Calculates and plots a heatmap of the "confusion matrix" M for the given subset of pages. M[i,j] is the probability that a 1-NN classifier classifies a random query from class i as belonging to j, given our dataset.
1 2 3 4 | drawHeatmap(filesPath, webpages = "all", showPercentages = F, P = 5,
windowType = "sakoechiba", windowSize = 100, maxLength = 1000,
sampFun = "sum", stepPattern = "symmetric1", pathOut,
matrixFileName = "confusionMatrix", heatmapFileName = "heatmap")
|
filesPath |
Path containing the crossDistance matrices. |
webpages |
List of the pages you want to restrict the classifier to. |
showPercentages |
Logical. TRUE displays the value of M[i,j] in the corresponding cell. Defaults to FALSE. |
P |
Timeseries averaging parameter |
pathOut |
Path to save the confusion matrix and heatmap image. |
matrixFileName |
R object file containing the confusion matrix. |
heatmapFileName |
pdf file to save the heatmap to. |
weight |
Either 'none' (default) for simple majority vote, 'inverse' for 1/distance weighting. |
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.