diff --git a/R/.Rhistory b/R/.Rhistory
index 90631e7..5426cf6 100644
--- a/R/.Rhistory
+++ b/R/.Rhistory
@@ -1,198 +1,3 @@
-hist(contrib_df$event_gap)
-median(contrib_df$event_gap)
-1786.431 / 265
-1786.431 / 365
-sd(contrib_df$event_gap)
-sd(contrib_df$event_gap)
-max(readme_df$event_gap)
-#all_gmodel <- glmer.nb(log1p_count ~ D * week_offset + scaled_project_age + scaled_event_gap + (D * week_offset | upstream_vcs_link),
-#              control=glmerControl(optimizer="bobyqa",
-#                                           optCtrl=list(maxfun=2e5)), nAGQ=0, data=all_actions_data)
-all_gmodel <- readRDS("0710_contrib_all.rda")
-summary(all_gmodel)
-library(tidyverse)
-library(texreg)
-readme_rdd <- readRDS("final_models/0624_readme_all_rdd.rda")
-contrib_rdd <- readRDS("final_models/0710_contrib_all.rda")
-contrib_rdd <- readRDS("final_models/0710_contrib_all_rdd.rda")
-texreg(list(readme_rdd, contrib_rdd), stars=NULL, digits=3, use.packages=FALSE,
-custom.model.names=c( 'README','CONTRIBUTING'),
-custom.coef.names=c('(Intercept)', 'Indtroduction', 'Week (Time)', 'Project Age', 'Introduction:Week', 'Event Gap'),
-table=FALSE, ci.force = TRUE)
-source("~/Desktop/git/24_deb_gov/R/contribCrescAnalysis.R")
-#all_gmodel <- readRDS("0710_contrib_all.rda")
-summary(all_gmodel)
-saveRDS(all_gmodel, "0710_contrib_cresc.rda")
-range(all_actions_data$log1p_count)
-source("~/Desktop/git/24_deb_gov/R/contribRDDAnalysis.R")
-source("~/Desktop/git/24_deb_gov/R/contribRDDAnalysis.R")
-all_gmodel <- readRDS("0711_contrib_all.rda")
-summary(all_gmodel)
-library(tidyverse)
-library(texreg)
-library(tidyverse)
-library(texreg)
-readme_rdd <- readRDS("final_models/0624_readme_all_rdd.rda")
-contrib_rdd <- readRDS("final_models/0711_contrib_all_rdd.rda")
-summary(readme_rdd)
-texreg(list(readme_rdd, contrib_rdd), stars=NULL, digits=3, use.packages=FALSE,
-custom.model.names=c( 'README','CONTRIBUTING'),
-custom.coef.names=c('(Intercept)', 'Indtroduction', 'Week (Time)', 'Project Age', 'Introduction:Week', 'Event Gap'),
-table=FALSE, ci.force = TRUE)
-contrib_rdd <- readRDS("final_models/0711_contrib_all_rdd.rda")
-contrib_rdd <- readRDS("final_models/0711_contrib_all_rdd.rda")
-texreg(list(readme_rdd, contrib_rdd), stars=NULL, digits=3, use.packages=FALSE,
-custom.model.names=c( 'README','CONTRIBUTING'),
-custom.coef.names=c('(Intercept)', 'Indtroduction', 'Week (Time)', 'Project Age', 'Introduction:Week', 'Event Gap'),
-table=FALSE, ci.force = TRUE)
-texreg(list(readme_rdd, contrib_rdd), stars=NULL, digits=3, use.packages=FALSE,
-custom.model.names=c( 'README','CONTRIBUTING'),
-custom.coef.names=c('(Intercept)', 'Indtroduction', 'Week (Time)', 'Project Age', 'Introduction:Week'),
-table=FALSE, ci.force = TRUE)
-readme_groupings <- read.csv('../final_data/deb_readme_interaction_groupings.csv')
-contrib_groupings <- read.csv('../final_data/0711_contrib_inter_groupings.csv')
-subdirColors <-
-setNames( c('firebrick1', 'forestgreen', 'cornflowerblue')
-, c(0,1,2)  )
-readme_g <- readme_groupings |>
-ggplot(aes(x=rank, y=estimate, col = as.factor(ranef_grouping))) +
-geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
-scale_color_manual(values = subdirColors) +
-guides(fill="none", color="none")+
-theme_bw()
-readme_g
-contrib_g <- contrib_groupings |>
-ggplot(aes(x=rank, y=estimate, col = as.factor(ranef_grouping))) +
-geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
-scale_color_manual(values = subdirColors) +
-theme_bw() +
-theme(legend.position = "top")
-contrib_g
-library(gridExtra)
-grid.arrange(contrib_g, readme_g, nrow = 1)
-source("~/Desktop/git/24_deb_gov/R/contribRDDAnalysis.R")
-source("~/Desktop/git/24_deb_gov/R/documentReadabilityAnalysis.R")
