我有關于使用Q和A應答序列期間注視行為的資料；注視被記錄用于每個揚聲器A，B以及C在列A_aoi，B_aoi和C_aoi，凝視持續時間被記錄在列A_aoi_dur，B_aoi_dur和C_aoi_dur：
df <- data.frame(
Speaker = c("ID01.A", NA, "ID01.B", "ID33.B", "ID33.A", "ID33.C"),
Utterance = c("Who did it?", NA, "Peter did.", "So you're coming?", "erm", "Yes, sure."),
Sequ = c(1,1,1,2,2,2),
Q = c("q_wh", "", "", "q_decl", "", ""),
A_aoi = c("C*B*B", "B", "B*", "B*C", "*C", "B*"),
A_aoi_dur = c("1,2,3,4,5", "1", "1,2", "1,2,3", "1,2", "1,2"),
B_aoi = c("C*A", "*A", "A*", "A*C", "C", "*C"),
B_aoi_dur = c("1,2,3", "1,2", "1,2", "1,2,3", "1", "1,2"),
C_aoi = c("A*A", "A", "A*", "B*C*B", "*B", "B*A"),
C_aoi_dur = c("1,2,3", "1", "1,2", "1,2,3,4,5", "1,2", "1,2,3")
)
我需要找出是哪個人的提問，在完成他們的問題，注視著最后。
我一直試圖通過這一系列操作到達那里，但被卡住了：
library(tidyr)
library(dplyr)
library(stringr)
df %>%
# for each `Sequ`...
group_by(Sequ) %>%
mutate(
# Who is the question by?
Quest_by = sub(".*(.)$", "\\1", first(Speaker)),
# Who is the answer by?
Answ_by = sub(".*(.)$", "\\1", last(Speaker))
) %>%
# rename to create column names that are processable by `names_pattern` for `pivot_longer`:
rename_with(~ str_c(., "_AOI"), ends_with("_aoi")) %>%
# collect all AOI gazes by A, B, and C into one column:
pivot_longer(cols = contains("_aoi"),
names_to = c("Gaze_by", ".value"), #
names_pattern = "^(.*)_([^_] $)"
) %>%
# rename `AOI` and `dur` columns:
rename(Gaze_to = AOI, Gaze_dur = dur) %>%
# edit `Gaze_by` and `Gaze_to` values for upcoming analysis:
mutate(
# simplify `Gaze_by` values to speaker labels:
Gaze_by = sub("^(.).*", "\\1", Gaze_by),
# insert comma into `Gaze_to` as splitting pattern for `separate_rows` command below:
Gaze_to = str_replace_all(Gaze_to, "(?<=.)(?=.)", ",")
) %>%
# assign each `Gaze_to` and `Gaze_dur` value its own row based on comma as splitting pattern:
separate_rows(c(Gaze_to, Gaze_dur), sep = ",", convert = TRUE)
所需的輸出：（以這種或類似的形式）
Speaker Utterance Sequ Q Q_by Answ_by Last_Gaze_to Last_Gaze_dur
1 ID01.A Who did it? 1 q_wh A B B 5
2 <NA> <NA> 1
3 ID01.B Peter did. 1
4 ID33.B So you're coming? 2 q_decl B C C 3
5 ID33.A erm 2
6 ID33.C Yes, sure. 2
編輯：我想出了這個解決方案（df0上述操作的結果在哪里）：
df0 %>%
filter(Quest_by == Gaze_by) %>%
group_by(Q, Sequ) %>%
mutate(Last_Gaze_to = last(Gaze_to),
Last_Gaze_dur = last(Gaze_dur)) %>%
ungroup() %>%
group_by(Line) %>%
slice_head() %>%
select(-matches("^G")) %>%
ungroup() %>%
mutate(across(c(5:9),
~ifelse(Q == "", NA, .)))
