Last change
on this file since 15924 was
15924,
checked in by gkronber, 6 years ago
|
#2886 remove obsolete code in C# program for the evaluation of sentences, switch to NSME as quality measure. Tried plotting functions within clusters in R
|
File size:
941 bytes
|
Line | |
---|
1 | library(largeVis)
|
---|
2 | library(ggplot2)
|
---|
3 | library(dplyr)
|
---|
4 |
|
---|
5 |
|
---|
6 |
|
---|
7 | sentenceFileName <- "D:/heal/documents/trunk/Publications/2018/GPTP/data/evaluations_allSentences_2018-04-13_16-40_TreeSize-7_1d.csv.gz";
|
---|
8 | evalData <- read.csv(sentenceFileName,header = TRUE, sep = ";", dec=",");
|
---|
9 | qualities <- evalData$R2.keijzer4;
|
---|
10 | outputs <- evalData[,6:105];
|
---|
11 |
|
---|
12 | lv <- largeVis(outputs, dim=2, K = 50, n_trees = 50) # TODO scale?
|
---|
13 | clusters <- hdbscan(lv, minPts = 3, K=50);
|
---|
14 |
|
---|
15 |
|
---|
16 |
|
---|
17 | m <- data.frame(x=t(lv$coords)[,1], y=t(lv$coords)[,2], c=clusters$clusters, q=qualities, outputs)
|
---|
18 | # plot mapped points
|
---|
19 | ggplot(data=m, aes(x=x, y=y)) + geom_point(aes(color=c)) + theme(legend.position = "none") ;
|
---|
20 |
|
---|
21 | cluster_n <- dplyr::filter(m, c==5);
|
---|
22 | cluster_evals <- data.frame(x=seq(1,100,1), t(cluster_n[,5:104]))
|
---|
23 | evals_cluster_n <- tidyr::gather(cluster_evals,"f", "fx", 2:ncol(cluster_evals))
|
---|
24 |
|
---|
25 | p <- ggplot(evals_cluster_n, aes(x=x, y=fx,color=f)) + geom_line();
|
---|
26 | p
|
---|
27 |
|
---|
Note: See
TracBrowser
for help on using the repository browser.