-contrib_pop_df <- read_csv("../final_data/deb_contrib_pop_change.csv")
-contrib_df <- read_csv("../final_data/deb_contrib_did.csv")
-View(contrib_pop_df)
-contrib_readability_df <- read_csv('../text_analysis/dwo_readability_contributing.csv')
-View(contrib_readability_df)
-View(contrib_pop_df)
-View(contrib_readability_df)
-View(contrib_pop_df)
-View(contrib_readability_df)
-View(contrib_pop_df)
-View(contrib_pop_df)
-View(contrib_df)
-View(contrib_pop_df)
-View(contrib_readability_df)
-View(contrib_pop_df)
-#concat dataframes into central data
-contrib_df_total <- contrib_pop_df |>
-mutate(project_name = str_split(upstream_vcs_link, pattern="/")[-1])
-View(contrib_pop_df)
-View(contrib_readability_df)
-View(contrib_readability_df)
-contrib_df_total <- contrib_readability_df |>
-mutate(project_name = str_split(filename, pattern="_")[-2])
-View(contrib_readability_df)
-contrib_df_total <- contrib_readability_df |>
-mutate(project_name = str_split(filename, pattern="_"))
-View(contrib_df_total)
-contrib_df_total <- contrib_readability_df |>
-mutate(project_name = str_split(filename, pattern="_")[0])
-contrib_df_total <- contrib_readability_df |>
-mutate(project_name = str_split(filename, pattern="_")[1])
-View(contrib_df_total)
-contrib_df_total <- contrib_readability_df |>
-mutate(project_name = str_split(filename, pattern="_")[1]  |>
-sapply("[[", 1))
-View(contrib_df_total)
-contrib_df_total <- contrib_readability_df |>
-mutate(project_name = str_split(filename, pattern="_"))
-View(contrib_df_total)
-contrib_df_total <- contrib_readability_df |>
-mutate(project_name_array = str_split(filename, pattern="_")) |>
-mutate(projes_name = project_name_array[1])
-View(contrib_df_total)
-View(contrib_readability_df)
-View(contrib_pop_df)
-#concat dataframes into central data
-contrib_pop_df <- contrib_pop_df %>%
-mutate(first_element = map_chr(upstream_vcs_link, ~ {
-parts <- str_split(.x, pattern = "/")[[1]]
-if (length(parts) >= 1) {
-parts[1]  # Extract the first element after splitting
-} else {
-NA_character_
-}
-}))
-View(contrib_pop_df)
-contrib_df_total <- contrib_readability_df |>
-mutate(project_name = map_chr(filename, ~ {
-parts <- str_split(.x, pattern = "_")[[1]]
-if (length(parts) >= 1) {
-parts[1]
-} else {
-NA_character_
-}
-}))
-contrib_df <- read_csv("../final_data/deb_contrib_did.csv")
-contrib_pop_df <- read_csv("../final_data/deb_contrib_pop_change.csv")
-contrib_readability_df <- read_csv('../text_analysis/dwo_readability_contributing.csv')
-contrib_df_total <- contrib_readability_df |>
-mutate(project_name = map_chr(filename, ~ {
-parts <- str_split(.x, pattern = "_")[[1]]
-if (length(parts) >= 1) {
-parts[1]
-} else {
-NA_character_
-}
-}))
-View(contrib_df_total)
-contrib_pop_df <- contrib_pop_df |>
-mutate(project_name = map_chr(upstream_vcs_link, ~ {
-parts <- str_split(.x, pattern = "/")[[1]]
-if (length(parts) >= 1) {
-parts[-1]
-} else {
-NA_character_
-}
-}))
-parts[length(parts)]
-contrib_pop_df <- contrib_pop_df |>
-mutate(project_name = map_chr(upstream_vcs_link, ~ {
-parts <- str_split(.x, pattern = "/")[[1]]
-if (length(parts) >= 1) {
-parts[length(parts)]
-} else {
-NA_character_
-}
-}))
-View(contrib_pop_df)
-source("~/Desktop/git/24_deb_gov/R/docChar_outcomes.R")
-source("~/Desktop/git/24_deb_gov/R/docChar_outcomes.R")
-contrib_total_df <- contrib_pop_df |>
-left_join(contrib_readability_df, by="project_name")
-View(contrib_total_df)
-# test regressions
-lm1 <- glm.nb(after_contrib_new ~ word_count, data = contrib_total_df)
-# test regressions
-library(MASS)
-lm1 <- glm.nb(after_contrib_new ~ word_count, data = contrib_total_df)
-summary(lm1)
-View(contrib_total_df)