# A tibble: 6 × 9
Line Speaker Utterance Sequ Q Quest_by Answ_by Last_Gaze_to Last_Gaze_dur
<int> <chr> <chr> <dbl> <chr> <chr> <chr> <chr> <int>
1 1 ID01.A Who did it? 1 q_wh A B B 5
2 2 NA NA 1 NA NA NA NA NA
3 3 ID01.B Peter did. 1 NA NA NA NA NA
4 4 ID33.B So you're coming? 2 q_decl B C C 3
5 5 ID33.A erm 2 NA NA NA NA NA
6 6 ID33.C Yes, sure. 2 NA NA NA NA NA
Thanks for anybody who did take the trouble of looking into this difficult question. Tips for improvement of the solution are well taken!
uj5u.com熱心網友回復：
這是一個嘗試。我對“凝視”等沒有任何經驗......
我花了一些時間和一些幫助（請參閱此處有條件地從 column1 獲取值，如果 column1 name == first(value) from column2 BY GROUP感謝@tmfmnk。
我希望這些雜七雜八的代碼可能會有所幫助。為了可讀性，我保留了代碼。我相信可以對其進行微調。我嘗試做的主要部分是在塊中。
library(tidyverse)
df %>%
# block1
separate(Speaker, c("SpeakerID", "SpeakerName")) %>%
group_by(Sequ) %>%
mutate(Q_by = first(SpeakerName)) %>%
mutate(Answer_by = last(na.omit(SpeakerName))) %>%
rename_with(~str_replace(.x, '_aoi', ''), matches('aoi')) %>%
# block 2
rowwise() %>%
mutate(Last_Gaze_to = get(Q_by)) %>%
group_by(Sequ, Q_by) %>%
mutate(Last_Gaze_to = str_extract(last(Last_Gaze_to), '[A-Z]')) %>%
rename(A_aoi = A, B_aoi = B, C_aoi = C) %>%
rename_with(~str_replace(.x, '_dur', ''), matches('dur')) %>%
# block 3
rowwise() %>%
mutate(Last_Gaze_dur = get(Q_by)) %>%
group_by(Sequ, Q_by) %>%
mutate(Last_Gaze_dur = first(Last_Gaze_dur)) %>%
mutate(Last_Gaze_dur = str_sub(Last_Gaze_dur, -1,-1)) %>%
# block 4
ungroup() %>%
group_by(Sequ) %>%
mutate(across(c(Q_by, Answer_by, Last_Gaze_to, Last_Gaze_dur), ~ifelse(duplicated(.), NA,first(.)))) %>%
rename(A_aoi_dur = A, B_aoi_dur=B, C_aoi_dur=C)
輸出：
oups: Sequ [2]
SpeakerID SpeakerName Utterance Sequ Q A_aoi A_aoi_dur B_aoi B_aoi_dur C_aoi C_aoi_dur Q_by Answer_by Last_Gaze_to Last_Gaze_dur
<chr> <chr> <chr> <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 ID01 A Who did it? 1 "q_wh" C*B*B 1,2,3,4,5 C*A 1,2,3 A*A 1,2,3 A B B 5
2 NA NA NA 1 "" B 1 *A 1,2 A 1 NA NA NA NA
3 ID01 B Peter did. 1 "" B* 1,2 A* 1,2 A* 1,2 NA NA NA NA
4 ID33 B So you're coming? 2 "q_decl" B*C 1,2,3 A*C 1,2,3 B*C*B 1,2,3,4,5 B C C 3
5 ID33 A erm 2 "" *C 1,2 C 1 *B 1,2 NA NA NA NA
6 ID33 C Yes, sure. 2 "" B* 1,2 *C 1,2 B*A 1,2,3 NA NA NA NA
轉載請註明出處，本文鏈接：https://www.uj5u.com/ruanti/393456.html
上一篇：如何清理R中的面板資料集，以便僅選擇連續一年或兩年以上的條目？
下一篇：僅在R中從列日期類中提取