Data Mining: Practical Machine Learning Tools and Techniques, Second Edition

sized random samples. But we do not choose random samples; we choose those instances which, according to the data mining tool, a ...

of positives included in the sample on the vertical axis, expressed as a percent- age of the total number of positives, against ...

smooth curve like that in Figure 5.2—although in reality such curves do not generally look quite so smooth. This is just one way ...

should choose method A, which gives a false positive rate of around 5%, rather than method B, which gives more than 20% false po ...

refer to recall for the top ten documents, that is, 8/40 =5%; while “precision at 10” would be 8/10 =80%. Information retrieval ...

Different terms are used in different domains. Medics, for example, talk about the sensitivityand specificityof diagnostic tests ...

an expected error of one if the dataset contains no +instances and zero if all its instances are +; the other always predicts -, ...

So far we have not taken costs into account, or rather we have used the default cost matrix in which all errors cost the same. C ...

cost values at the left and right sides of the graph are fpand fn,just as they are for the error curve, so you can draw the cost ...

holdout method, and cross-validation—apply equally well to numeric predic- tion. But the basic quality measure offered by the er ...

relation, to -1 when the results are perfectly correlated negatively. Of course, negative values should not occur for reasonable ...

discrepancies much more heavily than small ones, whereas the absolute error measures do not. Taking the square root (root mean-s ...

it is capable of generating new facts about the domain—in other words, the class of unseen instances. Theory is a rather grandio ...

be transmitted through a noiseless channel. Any similarity that is detected among them can be exploited to give a more compact c ...

Taking negative logarithms, Maximizing the probability is the same as minimizing its negative logarithm. Now (as we saw in Secti ...

We end this section as we began, on a philosophical note. It is important to appreciate that Occam’s razor, the preference of si ...

it belongs to (in log 2 kbits) followed by its attribute values with respect to the cluster center—perhaps as the numeric differ ...

tion theory is covered by Egan (1975); this work has been extended for visual- izing and analyzing the behavior of diagnostic sy ...

...

We have seen the basic ideas of several machine learning methods and studied in detail how to assess their performance on practi ...