stau.space
this repo has no description
Merge branch 'main' of github.com:sona-tau/underrepresentation-theory
+86
+86
code/interactive_wordcloud.R
+86
code/interactive_wordcloud.R
···
1
+
load("code/big_question_tag_df.rda")
2
+
3
+
head(big_question_tag_df)
4
+
summary(big_question_tag_df)
5
+
view(big_question_tag_df)
6
+
7
+
#Remove rows where Tags = NA
8
+
only_tag <- big_question_tag_df |>
9
+
filter(Tags != "NA")
10
+
view(only_tag)
11
+
12
+
tagged_ams <- only_tag |>
13
+
filter(Source == "AMS")
14
+
15
+
tagged_cbms <- only_tag |>
16
+
filter(Source == "CBMS")
17
+
18
+
view(tagged_ams)
19
+
view(tagged_cbms)
20
+
21
+
#All questions by source
22
+
ams_ques <- big_question_tag_df |>
23
+
filter(Source == "AMS")
24
+
25
+
cbms_ques <- big_question_tag_df |>
26
+
filter(Source == "CBMS")
27
+
28
+
ipeds_ques <- big_question_tag_df |>
29
+
filter(Source == "IPEDS")
30
+
31
+
#Tokenization and wordcloud per source
32
+
#AMS
33
+
tidy_ams_ques <- ams_ques |>
34
+
unnest_tokens(word, Questions) |>
35
+
anti_join(stop_words) |>
36
+
filter(!str_detect(word, "^[0-9]+$"))
37
+
38
+
word_counts_ams <- tidy_ams_ques |>
39
+
count(word, sort = TRUE) |>
40
+
filter(n > 0)
41
+
42
+
view(word_counts_ams)
43
+
44
+
#CBMS
45
+
tidy_cbms_ques <- cbms_ques |>
46
+
unnest_tokens(word, Questions) |>
47
+
anti_join(stop_words) |>
48
+
filter(!str_detect(word, "^[0-9]+$"))
49
+
50
+
word_counts_cbms <- tidy_cbms_ques |>
51
+
count(word, sort = TRUE) |>
52
+
filter(n > 5) |>
53
+
filter(!str_detect(word, "_|b2|b1|e1|f1|e2|e.g|ii"))
54
+
55
+
view(word_counts_cbms)
56
+
57
+
#IPEDS
58
+
tidy_ipeds_ques <- ipeds_ques |>
59
+
unnest_tokens(word, Questions) |>
60
+
anti_join(stop_words) |>
61
+
filter(!str_detect(word, "^[0-9]+$"))
62
+
63
+
word_counts_ipeds <- tidy_ipeds_ques |>
64
+
count(word, sort = TRUE) |>
65
+
filter(n > 5) |>
66
+
filter(!str_detect(word, "e.g"))
67
+
68
+
view(word_counts_ipeds)
69
+
70
+
#install.packages("wordcloud2")
71
+
library("wordcloud2")
72
+
#install.packages("httpgd")
73
+
74
+
#AMS
75
+
my_palette = c("#355070",
76
+
"#6d597a",
77
+
"#b56576",
78
+
"#e56b6f",
79
+
"#eaac8b")
80
+
81
+
ams_wc = wordcloud2(
82
+
word_counts_ams,
83
+
color = rep_len(my_palette,
84
+
nrow(word_counts_ams)))
85
+
86
+