mgaughan/govdoc-cr-analysis
1
0
Fork 0
Code

last minute check

Browse Source
This commit is contained in:
Matthew Gaughan 2025-02-09 10:24:45 -08:00
parent e8afd485ed
commit 559aeaf25b
3 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
.RData
View File

Binary file not shown.

7
mg-govdoc-cr_24092572.out → mg-govdoc-cr_24106808.out
View File

@ -1,17 +1,18 @@
1. SSH tunnel from your workstation using the following command: 1. SSH tunnel from your workstation using the following command:
ssh -N -L 8787:n3433:51613 mjilg@klone.hyak.uw.edu ssh -N -L 8787:n3449:47855 mjilg@klone.hyak.uw.edu
and point your web browser to http://localhost:8787 and point your web browser to http://localhost:8787
2. log in to RStudio Server using the following credentials: 2. log in to RStudio Server using the following credentials:
user: mjilg user: mjilg
password: ezvnunJrjaDZsvr0nhPR password: eam/2d4iPuXQLfLdYWQl
When done using RStudio Server, terminate the job by: 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) 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: 2. Issue the following command on the login node:
scancel -f 24092572 scancel -f 24106808
slurmstepd: error: *** JOB 24106808 ON n3449 CANCELLED AT 2025-02-09T10:24:10 ***

8
quartile_splits.R
View File

@ -1,4 +1,4 @@
contributing_count_filepath <- "/mmfs1/gscratch/comdata/users/mjilg/govdoc-cr-data/final_data/metadata/final_0207_CONTRIBUTING_weekly_count_data.csv" contributing_count_filepath <- "/mmfs1/gscratch/comdata/users/mjilg/govdoc-cr-data/final_data/metadata/CONTRIBUTING_weekly_count_data.csv"
contributing_count_df = read.csv(contributing_count_filepath, header = TRUE) contributing_count_df = read.csv(contributing_count_filepath, header = TRUE)
window_num <- 5 window_num <- 5
@ -9,7 +9,7 @@ contributing_count_df <- contributing_count_df |>
mutate(log1p_count = log1p(commit_count)) mutate(log1p_count = log1p(commit_count))
quantile(contributing_count_df$age / 365, probs = c(0.25, 0.5, 0.75)) quantile(contributing_count_df$age / 365, probs = c(0.25, 0.5, 0.75))
quantile(contributing_count_df$age_at_commit / 365, probs = c(0.25, 0.5, 0.75)) quantile(contributing_count_df$age_at_commit , probs = c(0.25, 0.5, 0.75))
aggregate_cccd <- contributing_count_df |> aggregate_cccd <- contributing_count_df |>
group_by(project_id) |> group_by(project_id) |>
summarize( summarize(
@ -21,7 +21,7 @@ quantile(aggregate_cccd$avg_weekly_commits, probs = c(0.25, 0.5, 0.75))
quantile(aggregate_cccd$authors_before, probs = c(0.25, 0.5, 0.75)) quantile(aggregate_cccd$authors_before, probs = c(0.25, 0.5, 0.75))
quantile(aggregate_cccd$authors_after, probs = c(0.25, 0.5, 0.75)) quantile(aggregate_cccd$authors_after, probs = c(0.25, 0.5, 0.75))
readme_count_filepath <- "/mmfs1/gscratch/comdata/users/mjilg/govdoc-cr-data/final_data/metadata/final_0207_README_weekly_count_data.csv" readme_count_filepath <- "/mmfs1/gscratch/comdata/users/mjilg/govdoc-cr-data/final_data/metadata/README_weekly_count_data.csv"
readme_count_df = read.csv(readme_count_filepath, header = TRUE) readme_count_df = read.csv(readme_count_filepath, header = TRUE)
window_num <- 5 window_num <- 5
@ -32,7 +32,7 @@ readme_count_df <- readme_count_df |>
mutate(log1p_count = log1p(commit_count)) mutate(log1p_count = log1p(commit_count))
quantile(readme_count_df$age / 365, probs = c(0.25, 0.5, 0.75)) quantile(readme_count_df$age / 365, probs = c(0.25, 0.5, 0.75))
quantile(readme_count_df$age_at_commit / 365, probs = c(0.25, 0.5, 0.75)) quantile(readme_count_df$age_at_commit, probs = c(0.25, 0.5, 0.75))
sd(readme_count_df$age_at_commit / 365) sd(readme_count_df$age_at_commit / 365)
aggregate_rccd <- readme_count_df |> aggregate_rccd <- readme_count_df |>
group_by(project_id) |> group_by(project_id) |>