DATA MINING Desktop Survival Guide by Graham Williams
Desktop Survival Project Home List of Figures List of Tables Data Mining Data Mining Data Mining with Rattle Introduction Data Transform Explore A Model Building Framework Unsupervised Modelling Two Class Models Multi Class Models Regression Models Text Mining Evaluation and Deployment Moving into R Troubleshooting R for the Data Miner R Data Graphics in R Understanding Data Preparing Data Building Models Evaluating Models Algorithms Apriori Bagging Bayes Classifier Boosting Cluster Analysis Conditional Trees Hierarchical Clustering K-Means K-Nearest Neighbours Linear Models Logistic Regression Neural Networks Support Vector Machines Text Mining 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 Appendicies Glossary Bibliography Index

Tips and Tricks

SAS Enterprise Miner is a large product (including the SAS statistical package), and sometimes cumbersome and quaintly old fashioned. It is being migrated into a modern world, slowly, and its functionality is improving regularly. Below we highlight some issues and tricks that may be helpful.

• Log Transform of a dataset seems somewhat of a trap. A log transform essentially transforms the data items $d$ with $ln(1+(d-d_{min}\over d_{max}-d_{min}$. The $d_{min}$ and $d_{max}$ are determined from the current dataset. However, if you log transform your training dataset, and separately log transform your test dataset, then the transforms will end up being different! Hence, the model you build will not be applicable to any data unless it is transformed with the same values of $d_{min}$ and $d_{max}$! You may want to avoid such transforms.

Support further development through the purchase of the PDF version of the book.
Brought to you by Togaware.