Knowledge Discovery and Data Mining Research Group 
KDDRG

Miscellaneous Notes on R 

These notes are based on several online R resources

• Useful R Resources
• Some Datasets
• Loading Data onto R
• R's Data Frame structure
• Data Preprocessing in R
• R Weka Interface

Useful R Resources

• R's online Manual "An Introduction to R"
• The R Manuals.
• "R Tutorial: An R Introduction to Statistics"
• "Try R"
• CS539inR Wiki: Students in CS539 have contributed to this wiki.

Data Files

• contact-lenses-with-attrib-names.csv
• contact-lenses-no-attrib-names.csv
• diabetes_numeric_only.csv

> getwd()

Different ways to upload data onto R:

Below, some examples are included. Use "help " on the Command Window to learn more about each .

• Using built-in Datasets: See a description of the

  Use:
  
  > data()
  
  to list the datasets available.  Take for example the iris dataset. You can look at this dataset with the command:
  
  
  > iris
  
      Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
  1            5.1         3.5          1.4         0.2     setosa
  2            4.9         3.0          1.4         0.2     setosa
  3            4.7         3.2          1.3         0.2     setosa
  4            4.6         3.1          1.5         0.2     setosa
  5            5.0         3.6          1.4         0.2     setosa
  6            5.4         3.9          1.7         0.4     setosa
  ...
  149          6.2         3.4          5.4         2.3  virginica
  150          5.9         3.0          5.1         1.8  virginica
  
  One can also use the command data(...) to upload a dataset that is not already loaded in the environment. For example, if "iris" wasn't already loaded, it could be loaded with: 
  
  > data(iris)
  

  • See also the "BJSales" dataset, which is a dataset of time series.
  • To load datasets from other R packages see: Loading Data from other R packages".

• Reading Datasets from Files: See the "Reading data from files" section of the R manual.

  For example, to upload the

• contact-lenses-with-attrib-names.csv working directory given by:

   getwd()

  and then use:

   
  > clenses = read.csv("contact-lenses-with-attrib-names.csv")
  

  you can then see the content of the dataset using:

  > clenses
  

  If the dataset is not comma separated, but space-separated, use

  > clenses = read.table("contact-lenses-with-attrib-names.txt")
  

  instead.
• See other data import functions in the R Tutorial.

Using the DATA FRAME structure in R:

• See the "R Tutorial: An R Introduction to Statistics" section on Data Frames.
• See the "An Introduction to R" manual entry on Data Frames.

Data Preprocessing in R:

• Data sampling
  • Package 'sampling'
• Attribute discretization
  • Package 'discretization' (supervized)
• Missing values
  • Chapter on Missing data imputation of the "Data Analysis Using Regression and Multilevel/Hierarchical Models" by Andrew Gelman and Jennifer Hill Available Online.
  • R packages:
    • Package 'MissingDataGUI'
    • Package 'mi'
• Dimensionality Reduction:
  • Attribute/feature selection:
    Correlation based Feature Selection (CFS), ReliefF, ...
  • Feature Extraction:
    Singular Value Decomposition (SVD), Principal Components Analysis (PCA), Fourier transform, ...

• See: http://cran.r-project.org/web/packages/RWeka/index.html
• Search online for more resources