updating data with new initial commit dates

R/data_updates.R

@@ -0,0 +1,62 @@
+library(tidyverse)
+#things to get:
+# - delete old age column
+# - normal age, in date
+# - age from today in days 
+# - delta between first commit and document in days 
+#README Document updates 
+#loading in new ages
+####RDD CSV
+first_commit_df <- read_csv("../062424_did_first_commit_readme.csv")
+first_commit_df_2 <- read_csv("../062424_did_first_commit_readme_2.csv")
+first_commit_df <- rbind(first_commit_df, first_commit_df_2)
+# need to first do an rbind with this data and the second file
+# check with the head of the file/size of the file
+old_rdd_readme <- read_csv("../final_data/deb_readme_did.csv")
+old_rdd_readme <- merge(old_rdd_readme, first_commit_df, by="upstream_vcs_link")
+new_rm_data <- old_rdd_readme |>
+  mutate(first_commit_dt = as.POSIXct(first_commit, 
+                                      format = "%a %b %d %H:%M:%S %Y %z")) |>
+  mutate(age_in_days =  
+           as.numeric(
+             difftime(
+               as.POSIXct("2024-06-24 00:00:00", format = "%Y-%m-%d %H:%M:%S"),
+               first_commit_dt,
+               units = "days"))) |>
+  mutate (event_gap = 
+            as.numeric(
+              difftime(
+                as.POSIXct(event_date, format = "%Y-%m-%d %H:%M:%S"),
+                first_commit_dt, 
+                units = "days")))
+head(new_rm_data)
+new_rm_data$age_of_project = NULL
+head(new_rm_data)
+write.csv(new_rm_data, file = "../final_data/deb_readme_did_updated.csv", row.names = FALSE)
+####PopChange CSV
+old_pop_readme <- read_csv("../final_data/deb_readme_pop_change.csv")
+old_pop_readme <- merge(old_pop_readme, first_commit_df, by="upstream_vcs_link")
+new_pop_data <- old_pop_readme |>
+  mutate(first_commit_dt = as.POSIXct(first_commit, 
+                                      format = "%a %b %d %H:%M:%S %Y %z")) |>
+  mutate(age_in_days =  
+           as.numeric(
+             difftime(
+               as.POSIXct("2024-06-24 00:00:00", format = "%Y-%m-%d %H:%M:%S"),
+               first_commit_dt,
+               units = "days"))) |>
+  mutate (event_gap = 
+            as.numeric(
+              difftime(
+                as.POSIXct(event_date, format = "%Y-%m-%d %H:%M:%S"),
+                first_commit_dt, 
+                units = "days")))
+new_pop_data$age_of_project = NULL
+head(new_pop_data)
+write.csv(new_pop_data, file = "../final_data/deb_readme_pop_change_updated.csv", row.names = FALSE)
+#CONTRIBUTING Document updates 
+
+####RDD CSV
+old_rdd_contrib <- read_csv("../final_data/deb_contrib_did.csv")
+####PopChange CSV
+old_pop_contrib <- read_csv("../final_data/deb_contrib_pop_change.csv")