Rattle is Free (as in Libre) Open Source Software and the source code is available from the Bitbucket repository. We give you the freedom to review the code, use it for whatever purpose you like, and to extend it however you like, without restriction, except that if you then distribute your changes you also need to distribute your source code too. Rattle - the R Analytical Tool To Learn Easily - is a popular GUI for data mining using R. It presents statistical and visual summaries of data, transforms data that can be readily modelled, builds both unsupervised and supervised models from the data, presents the performance of models graphically, and scores new datasets. One of the most important features (according to me) is that all of your interactions through the graphical user interface are captured as an R script that can be readily executed in R independently of the Rattle interface. Rattle clocks between 10,000 and 20,000 installations per month from the RStudio CRAN node (one of over 100 nodes). Rattle has been downloaded several million times overall.

1. INTRODUCTION TO R AND RATTLE
1IAUSHIRAZ1/14/2017

2. What is the R
Statistical Programming Language
used among statisticians and data miners for developing statistical software and data analysis.
Free and Open Source
Written in C, Fortran and R
Statistical features
Linear and nonlinear modeling
Statistical tests
Classification, Clustering
Can manipulate R Objects with C, C++, Java, .NET or Python code.
2IAUSHIRAZ1/14/2017

3. Source Example
> x <- c(1,2,3,4,5,6) # Create ordered collection (vector)
> y <- x^2 # Square the elements of x
> print(y) # print (vector) y
[1] 1 4 9 16 25 36
> mean(y) # Calculate average (arithmetic mean) of (vector) y; result is scalar
[1] 15.16667
> var(y) # Calculate sample variance
[1] 178.9667
> lm_1 <- lm(y ~ x) # Fit a linear regression model "y = f(x)" or "y = B0 + (B1 * x)"
# store the results as lm_1
> print(lm_1) # Print the model from the (linear model object) lm_1
Call:
lm(formula = y ~ x)
Coefficients:
(Intercept) x
-9.333 7.000
> summary(lm_1) # Compute and print statistics for the fit
# of the (linear model object) lm_1
Call:
lm(formula = y ~ x)
Residuals:
1 2 3 4 5 6
3.3333 -0.6667 -2.6667 -2.6667 -0.6667 3.3333
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -9.3333 2.8441 -3.282 0.030453 *
x 7.0000 0.7303 9.585 0.000662 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 3.055 on 4 degrees of freedom
Multiple R-squared: 0.9583, Adjusted R-squared: 0.9478
F-statistic: 91.88 on 1 and 4 DF, p-value: 0.000662
> par(mfrow=c(2, 2)) # Request 2x2 plot layout
> plot(lm_1) # Diagnostic plot of regression model
3IAUSHIRAZ1/14/2017

4. Graphical front-ends
Architect – cross-platform open source IDE based on Eclipse and StatET
DataJoy – Online R Editor focused on beginners to data science and collaboration.
Deducer – GUI for menu-driven data analysis (similar to SPSS/JMP/Minitab).
Java GUI for R – cross-platform stand-alone R terminal and editor based on Java (also known as JGR).
Number Analytics - GUI for R based business analytics (similar to SPSS) working on the cloud.
Rattle GUI – cross-platform GUI based on RGtk2 and specifically designed for data mining.
R Commander – cross-platform menu-driven GUI based on tcltk (several plug-ins to Rcmdr are also
available).
Revolution R Productivity Environment (RPE) – Revolution Analytics-provided Visual Studio-based IDE,
and has plans for web based point and click interface.
RGUI – comes with the pre-compiled version of R for Microsoft Windows.
RKWard – extensible GUI and IDE for R.
RStudio – cross-platform open source IDE (which can also be run on a remote Linux server).
4IAUSHIRAZ1/14/2017

5. What is the Rattle
R Graphical User Interface Package
Offered by Graham Williams in Togaware Pty Ltd.
Free and Open Source
Represents Statistical and Visual Summaries of data
Tabs :
Load Data
Data Exploration
Model
Evaluation
Test
…
5IAUSHIRAZ1/14/2017

6. Rattle Installation Process
Download and Installing R
https://r-project.org
About 60MB
Download the Rattle Package
About 300MB
Follow Instructions :
 install.packages("rattle", dependencies=c("Depends", "Suggests"))
 Library(rattle)
 Rattle()
6IAUSHIRAZ1/14/2017

