I'm new to R and I'm trying to do a PAM clustering analysis and visualize the results via t-SNE. However, I keep getting this error Error in UseMethod("mutate") : no applicable method for 'mutate' applied to an object of class "factor".
The problem is I'm working with chr type of values as well as numeric. I've been trying to do the cluster analysis without getting rid of the chr and so I used the PAM method listed here: https://www.r-bloggers.com/2016/06/clustering-mixed-data-types-in-r/
This is my data:
# A tibble: 6 × 5
country health_expen gdp_pc life_exp healthsoc_empl
<chr> <dbl> <dbl> <dbl> <dbl>
1 Australia 5130. 52669. 82.9 68
2 Austria 5624. 58076. 82 53.0
3 Belgium 5353. 54278. 82.1 56.4
4 Canada 5190. 49299. 82.3 59.9
5 Chile 2297. 25189. 80.6 26.5
6 Colombia 1293. 15662. 76.6 18.4
and this is what I've been trying to do, where 'df2' is my data:
#cluster interpretation
pam_fit <- pam(gower_dist, diss = TRUE, k = 2)
pam_results <- df2 %>%
dplyr::select(-country) %>%
mutate(cluster = pam_fit$clustering) %>%
group_by(cluster) %>%
do(the_summary = summary(.))
pam_results$the_summary
df2[pam_fit$medoids, ]
#visualize variables with t-distributted stochastic neigbourhood embedding
tsne_obj<- Rtsne(gower_dist, is_distance = TRUE,dims = 3, perplexity = 1)
tsne_data <- tsne_obj$Y %>%
data.frame() %>%
setNames(c("X", "Y")) %>%
mutate(cluster = factor(pam_fit$clustering),name = df2$country)
ggplot(aes(x = X, y = Y), data = tsne_data) +
geom_point(aes(color = cluster))
But as I said, I get an error because of the object of class "factor". What should I do?
