#RStudio Version Version 1.2.1335 need this one--> 1.2.5019
sessionInfo()
# R version 4.0.0 Patched (2020-05-03 r78349)
#Platform: x86_64-w64-mingw32/x64 (64-bit)
#Running under: Windows 10 x64 (build 17763)
Hello:
I have data that I am trying to manipulate for Kmeans clustering.
Original data looks like this
str(geo1)
# 'data.frame': 2352 obs. of 5 variables:
# $ ID: Factor w/ 2352 levels "101040199600",..: 590 908 976 509 1674 690 1336
86 726 1702 ...
# $ state : Factor w/ 41 levels "AL","AR","AZ",..: 32 10 25 11 9 32
13 31 12 12 ...
# $ city : Factor w/ 1337 levels "ABBOTTSTOWN",..: 932 156 230 698
965 1330 515 727 1127 1304 ...
# $ latitude : num 40.4 31.2 40.8 42.1 26.8 ...
# $ longitude : num -79.9 -81.5 -74 -91.6 -82.1 ...
I created a subset adding column prop_of_total
str(trnd1_tbl)
tibble [1,457 x 5] (S3: tbl_df/tbl/data.frame)
$ city : Factor w/ 1337 levels "ABBOTTSTOWN",..: 1 2 3 4 5 6 7 8 9 10
...
$ state : Factor w/ 41 levels "AL","AR","AZ",..: 32 36 10 28 12 36 10
11 26 38 ...
$ Basecountsum : num [1:1457] 2352 2352 2352 2352 2352 ...
$ Basecount2 : num [1:1457] 1 1 1 1 1 2 1 1 2 1 ...
$ prop_of_total: num [1:1457] 0.000425 0.000425 0.000425 0.000425 0.000425 ...
Then I spread it
trnd2_tbl <- trnd1_tbl %>%
dplyr::select(city, state, prop_of_total) %>%
spread(key = city, value = prop_of_total, fill = 0) #remove the NA's with
fill
str(trnd2_tbl)#tibble [41 x 1,338] (S3: tbl_df/tbl/data.frame)
Then I run a Kmeans
kmeans_obj1 <- trnd2_tbl %>%
dplyr::select(- state) %>%
kmeans(centers = 20, nstart = 100)
str(kmeans_obj1)
List of 9
$ cluster : int [1:41] 11 11 9 11 11 4 11 11 16 2 ...
$ centers : num [1:20, 1:1337] 0 0 0 0 0 0 0 0 0 0 ...
..- attr(*, "dimnames")=List of 2
.. ..$ : chr [1:20] "1" "2" "3" "4" ...
.. ..$ : chr [1:1337] "ABBOTTSTOWN" "ABILENE" "ACWORTH" "ADAMS" ...
$ totss : num 0.00158
$ withinss : num [1:20] 0 0 0 0 0 0 0 0 0 0 ...
$ tot.withinss: num 0.0000848
$ betweenss : num 0.0015
$ size : int [1:20] 1 1 1 1 1 1 1 1 1 1 ...
$ iter : int 3
$ ifault : int 0
- attr(*, "class")= chr "kmeans"
Then I go and try to tidy:
#Tidy, glance, augment
#Just makes it easier to use or view the obj's in the obj list
broom::tidy(kmeans_obj1) %>% glimpse()
broom::glance(kmeans_obj1)
##A tibble: 1 x 4
# totss tot.withinss betweenss iter
# <dbl> <dbl> <dbl> <int>
# 1 0.00158 0.0000848 0.00150 3
However, when I run this piece I get an error:
broom::augment(kmeans_obj1, trnd2_tbl) %>%
dplyr::select(city, .cluster)
#Error: Must subset columns with a valid subscript vector.
# The subscript has the wrong type `data.frame<
# u: double
# x: double
>`.
i It must be numeric or character.
Here is the back trace:
rlang::last_error()
# Backtrace:
# 1. broom::augment(kmeans_obj1, trnd2_tbl)
# 9. dplyr::select(., city, .cluster)
# 11. tidyselect::vars_select(tbl_vars(.data), !!!enquos(...))
# 12. tidyselect:::eval_select_impl(...)
# 20. tidyselect:::vars_select_eval(...)
# 21. tidyselect:::walk_data_tree(expr, data_mask, context_mask)
# 22. tidyselect:::eval_c(expr, data_mask, context_mask)
# 23. tidyselect:::reduce_sels(node, data_mask, context_mask, init = init)
# 24. tidyselect:::walk_data_tree(new, data_mask, context_mask)
# 25. tidyselect:::as_indices_sel_impl(...)
# 26. tidyselect:::as_indices_impl(x, vars, strict = strict)
# 27. vctrs::vec_as_subscript(x, logical = "error")
I am not sure what I am supposed to fix?
Maybe someone has had similar error and can advise me please?
Thank you.
WHP
Proprietary
NOTICE TO RECIPIENT OF INFORMATION:\ This e-mail may con...{{dropped:16}}
______________________________________________
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