-contrib_total_df <- contrib_pop_df |>
-join(contrib_readability_df, by="project_name")
-View(contrib_total_df)
-View(contrib_readability_df)
-qqnorm(residuals(lm1))
-source("~/Desktop/git/24_deb_gov/R/docChar_outcomes.R")
-lm1 <- glm.nb(after_contrib_new ~ linsear_write, data = contrib_total_df)
-lm1 <- glm.nb(after_contrib_new ~ linsear, data = contrib_total_df)
-View(contrib_total_df)
-lm1 <- glm.nb(after_contrib_new ~ linsear_write_formula, data = contrib_total_df)
-qqnorm(residuals(lm1))
 summary(lm1)
 lm1 <- glm.nb(after_contrib_new ~ reading_time, data = contrib_total_df)
 qqnorm(residuals(lm1))
@@ -510,3 +315,198 @@ summary(lm1)
 lm1 <- glm.nb(summed_count ~ reading_time + linsear_write_formula + flesch_reading_ease + mcalpine_eflaw + word_count, data = contrib_total_df)
 qqnorm(residuals(lm1))
 summary(lm1)
+contrib_topics_df <- read_csv("../text_analysis/contrib_file_topic_distributions.csv")
+library(tidyverse)
+contrib_topics_df <- read_csv("../text_analysis/contrib_file_topic_distributions.csv")
+View(contrib_topics_df)
+source("~/Desktop/git/24_deb_gov/R/contrib_topic_outcomes.R")
+source("~/Desktop/git/24_deb_gov/R/contrib_topic_outcomes.R")
+source("~/Desktop/git/24_deb_gov/R/contrib_docChar_outcomes.R")
+source("~/Desktop/git/24_deb_gov/R/contrib_topic_outcomes.R")
+source("~/Desktop/git/24_deb_gov/R/contrib_topic_outcomes.R")
+source("~/Desktop/git/24_deb_gov/R/contrib_topic_outcomes.R")
+lm1 <- glm.nb(summed_count ~ t0 + t1 + t2 + t3, data = contrib_total_df)
+#running regressions
+library(MASS)
+lm1 <- glm.nb(summed_count ~ t0 + t1 + t2 + t3, data = contrib_total_df)
+source("~/Desktop/git/24_deb_gov/R/contrib_topic_outcomes.R")
+library(stringr)
+library(plyr)
+contrib_topics_df <- read_csv("../text_analysis/contrib_file_topic_distributions.csv")
+contrib_df <- read_csv("../final_data/deb_contrib_did.csv")
+contrib_pop_df <- read_csv("../final_data/deb_contrib_pop_change.csv")
+#get the contribution count
+#some preprocessing and expansion
+col_order <- c("upstream_vcs_link", "age_in_days", "first_commit", "first_commit_dt", "event_gap", "event_date",  "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+contrib_df <- contrib_df[,col_order]
+contrib_df$ct_before_all <- str_split(gsub("[][]","", contrib_df$before_all_ct), ", ")
+contrib_df$ct_after_all <- str_split(gsub("[][]","", contrib_df$after_all_ct), ", ")
+contrib_df$ct_before_mrg <- str_split(gsub("[][]","", contrib_df$before_mrg_ct), ", ")
+contrib_df$ct_after_mrg <- str_split(gsub("[][]","", contrib_df$after_mrg_ct), ", ")
+drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct")
+contrib_df = contrib_df[,!(names(contrib_df) %in% drop)]
+# 2 some expansion needs to happens for each project
+expand_timeseries <- function(project_row) {
+longer <- project_row |>
+pivot_longer(cols = starts_with("ct"),
+names_to = "window",
+values_to = "count") |>
+unnest(count)
+longer$observation_type <- gsub("^.*_", "", longer$window)
+longer <- ddply(longer, "observation_type", transform, week=seq(from=0, by=1, length.out=length(observation_type)))
+longer$count <- as.numeric(longer$count)
+#longer <- longer[which(longer$observation_type == "all"),]
+return(longer)
+}
+expanded_data <- expand_timeseries(contrib_df[1,])
+for (i in 2:nrow(contrib_df)){
+expanded_data <- rbind(expanded_data, expand_timeseries(contrib_df[i,]))
+}
+#filter out the windows of time that we're looking at
+window_num <- 8
+windowed_data <- expanded_data |>
+filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
+mutate(D = ifelse(week > 27, 1, 0))
+summed_data <- windowed_data |>
+filter(D==1) |>
+group_by(upstream_vcs_link) |>
+summarise_at(vars(count), list(summed_count=sum))
