DATA MINING Desktop Survival Guide by Graham Williams
Desktop Survival Project Home Data Mining Introduction Getting Started Data Loading Data Exploring Data Interactive Graphics Test Descriptive Data Mining Predictive Data Mining Evaluation and Deployment Data Cleaning Handling Missing Data Transforming Data Data Reduction Deployment Troubleshooting Issues Moving into R Beyond Rattle R Getting Help Data Graphics in R Understanding Data Preparing Data Descriptive and Predictive Analytics Issues Evaluating Models Reporting Topics in Data Mining Fraud Analysis Archetype Analysis Text Mining Survival Analysis Algorithms Bagging Bayes Classifier Cluster Analysis Conditional Trees Hierarchical Clustering K-Nearest Neighbours Linear Models Support Vector Machines Open Products AlphaMiner Borgelt Data Mining Suite KNime R Rattle Weka Closed Products C4.5 Clementine Equbits Foresight GhostMiner InductionEngine ODM Enterprise Miner Statistica Data Miner TreeNet Virtual Predict Appendices Installing Rattle Bibliography Index Preface Goals Organisation Features Audience Typographical Conventions A Note on Languages Currency Acknowledgements

Building a Model

Todo: Get a two dimensional dataset, like Hastie, and build models over that.

Let's have a look at the simplest of problems. Suppose we want to model one variable (e.g., a person's height) in terms of another variable (e.g., a person's age).

We can create a collection of people's ages and heights, using some totally random data:

> set.seed(123)			# To ensure repeatability.
> ages <- runif(10, 1, 20)	# Random ages between 1 and 20
> heights <- 30 + rnorm(10, 1, as.integer(ages)) + ages*5
> plot(ages, heights)

We can now build a model (in fact, a linear interpolation) that approximates this data using R's approxfun:

> my.model <- approxfun(ages, heights)
> my.model(15)
[1] 85.38172
> plot(my.model, add=TRUE, col=2, ylim=c(20,200), xlim=c(1,20))

The resulting plot is show in Figure 25.1. We can see it is only an approximate model and indeed, not a very good model. The data is pretty deficient, and we also know that generally height does not decrease for any age group in this range. It illustrates the modelling task though.

Todo: Convert this to R code to generate better quality plot.

Figure 25.1: A approximate model of random data.

> my.spline <- splinefun(ages, heights)

Support further development through the purchase of the PDF version of the book.
The PDF version is a formatted comprehensive draft book (with over 800 pages).
Brought to you by Togaware. This page generated: Saturday, 16 January 2010