1

我希望有人能帮助我。我一直想知道我的数据是如何聚集的，为此我一直在使用 R 中的 k-means 和肘部方法，正如 R-bloggers 博客中所建议的那样。

这是我的数据的示例（datanet）。我的聚类分析基于前三列 ACTIVITY X、ACTIVITY Y 和 ACTIVITY Z：

   ACTIVITY_X ACTIVITY_Y ACTIVITY_Z   Event
1:         40         47         62 Vigilance
2:         60         74         95 Head-up
3:         62         63         88 Head-up
4:         60         56         82 Head-up
5:         66         61         90 Head-up
6:         60         53         80 Head-up

我已经获得了between_SS/total_SS89.0 % 的分数k=4，所以我非常有信心我的数据被分为 4 个集群。

现在，我想知道我的数据是否基于上面数据示例的事件列上的不同标签进行了 4 聚类。

我使用tsclust()了一种fuzzy-type 的聚类来查看我的数据是如何聚类的。这是我实现代码的方式：

library(dtwclust)
trainset1 <- datanet[, !"Event"]
train = as.matrix(trainset1, byrow = T, ncol=3)
head(train)
train_clust<- tsclust(train, k = 4L, type = "fuzzy")
plot(train_clust@cluster)
plot(train_clust)

最后一个命令plot(train_clust)允许我找到不同集群的各自质心： 在此处输入图像描述

plot(train_clust@cluster)显示每个数据点属于哪个集群： 在此处输入图像描述

但是，有没有办法知道每个数据点代表的事件列中的哪个标签？如前所述，我将我的数据tsclust()作为train矩阵输入，仅包括我的数据的前三列，如上所示（因为它们是具有值的列）。