+#concat dataframes into central data
+contrib_pop_df <- contrib_pop_df |>
+mutate(project_name = map_chr(upstream_vcs_link, ~ {
+parts <- str_split(.x, pattern = "/")[[1]]
+if (length(parts) >= 1) {
+parts[length(parts)]
+} else {
+NA_character_
+}
+}))
+contrib_topic_df <- contrib_topic_df |>
+mutate(project_name = map_chr(filename, ~ {
+parts <- str_split(.x, pattern = "_")[[1]]
+if (length(parts) >= 1) {
+paste(head(parts, -1), collapse="_")
+} else {
+NA_character_
+}
+}))
+contrib_topics_df <- contrib_topics_df |>
+mutate(project_name = map_chr(filename, ~ {
+parts <- str_split(.x, pattern = "_")[[1]]
+if (length(parts) >= 1) {
+paste(head(parts, -1), collapse="_")
+} else {
+NA_character_
+}
+}))
+contrib_total_df <- contrib_pop_df |>
+join(contrib_topics_df, by="project_name")
+contrib_total_df <- contrib_total_df|>
+join(summed_data, by="upstream_vcs_link")
+#outcome variable that is number of commits by number of new contributors
+contrib_total_df$commit_by_contrib = contrib_total_df$summed_count * contrib_total_df$after_contrib_new
+contrib_total_df$logged_outcome = log1p(contrib_total_df$commit_by_contrib)
+#running regressions
+library(MASS)
+lm1 <- glm.nb(summed_count ~ t0 + t1 + t2 + t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+View(contrib_total_df)
+lm1 <- glm.nb(summed_count ~ t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(summed_count ~ t3 + t2 + t1, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(summed_count ~ t3 + t2 + t1 + t0, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(summed_count ~ t0 + t1 + t2 + t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- lm(summed_count ~ t0 + t1 + t2 + t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(summed_count ~ t0 + t1 + t2 + t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(summed_count ~ t1 + t2 + t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(summed_count ~ t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t1 + t2 +t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t2, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t1, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+source("~/Desktop/git/24_deb_gov/R/readme_topic_outcomes.R")
+#outcome variable that is number of commits by number of new readmeutors
+readme_total_df$commit_by_contrib = readme_total_df$summed_count *readme_total_df$after_contrib_new
+readme_total_df$logged_outcome = log1p(readme_total_df$commit_by_readme)
+#running regressions
+library(MASS)
+lm1 <- glm.nb(commit_by_readme ~ t3, data = readme_total_df)
+lm1 <- glm.nb(commit_by_contrib ~ t3, data = readme_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t0, data = readme_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t1, data = readme_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t7, data = readme_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t0+t1+t7, data = readme_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t0+t1+t2+t7, data = readme_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t0+t1+t2+t7+t3, data = readme_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t0+t1+t2+t7+t3 + t4, data = readme_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t0+t1+t2+t7+t3 +t4 + t5 + t6, data = readme_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t0+t1+t2+t7+t3 +t4 + t5, data = readme_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+source("~/Desktop/git/24_deb_gov/R/contrib_topic_outcomes.R")
+lm1 <- glm.nb(commit_by_contrib ~ t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t0+ t1+ t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t0+ t1+ t2+ t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t1+ t2+ t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t1+  t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
