mgaughan/mw-lifecycle-analysis
1
0
Fork 0
Code

updating human sampling

Browse Source
This commit is contained in:
Matthew Gaughan 2025-10-06 09:37:06 -07:00
parent a14b08cfd8
commit b982973f37
2 changed files with 55688 additions and 54367 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

110048
dsl/100625_human_info_sample.csv
View File

File diff suppressed because one or more lines are too long

7
dsl/human_sampling.R
View File

@ -3,11 +3,11 @@ library(tidyverse)
main_csv <-"~/analysis_data/100325_unified_phab.csv"
main_df <- read.csv(main_csv, header = TRUE)
set.seed(1871) # For reproducibility
set.seed(1893) # For reproducibility
sampled_df <- main_df %>%
group_by(source) %>%
mutate(sampled_TaskPHID = TaskPHID %in% sample(unique(TaskPHID), 35)) %>%
mutate(sampled_TaskPHID = TaskPHID %in% sample(unique(TaskPHID), 40)) %>%
ungroup() %>%
filter(sampled_TaskPHID) %>%
select(-sampled_TaskPHID)
@ -16,7 +16,7 @@ labeling_sampled_df <- sampled_df %>%
group_by(source) %>%
mutate(
verification_sample = if_else(
TaskPHID %in% sample(unique(TaskPHID), min(7, length(unique(TaskPHID)))), 1L, 0L
TaskPHID %in% sample(unique(TaskPHID), min(8, length(unique(TaskPHID)))), 1L, 0L
)
) %>%
ungroup()
@ -41,5 +41,6 @@ sentence_level_sample <- labeling_sampled_df |>
table(sentence_level_sample$verification_sample)
(nrow(sentence_level_sample) / 293) * 1.5
length(unique(sentence_level_sample$TaskPHID))
write.csv(sentence_level_sample, "100625_human_info_sample.csv", row.names = FALSE)