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

finished commit/topic outcome model

Browse Source
This commit is contained in:
Matthew Gaughan 2025-02-03 17:19:01 -08:00
parent ef5348013e
commit 6c4ed8461d
3 changed files with 10 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
.RData
View File

Binary file not shown.

BIN
020325_CONTRIBUTING_commit_topic_model.rda Normal file
View File

Binary file not shown.

18
topic-outcome-models/readme_topic_outcome_model.R
View File

@ -6,7 +6,7 @@ library(stringr)
readme_count_data_filepath <- "/mmfs1/gscratch/comdata/users/mjilg/govdoc-cr-data/final_data/README_weekly_count_data.csv" readme_count_data_filepath <- "/mmfs1/gscratch/comdata/users/mjilg/govdoc-cr-data/final_data/README_weekly_count_data.csv"
readme_count_df = read.csv(readme_count_data_filepath, header = TRUE) readme_count_df = read.csv(readme_count_data_filepath, header = TRUE)
readme_topic_dist_filepath <- "text_analysis/020125_README_file_topic_distributions.csv" readme_topic_dist_filepath <- "text_analysis/020325_README_file_topic_distributions.csv"
readme_topics_df = read.csv(readme_topic_dist_filepath, header = TRUE) readme_topics_df = read.csv(readme_topic_dist_filepath, header = TRUE)
window_num <- 5 window_num <- 5
@ -26,14 +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 |> #loss of jaraco_keyring, though jaraco keyrings.alt is represented
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)
library(MASS)
commit_outcome_model <- glm.nb(logged_commits ~ 0 + t0 + t1 + t2 + t3 + t4 + t5 + t6 + t7 + t8 + t9 + t10, data=merged_df)
qqnorm(residuals(commit_outcome_model))
summary(commit_outcome_model)
saveRDS(commit_outcome_model, "020325_CONTRIBUTING_commit_topic_model.rda")