperability
osmdata - OpenStreet Overpass API Python: reticulate (CS) Java: rJava
tmaptools - OpenStreet Nominatum API C++: Rcpp D3: r2d3
Simple Features (sf objects): sf (CS) (tidy)
Financial Analysis Spatial Objects (sp objects): sp (non-tidy, pre-sf)

Getting financial data: tidyquant & quantmod Miscellaneous Tools


Quantitative Analysis: tidyquant & xts/TTR
Portfolio Analysis: tidyquant & PerformanceAnalytics Geospatial Viz Production:
plumber, targets, renv
Static: Building R Packages: R packages Book
Financial Viz ggmap - Google API (requires key) devtools (CS), usethis, pkgdown
Static: osmplotr - Impressive Maps via OSM Advanced Concepts (Advanced R Book)
tidyquant - Financial ggplot2 geoms tmap - Thematic Maps rlang & Tidy Evaluation (CS)
cartography (CS) - Thematic Maps Making Blogs & Books:
Interactive:
highcharter - [Link] in R Interactive (JavaScript): blogdown, bookdown
dygraphs - xts plotting leaflet (CS) - [Link] in R Posting Code (GitHub, Stack Overflow):
plotly (CS) - [Link] (financial) in R plotly (CS) - [Link] (maps) in R reprex

Business Science University


Learn High-Performance Time Series Forecasting [Link]

You might also like