+lm1 <- glm.nb(commit_by_contrib ~ t2+  t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
diff --git a/R/contrib_topic_outcomes.R b/R/contrib_topic_outcomes.R
new file mode 100644
index 0000000..fdc0c97
--- /dev/null
+++ b/R/contrib_topic_outcomes.R
@@ -0,0 +1,80 @@
+
+library(stringr)
+library(plyr)
+contrib_topics_df <- read_csv("../text_analysis/contrib_file_topic_distributions.csv")
+contrib_df <- read_csv("../final_data/deb_contrib_did.csv")
+contrib_pop_df <- read_csv("../final_data/deb_contrib_pop_change.csv")
+
+#get the contribution count 
+#some preprocessing and expansion 
+col_order <- c("upstream_vcs_link", "age_in_days", "first_commit", "first_commit_dt", "event_gap", "event_date",  "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+contrib_df <- contrib_df[,col_order]
+contrib_df$ct_before_all <- str_split(gsub("[][]","", contrib_df$before_all_ct), ", ")
+contrib_df$ct_after_all <- str_split(gsub("[][]","", contrib_df$after_all_ct), ", ")
+contrib_df$ct_before_mrg <- str_split(gsub("[][]","", contrib_df$before_mrg_ct), ", ")
+contrib_df$ct_after_mrg <- str_split(gsub("[][]","", contrib_df$after_mrg_ct), ", ")
+drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct")
+contrib_df = contrib_df[,!(names(contrib_df) %in% drop)]
+# 2 some expansion needs to happens for each project 
+expand_timeseries <- function(project_row) {
+  longer <- project_row |> 
+    pivot_longer(cols = starts_with("ct"),
+                 names_to = "window",
+                 values_to = "count") |>
+    unnest(count) 
+  longer$observation_type <- gsub("^.*_", "", longer$window)
+  longer <- ddply(longer, "observation_type", transform, week=seq(from=0, by=1, length.out=length(observation_type)))
+  longer$count <- as.numeric(longer$count)
+  #longer <- longer[which(longer$observation_type == "all"),]
+  return(longer)
+}
+expanded_data <- expand_timeseries(contrib_df[1,])
+for (i in 2:nrow(contrib_df)){
+  expanded_data <- rbind(expanded_data, expand_timeseries(contrib_df[i,]))
+}
+#filter out the windows of time that we're looking at
+window_num <- 8
+windowed_data <- expanded_data |>
+  filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
+  mutate(D = ifelse(week > 27, 1, 0))
+
+summed_data <- windowed_data |>
+  filter(D==1) |>
+  group_by(upstream_vcs_link) |>
+  summarise_at(vars(count), list(summed_count=sum))
+
+#concat dataframes into central data
+contrib_pop_df <- contrib_pop_df |>
+  mutate(project_name = map_chr(upstream_vcs_link, ~ {
+    parts <- str_split(.x, pattern = "/")[[1]]
+    if (length(parts) >= 1) {
+      parts[length(parts)]  
+    } else {
+      NA_character_
+    }
+  }))
+
+contrib_topics_df <- contrib_topics_df |>
+  mutate(project_name = map_chr(filename, ~ {
+    parts <- str_split(.x, pattern = "_")[[1]]
+    if (length(parts) >= 1) {
+      paste(head(parts, -1), collapse="_")
+    } else {
+      NA_character_
+    }
+  }))
+
+contrib_total_df <- contrib_pop_df |>
+  join(contrib_topics_df, by="project_name") 
+
+contrib_total_df <- contrib_total_df|>
+  join(summed_data, by="upstream_vcs_link")
+
+#outcome variable that is number of commits by number of new contributors
+contrib_total_df$commit_by_contrib = contrib_total_df$summed_count * contrib_total_df$after_contrib_new
+contrib_total_df$logged_outcome = log1p(contrib_total_df$commit_by_contrib)
+#running regressions 
+library(MASS)
+lm1 <- glm.nb(commit_by_contrib ~ t2+  t3, data = contrib_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)
diff --git a/R/readme_docChar_outcomes.R b/R/readme_docChar_outcomes.R
