1
0

shelving some of the merge work for now

This commit is contained in:
Matthew Gaughan 2025-09-14 09:11:33 -07:00
parent 77fc3ec541
commit f9c12bb445
4 changed files with 151733 additions and 2 deletions

View File

@ -0,0 +1,17 @@
1. SSH tunnel from your workstation using the following command:
ssh -N -L 8787:n3439:36873 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: qv1O0tpb3YCkMtmNIRbg
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 29576188

151688
p2/080425_gerrit_filled_df.csv Normal file

File diff suppressed because one or more lines are too long

26
p2/df_consolidation.R Normal file
View File

@ -0,0 +1,26 @@
library(tidyverse)
library(jsonlite)
main_csv <-"~/p2/071425_master_discussion_data.csv"
main_df <- read.csv(main_csv, header = TRUE)
gerrit_csv <-"~/p2/080425_gerrit_filled_df.csv"
gerrit_df <- read.csv(gerrit_csv, header = TRUE)
library(dplyr)
gerrit_extracted_df <- gerrit_df |>
mutate(
jsonfixed = gsub("(?<=\\{|\\[|, )'(\\w+?)'(?=\\s*:)", '"\\1"', selected_gerrit_results, perl = TRUE),
jsonfixed = gsub(":(\\s*)'(.*?)'(?=[}\\],])", ':\\1"\\2"', jsonfixed, perl = TRUE),
jsonfixed = gsub("(?<=[:\\[,\\{])\\s*'([^']*)'\\s*(?=[,\\}\\]])", '"\\1"', jsonfixed, perl = TRUE),
expandedjsonlist = lapply(jsonfixed, fromJSON)
)
# TODO select
# gerrit status: categorical
# owner_wikimedia: BOOL
# LOCa: #
# LOCd: #
# count_reviewers: #
# url: url

View File

@ -11,7 +11,7 @@ information_typology = c("EXPECTED BEHAVIOR", "MOTIVATION", "OBSERVED BUG BEHAVI
"ISSUE CONTENT MANAGEMENT", "ACTION ON ISSUE", "SOCIAL CONVERSATION")
url_extensions = c("GERRIT_URL", "URL")
olmo_categorization_csv <-"~/p2/quest/090425_olmo_batched_categorized.csv"
(olmo_categorization_csv <-"~/p2/quest/090425_olmo_batched_categorized.csv"
olmo_categorization_df <- read.csv(olmo_categorization_csv, header = TRUE)
olmo_categorization_df <- olmo_categorization_df %>%