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

pulling sample for human_labeling

Browse Source
This commit is contained in:
Matthew Gaughan 2025-10-06 09:14:00 -07:00
parent 83bcc15811
commit a14b08cfd8
3 changed files with 59732 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59686
dsl/100625_human_info_sample.csv Normal file
View File

File diff suppressed because one or more lines are too long

36
dsl/human_sampling.R
View File

@ -1,23 +1,45 @@
library(tidyverse) library(tidyverse)
main_csv <-"~/analysis_data/092925_unified_phab.csv" main_csv <-"~/analysis_data/100325_unified_phab.csv"
main_df <- read.csv(main_csv, header = TRUE) main_df <- read.csv(main_csv, header = TRUE)
set.seed(123) # For reproducibility set.seed(1871) # For reproducibility
sampled_df <- main_df %>% sampled_df <- main_df %>%
group_by(source) %>% group_by(source) %>%
mutate(sampled_TaskPHID = TaskPHID %in% sample(unique(TaskPHID), 30)) %>% mutate(sampled_TaskPHID = TaskPHID %in% sample(unique(TaskPHID), 35)) %>%
ungroup() %>% ungroup() %>%
filter(sampled_TaskPHID) %>% filter(sampled_TaskPHID) %>%
select(-sampled_TaskPHID) select(-sampled_TaskPHID)
sentence_level_sample <- sampled_df |> labeling_sampled_df <- sampled_df %>%
mutate(cleaned_sentences = str_extract_all(olmo_cleaned_sentences, "(?<=')[^']+(?=')")) |> group_by(source) %>%
mutate(
verification_sample = if_else(
TaskPHID %in% sample(unique(TaskPHID), min(7, length(unique(TaskPHID)))), 1L, 0L
)
) %>%
ungroup()
sentence_level_sample <- labeling_sampled_df |>
mutate(
cleaned_sentences = lapply(
olmo_cleaned_sentences,
function(x) {
m <- str_match_all(x, "'([^']*)'|\"([^\"]*)\"")[[1]]
# Both columns 2 and 3 may exist, but only one will be filled for each match
vals <- c(m[,2], m[,3])
vals <- vals[vals != "" & !is.na(vals)]
return(vals)
}
)
)|>
unnest(cleaned_sentences)|> unnest(cleaned_sentences)|>
filter(cleaned_sentences != ", ") |> filter(cleaned_sentences != ", ") |>
select(-olmo_sentence_categories, -starts_with("normalized"), -starts_with("gerrit")) select(-olmo_sentence_categories, -starts_with("normalized"), -contains("gerrit"))
table(sentence_level_sample$verification_sample)
(nrow(sentence_level_sample) / 293) * 1.5 (nrow(sentence_level_sample) / 293) * 1.5
#write.csv(output_df, "100125_human_info_sample.csv", row.names = FALSE) write.csv(sentence_level_sample, "100625_human_info_sample.csv", row.names = FALSE)

17
mgaughan-rstudio-server_29985545.out Normal file
View File

@ -0,0 +1,17 @@
1. SSH tunnel from your workstation using the following command:
ssh -N -L 8787:n3439:58519 mjilg@klone.hyak.uw.edu
and point your web browser to http://localhost:8787
2. log in to RStudio Server using the following credentials:
user: mjilg
password: Kyq6AGP0kRtXvXeoXReZ
When done using RStudio Server, terminate the job by:
1. Exit the RStudio Session ("power" button in the top right corner of the RStudio window)
2. Issue the following command on the login node:
scancel -f 29985545