index b9451c9..bf2e4b8 100644
--- a/R/readme_docChar_outcomes.R
+++ b/R/readme_docChar_outcomes.R
@@ -99,3 +99,5 @@ library(MASS)
 lm1 <- glm.nb(logged_outcome~ reading_time + linsear_write_formula + flesch_reading_ease + mcalpine_eflaw + word_count, data = readme_total_df)
 qqnorm(residuals(lm1))
 summary(lm1)
+
+
diff --git a/R/readme_topic_outcomes.R b/R/readme_topic_outcomes.R
new file mode 100644
index 0000000..1d1882d
--- /dev/null
+++ b/R/readme_topic_outcomes.R
@@ -0,0 +1,80 @@
+
+library(stringr)
+library(plyr)
+readme_topics_df <- read_csv("../text_analysis/readme_file_topic_distributions.csv")
+readme_df <- read_csv("../final_data/deb_readme_did.csv")
+readme_pop_df <- read_csv("../final_data/deb_readme_pop_change.csv")
+
+#get the readmeution count 
+#some preprocessing and expansion 
+col_order <- c("upstream_vcs_link", "age_in_days", "first_commit", "first_commit_dt", "event_gap", "event_date",  "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+readme_df <- readme_df[,col_order]
+readme_df$ct_before_all <- str_split(gsub("[][]","", readme_df$before_all_ct), ", ")
+readme_df$ct_after_all <- str_split(gsub("[][]","", readme_df$after_all_ct), ", ")
+readme_df$ct_before_mrg <- str_split(gsub("[][]","", readme_df$before_mrg_ct), ", ")
+readme_df$ct_after_mrg <- str_split(gsub("[][]","", readme_df$after_mrg_ct), ", ")
+drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct")
+readme_df = readme_df[,!(names(readme_df) %in% drop)]
+# 2 some expansion needs to happens for each project 
+expand_timeseries <- function(project_row) {
+  longer <- project_row |> 
+    pivot_longer(cols = starts_with("ct"),
+                 names_to = "window",
+                 values_to = "count") |>
+    unnest(count) 
+  longer$observation_type <- gsub("^.*_", "", longer$window)
+  longer <- ddply(longer, "observation_type", transform, week=seq(from=0, by=1, length.out=length(observation_type)))
+  longer$count <- as.numeric(longer$count)
+  #longer <- longer[which(longer$observation_type == "all"),]
+  return(longer)
+}
+expanded_data <- expand_timeseries(readme_df[1,])
+for (i in 2:nrow(readme_df)){
+  expanded_data <- rbind(expanded_data, expand_timeseries(readme_df[i,]))
+}
+#filter out the windows of time that we're looking at
+window_num <- 8
+windowed_data <- expanded_data |>
+  filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
+  mutate(D = ifelse(week > 27, 1, 0))
+
+summed_data <- windowed_data |>
+  filter(D==1) |>
+  group_by(upstream_vcs_link) |>
+  summarise_at(vars(count), list(summed_count=sum))
+
+#concat dataframes into central data
+readme_pop_df <- readme_pop_df |>
+  mutate(project_name = map_chr(upstream_vcs_link, ~ {
+    parts <- str_split(.x, pattern = "/")[[1]]
+    if (length(parts) >= 1) {
+      parts[length(parts)]  
+    } else {
+      NA_character_
+    }
+  }))
+
+readme_topics_df <- readme_topics_df |>
+  mutate(project_name = map_chr(filename, ~ {
+    parts <- str_split(.x, pattern = "_")[[1]]
+    if (length(parts) >= 1) {
+      paste(head(parts, -1), collapse="_")
+    } else {
+      NA_character_
+    }
+  }))
+
+readme_total_df <- readme_pop_df |>
+  join(readme_topics_df, by="project_name") 
+
+readme_total_df <- readme_total_df|>
+  join(summed_data, by="upstream_vcs_link")
+
+#outcome variable that is number of commits by number of new readmeutors
+readme_total_df$commit_by_contrib = readme_total_df$summed_count *readme_total_df$after_contrib_new
+readme_total_df$logged_outcome = log1p(readme_total_df$commit_by_readme)
+#running regressions 
+library(MASS)
+lm1 <- glm.nb(commit_by_contrib ~ t0+t1+t2+t7+t3 +t4 + t5, data = readme_total_df)
+qqnorm(residuals(lm1))
+summary(lm1)