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

updated with new outcome variable

Browse Source
This commit is contained in:
Matthew Gaughan 2025-10-03 12:01:37 -07:00
parent 5f157ef532
commit 83bcc15811
4 changed files with 377640 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

377609
analysis_data/100325_unified_phab.csv Normal file
View File

File diff suppressed because one or more lines are too long

26
analysis_data/outcome_variable_check.R Normal file
View File

@ -0,0 +1,26 @@
library(tidyverse)
main_csv <- "~/analysis_data/092925_unified_phab.csv"
main_df <- read.csv(main_csv, header = TRUE)
date1 <-1380499199 # 9-29-2013
date2 <- 1385510399 # 11-26-2013
date3 <-1443657599 # 09-30-2015
new_outcome <- main_df |>
mutate(
resolution_outcome = case_when(
comment_type == "task_description" & source == "c1" & date_closed < date1 ~ TRUE,
comment_type == "task_description" & source == "c1" & date_closed >= date1 ~ FALSE,
comment_type == "task_description" & source == "c2" & date_closed < date2 ~ TRUE,
comment_type == "task_description" & source == "c2" & date_closed >= date2 ~ FALSE,
comment_type == "task_description" & source == "c3" & date_closed < date3 ~ TRUE,
comment_type == "task_description" & source == "c3" & date_closed >= date3 ~ FALSE,
comment_type == "task_description" & is.na(date_closed) ~ FALSE,
TRUE ~ NA
)
) |>
select(-closed_relevance)
anyNA(new_outcome$resolution_outcome[new_outcome$comment_type == "task_description"])
write.csv(new_outcome, "100325_unified_phab.csv", row.names = FALSE)

5
analysis_data/roster_confirmation.R Normal file
View File

@ -0,0 +1,5 @@
library(tidyverse)
library(jsonlite)
## TODO: reload roster and map onto the existing data
roster_csv <-"~/analysis_data/100225_phabricator_api_roster_results.csv"
roster_df <- read.csv(roster_csv, header = TRUE)

0
analysis_data/092925_unified_phab.csv → analysis_data/stale_unifieds/092925_unified_phab.csv
View File

Can't render this file because it is too large.