7. Load Data
Dataset Types :
CSV File (CSV, TXT, EXCELL)
ARFF (CSV File which adds type information)
ODBC (MySQL, SqlLITE, SQL Server, …)
 Set Connections in : /etc/odbcinst.ini & /etc/odbc.ini
R Dataset (Existing Datasets in Current Solution)
R Data File
Library (Pre Existing Datasets)
Corpus ( Collection of Documents)
Script (Scripts for Generating Datasets)
1/14/2017 IAUSHIRAZ 7

8. Load Data
Variable Types :
Input (Most Variables as Input)
 Predict the Target Variables
Target (Influenced by the Input Variables)
 Known as the Output
 Prefix : TARGET_
Risk (Measure of the size of the Targets)
 Prefix : RISK_
Identifier (any Numeric Variable that has a Unique Value – Not Normally used in modeling)
 Such as : ID, Date
 Prefix : ID_
Ignore (Ignore from Modeling)
 Prefix : IGNORE_
Weight (Weighted by R Formula)
1/14/2017 IAUSHIRAZ 8

9. Transform
Rescale
Normalize
 Re Center
 Scale [0-1]
 Median/Mad
 Natural Log / Log 10
 Matrix
Order
 Rank
 Interval
 Number of Group
1/14/2017 IAUSHIRAZ 9

10. Transform
Impute (missing values)
Zero
Mean
Median
Mode
Constant
Recode
Quantiles
K-Means
Equal with
Indicator variable / Join Categories
As Categorical / As Numeric
1/14/2017 IAUSHIRAZ 10

11. Transform
Cleanup
Delete Ignored
Delete Selected
Delete Missing
Delete Observations with Missing
1/14/2017 IAUSHIRAZ 11

12. Exploration
Summary
Summary
 Min, Max, Mean, Quartiles Values.
Describe
 Missing, Unique, Sum, Mean, Lowest, Highest Values.
Basics (For Numeric Value)
 Measures of Numeric Data (Missing, Min, Max, Quartiles, Mean, Sum, Skewness, Kurtosis)
Kurtosis (For Numeric Value)
 A larger value indicates a sharper peak.
 A lower value indicates a smoother peak.
Skewness (For Numeric Value)
 A positive skew indicates that the tail to the right is longer.
 A negative skew that the tail to the left is longer.
1/14/2017 IAUSHIRAZ 12

13. Exploration
Summary
Show Missing
 Each row corresponds to a pattern of missing values.
 Perhaps coming to an understanding of why the data is missing.
 Rows and Columns are sorted in ascending order of missing data.
1/14/2017 IAUSHIRAZ 13

14. Exploration
Distributions (review the distributions of each variable in dataset)
Annotate (include numeric values in plots)
Group by
Numeric Outputs :
 Box Plot
 Histogram
 Cumulative
 Benford
 For any number of continuous variables
 Pairs
Categorical Outputs :
 Bar Plot
 Dot Plot
 Mosaic
 Pairs
1/14/2017 IAUSHIRAZ 14

15. Exploration
Correlations (Rattle only computes correlations between numeric variables at this time)
Ordered
 Order by strength of correlations
Explore Missing
 Correlation between missing values
Hierarchical
 Pearson
 Kendall
 Spearman
Principal Components
SVD
 For only Numeric Variables
Eigen
1/14/2017 IAUSHIRAZ 15

16. Model
Tree
Traditional
 Trade off between performance and simplicity of explanation
Conditional
Forest (many decision trees using random subsets of data and variables)
Number of Trees
Number of Variables
Impute (set median numeric value for missing values)
Sample Size (for balancing classes)
Importance (variable importance)
Rules (collection of random forest rules)
ROC (ROC Curve)
Errors
1/14/2017 IAUSHIRAZ 16

17. Model
SVM
Start with two parallel vector
Linear (linear regression)
For continues values
All
1/14/2017 IAUSHIRAZ 17

18. Cluster
K-Means
Set First K
EwKm
K-Means with entropy weighting
Hierarchical
Not needed to set first Cluster Number
BiCluster
Suitable subsets of both the variables and the observations
1/14/2017 IAUSHIRAZ 18