如何实现第三列"Event"，以便每个数据点都有一个关联的标签（Head-up、Vigilance 等）？

我的目标是最终得到一个类似于这样的集群图： 在此处输入图像描述

希望这个问题很有趣，因为我对 R 还很陌生。感谢任何输入！

PS 如评论中所问：

> dput(datanet)
structure(list(ACTIVITY_X = c(40L, 60L, 62L, 60L, 66L, 60L, 57L, 
54L, 52L, 93L, 80L, 14L, 52L, 61L, 51L, 40L, 20L, 21L, 5L, 53L, 
48L, 73L, 73L, 21L, 29L, 63L, 59L, 57L, 51L, 53L, 67L, 72L, 74L, 
70L, 60L, 74L, 85L, 77L, 68L, 58L, 80L, 34L, 45L, 34L, 60L, 75L, 
62L, 66L, 51L, 53L, 48L, 62L, 62L, 57L, 5L, 1L, 12L, 23L, 5L, 
4L, 0L, 13L, 45L, 44L, 31L, 68L, 88L, 43L, 70L, 18L, 83L, 71L, 
67L, 75L, 74L, 49L, 90L, 44L, 64L, 57L, 22L, 29L, 52L, 37L, 32L, 
120L, 45L, 22L, 54L, 30L, 9L, 27L, 14L, 3L, 29L, 12L, 10L, 61L, 
60L, 29L, 15L, 7L, 6L, 0L, 2L, 0L, 4L, 1L, 7L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 1L, 15L, 23L, 49L, 46L, 8L, 31L, 45L, 60L, 
31L, 37L, 61L, 52L, 51L, 38L, 86L, 60L, 41L, 43L, 40L, 42L, 42L, 
48L, 64L, 71L, 59L, 0L, 11L, 27L, 12L, 3L, 0L, 0L, 8L, 0L, 21L, 
6L, 2L, 7L, 4L, 3L, 3L, 46L, 46L, 59L, 53L, 37L, 44L, 39L, 49L, 
37L, 47L, 17L, 36L, 32L, 33L, 26L, 12L, 8L, 25L, 31L, 35L, 27L, 
27L, 24L, 17L, 35L, 39L, 28L, 54L, 5L, 0L, 0L, 0L, 0L, 0L, 17L, 
22L, 25L, 12L, 0L, 5L, 41L, 51L, 66L, 39L, 32L, 53L, 43L, 40L, 
44L, 45L, 48L, 51L, 41L, 45L, 39L, 46L, 59L, 31L, 5L, 24L, 18L, 
5L, 15L, 13L, 0L, 12L, 26L, 0L), ACTIVITY_Y = c(47L, 74L, 63L, 
56L, 61L, 53L, 40L, 41L, 49L, 32L, 54L, 13L, 39L, 99L, 130L, 
38L, 14L, 6L, 5L, 94L, 96L, 38L, 43L, 29L, 47L, 66L, 47L, 38L, 
31L, 36L, 35L, 38L, 72L, 54L, 44L, 45L, 51L, 80L, 48L, 39L, 85L, 
42L, 39L, 37L, 75L, 36L, 45L, 32L, 35L, 41L, 26L, 99L, 163L, 
124L, 0L, 0L, 24L, 37L, 0L, 6L, 0L, 29L, 29L, 26L, 27L, 54L, 
147L, 82L, 98L, 12L, 83L, 97L, 104L, 128L, 81L, 42L, 102L, 60L, 
79L, 58L, 15L, 14L, 75L, 75L, 40L, 130L, 40L, 13L, 54L, 42L, 
7L, 10L, 3L, 0L, 15L, 8L, 7L, 75L, 55L, 26L, 18L, 1L, 13L, 0L, 
0L, 0L, 1L, 0L, 4L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 5L, 
17L, 45L, 38L, 10L, 31L, 52L, 36L, 24L, 65L, 97L, 45L, 59L, 49L, 
92L, 51L, 34L, 21L, 20L, 29L, 28L, 22L, 32L, 30L, 86L, 0L, 4L, 
15L, 7L, 4L, 0L, 0L, 0L, 0L, 11L, 3L, 0L, 1L, 3L, 1L, 0L, 72L, 
62L, 98L, 55L, 26L, 39L, 28L, 81L, 20L, 52L, 12L, 48L, 24L, 40L, 
30L, 5L, 6L, 44L, 40L, 37L, 33L, 26L, 17L, 14L, 39L, 27L, 28L, 
67L, 0L, 0L, 0L, 0L, 0L, 0L, 10L, 12L, 14L, 7L, 0L, 2L, 39L, 
67L, 74L, 28L, 23L, 57L, 34L, 36L, 36L, 37L, 46L, 43L, 73L, 65L, 
31L, 64L, 128L, 17L, 3L, 12L, 17L, 0L, 9L, 7L, 0L, 7L, 17L, 0L
), ACTIVITY_Z = c(62L, 95L, 88L, 82L, 90L, 80L, 70L, 68L, 71L, 
98L, 97L, 19L, 65L, 116L, 140L, 55L, 24L, 22L, 7L, 108L, 107L, 
82L, 85L, 36L, 55L, 91L, 75L, 69L, 60L, 64L, 76L, 81L, 103L, 
88L, 74L, 87L, 99L, 111L, 83L, 70L, 117L, 54L, 60L, 50L, 96L, 
83L, 77L, 73L, 62L, 67L, 55L, 117L, 174L, 136L, 5L, 1L, 27L, 
44L, 5L, 7L, 0L, 32L, 54L, 51L, 41L, 87L, 171L, 93L, 120L, 22L, 
117L, 120L, 124L, 148L, 110L, 65L, 136L, 74L, 102L, 81L, 27L, 
32L, 91L, 84L, 51L, 177L, 60L, 26L, 76L, 52L, 11L, 29L, 14L, 
3L, 33L, 14L, 12L, 97L, 81L, 39L, 23L, 7L, 14L, 0L, 2L, 0L, 4L, 
1L, 8L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 16L, 29L, 67L, 
60L, 13L, 44L, 69L, 70L, 39L, 75L, 115L, 69L, 78L, 62L, 126L, 
79L, 53L, 48L, 45L, 51L, 50L, 53L, 72L, 77L, 104L, 0L, 12L, 31L, 
14L, 5L, 0L, 0L, 8L, 0L, 24L, 7L, 2L, 7L, 5L, 3L, 3L, 85L, 77L, 
114L, 76L, 45L, 59L, 48L, 95L, 42L, 70L, 21L, 60L, 40L, 52L, 
40L, 13L, 10L, 51L, 51L, 51L, 43L, 37L, 29L, 22L, 52L, 47L, 40L, 
86L, 5L, 0L, 0L, 0L, 0L, 0L, 20L, 25L, 29L, 14L, 0L, 5L, 57L, 
84L, 99L, 48L, 39L, 78L, 55L, 54L, 57L, 58L, 66L, 67L, 84L, 79L, 
50L, 79L, 141L, 35L, 6L, 27L, 25L, 5L, 17L, 15L, 0L, 14L, 31L, 
0L), Event = c("Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Moving", "Moving", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Moving", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Grazing", "Grazing", "Moving", "Moving", "Grazing", 
"Grazing", "Grazing", "Moving", "Moving", "Grazing", "Grazing", 
"Grazing", "Grazing", "Grooming", "Grooming", "Grazing", "Grazing", 
"Grooming", "Head-up", "Head-up", "Vigilance", "Grazing", "Grazing", 
"Grazing", "Grazing", "Vigilance", "Grazing", "Grazing", "Grazing", 
"Grazing", "Moving", "Grazing", "Grazing", "Grazing", "Grazing", 
"Grazing", "Moving", "Vigilance", "Vigilance", "Vigilance", "Head-up", 
"Head-up", "Head-up", "Head-up", "Grazing", "Grazing", "Grazing", 
"Grazing", "Grazing", "Grazing", "Grazing", "Grazing", "Grazing", 
"Grazing", "Grazing", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Grazing", "Grazing", "Grazing", "Grazing", "Grazing", 
"Grooming", "Grazing", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Moving", "Moving", "Vigilance", 
"Vigilance", "Grazing", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Moving", "Grazing", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Grazing", 
"Grazing", "Grazing", "Grazing", "Head-up", "Head-up", "Grazing", 
"Head-up", "Vigilance", "Head-up", "Head-up", "Head-up", "Moving", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Head-up", "Head-up", "Head-up", "Head-up", "Head-up", "Head-up", 
"Vigilance")), row.names = c(NA, -228L), class = c("data.table", 
"data.frame"), .internal.selfref = <pointer: 0x00000000051e1ef0>)
4

1 回答 1

1

不熟悉你用来进行聚类的包，所以我在弄清楚如何从中提取数据时获得了一些乐趣。我是这样做的：

library(tidyverse)  # This is a large package with many data manipulation functions
library(dtwclust)

trainset1 <- datanet %>%
             select(-Event)

train <- as.matrix(trainset1, byrow = T, ncol=3)

train_clust <- tsclust(train, k = 4L, type = "fuzzy")

clusters <- tibble(cluster = c(train_clust@cluster))

combined_set <- bind_cols(datanet, clusters)

combined_set %>% 
  # I find the ggplot2 package much better for graphing than the base package
  ggplot(aes(ACTIVITY_X, ACTIVITY_Y, color = as.factor(cluster), shape = Event)) +
  geom_point()

在此处输入图像描述

我强烈建议您查看tidyverse一般的数据操作和数据科学。查看这本免费电子书：https ://r4ds.had.co.nz/ 。

于 2019-02-28T16:07:00.317 回答