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

caught duplicates in documents, re-running README topic model

Browse Source
This commit is contained in:
Matthew Gaughan 2025-02-03 16:03:58 -08:00
parent f52ee087b7
commit 5ab4b58542
5 changed files with 4277 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
020325_readme_model.rda Normal file
View File

Binary file not shown.

4248
0203_readme_dweek_ranefs.csv Normal file
View File

File diff suppressed because it is too large Load Diff

17
mg-govdoc-cr_24004290.out Normal file
View File

@ -0,0 +1,17 @@
1. SSH tunnel from your workstation using the following command:
ssh -N -L 8787:n3434:42289 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: K/bHQjx0xRAp26CGpsXM
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 24004290

6
mlm/readme_did_model_fit.R
View File

@ -22,7 +22,7 @@ all_gmodel <- glmer.nb(log1p_count ~ before_after * week_index + scaled_age + (b
data=readme_df) data=readme_df)
summary(all_gmodel) summary(all_gmodel)
#saveRDS(all_gmodel, "020125_readme_model.rda") #saveRDS(all_gmodel, "020325_readme_model.rda")
model_residuals <- residuals(all_gmodel) model_residuals <- residuals(all_gmodel)
acf(model_residuals) acf(model_residuals)
@ -35,7 +35,7 @@ variance_components <- as.data.frame(VarCorr(all_gmodel))
library(broom.mixed) library(broom.mixed)
library(ggplot2) library(ggplot2)
condvals <- broom.mixed::tidy(all_gmodel, effects = "ran_vals", conf.int = TRUE) condvals <- broom.mixed::tidy(all_gmodel, effects = "ran_vals", conf.int = TRUE)
glmer_ranef_Dweek <- test_condvals [which(test_condvals $term == "before_after:week_index"),] glmer_ranef_Dweek <- condvals [which(condvals $term == "before_after:week_index"),]
has_zero <- function(estimate, low, high){ has_zero <- function(estimate, low, high){
return(ifelse((low < 0),ifelse((high > 0), 1, 0), 2)) return(ifelse((low < 0),ifelse((high > 0), 1, 0), 2))
} }
@ -48,4 +48,4 @@ g <- glmer_ranef_Dweek |>
theme_bw() theme_bw()
g g
write.csv(glmer_ranef_Dweek, "0201_readme_dweek_ranefs.csv") write.csv(glmer_ranef_Dweek, "0203_readme_dweek_ranefs.csv")

9
topic-outcome-models/readme_topic_outcome_model.R
View File

@ -26,5 +26,14 @@ readme_topics_df <- readme_topics_df |>
mutate(project_id = ifelse(filename=="jaraco_keyrings.alt_hullabaloo_README.rst", "jaraco_keyrings.alt", project_id)) |> mutate(project_id = ifelse(filename=="jaraco_keyrings.alt_hullabaloo_README.rst", "jaraco_keyrings.alt", project_id)) |>
mutate(project_id = ifelse(filename=="_vcr_vcr_README.md", "vcr_vcr", project_id)) mutate(project_id = ifelse(filename=="_vcr_vcr_README.md", "vcr_vcr", project_id))
filtered_topics <- readme_topics_df |>
filter(project_id %in% summed_data$project_id)
merged_df <- inner_join(summed_data, readme_topics_df, by="project_id") merged_df <- inner_join(summed_data, readme_topics_df, by="project_id")
multiple_mappings <- merged_df %>%
group_by(project_id) %>%
filter(n() > 1) %>%
ungroup()
merged_df$logged_commits <- log1p(merged_df$summed_count) merged_df$logged_commits <- log1p(merged_df$summed_count)