updating scripts with camera ready information

12825_revision/intermediary_script.py

@@ -8,10 +8,28 @@ import pandas as pd
 import datetime
 import argparse
 
+'''
+RUNNING INSTRUCTIONS:
+[1] set up tmux environment
+[2] edit this file where marked "FIX BELOW"
+[3] install pip packages
+[4] in your tmux environment, run the following three commands
+    - os.environ['GIT_SSH_COMMAND'] = 'ssh -o StrictHostKeyChecking=no'
+    - os.environ['GIT_ASKPASS'] = 'false'
+    - os.environ['GIT_TERMINAL_PROMPT'] = '0'
+[5] in tmux, run the script as follows with your START and STOP values
+    - python3 intermediary_script.py --start_index START --stop_index STOP
+[6] the password handling is imperfect, so I would appreciate if you could check on the script every so often in case anything hangs
+
+THANK YOU VERY MUCH - matt
+'''
+
+#FIX BELOW: temp_dir is where the repositories will be temporarily cloned to, if you are worried about space, specify here
 temp_dir = "/data/users/mgaughan/tmp3/"
 cst = datetime.timezone(datetime.timedelta(hours=-6))
 from_date = datetime.datetime(1970, 1, 1, 12, 00, 00, tzinfo=cst)
 to_date = datetime.datetime(2024, 3, 16, 12, 00, 00, tzinfo=cst)
+#FIX BELOW: this is where the commit data will be stored, the below parent directory needs to contain the subdirs contributing_commit_data and readme_commit_data within them
 COMMIT_SAVE_PREFIX = "/data/users/mgaughan/kkex/012825_cam_revision_main/"
 
 def temp_clone(vcs_link, temp_location):
@@ -126,9 +144,9 @@ def for_all_files(start_index, stop_index):
         lines = [line for line in file]
         for row in tqdm(csv.reader(lines), total=len(lines)):
             index += 1
-            #time.sleep(5)
             if index < start_index:
                 continue
+            time.sleep(4)
             if row[0] == "":
                 empty_row += 1
                 continue
@@ -165,7 +183,7 @@ def for_all_files(start_index, stop_index):
                     print(f'inside cloning error: {e}')
                     raise ValueError(e)
                 os.chdir(temp_repo_path)
-                os.system(f"git checkout `git rev-list -n 1 --before='2024-03-16 12:00:00' master`")
+                os.system(f"git checkout `git rev-list -n 1 --before='2024-03-16 12:00:00'`")
                 os.chdir(cwd)
                 has_readme_bool, has_contributing_bool = False, False
                 for filename in os.listdir(temp_repo_path):
@@ -221,4 +239,6 @@ if __name__ == "__main__":
     args = parser.parse_args()
     for_all_files(args.start_index, args.stop_index)
     #temp_repo, temp_repo_path = temp_clone(" https://gitlab.gnome.org/GNOME/almanah", temp_dir)
-    #delete_clone(temp_dir)
+    #delete_clone(temp_dir)
+
+    #python3 intermediary_script.py --start_index START --stop_index STOP

R/contribRDDAnalysis.R

@@ -51,10 +51,8 @@ quantile(grouped_averages$x)
 quantile(all_actions_data$before_auth_new)
 quantile(all_actions_data$after_auth_new)
 
-range(all_actions_data$log1p_count) # 0.000000 6.745236
-mean(all_actions_data$log1p_count) # 1.200043
-sd(all_actions_data$log1p_count) 
-median(all_actions_data$log1p_count) # 0.6931472
+mean(all_actions_data$count) #  8.440981
+var(all_actions_data$count) #] 542.9546
 # now for merge
 mrg_actions_data$logged_count <- log(mrg_actions_data$count)
 mrg_actions_data$log1p_count <- log1p(mrg_actions_data$count)

R/gam_plot_documents.R

@@ -68,14 +68,17 @@ doctypeColors <-
             , c("CONTRIBUTING", "README"))
 
 time_plot <- all_actions_data |>
-  ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
-  labs(x="Weekly Offset", y="Commit Count", color="Document Type") +
+  ggplot(aes(x=week_offset, y=count, color=factor(document_type))) +
+  scale_y_continuous(trans = 'log1p', labels = scales::comma) +
+  labs(x="Weekly Offset", y="Commit Count", color="Document Type: ") +
   scale_color_manual(values = doctypeColors) + 
   geom_smooth() +
   geom_vline(xintercept = 0)+
   theme_bw() +
   theme(legend.position = "top")
 time_plot
+
+ggsave(filename = "012825_gam_introduction.png", plot = time_plot, width = 8, height = 6, dpi = 500)
 #code to change the axes
 
 #scale_y_continuous(breaks = c(0, 0.5, 1.0, 1.5), 

R/readmeRDDAnalysis.R

@@ -59,8 +59,8 @@ library(lme4)
 library(optimx)
 library(lattice)
 #some more EDA to go between Poisson and neg binomial
-var(all_actions_data$log1p_count) # 1.125429
-mean (all_actions_data$log1p_count) # 0.6426873
+var(all_actions_data$count) # 268.4449
+mean (all_actions_data$count) # 3.757298
 sd(all_actions_data$log1p_count)
 median(all_actions_data$log1p_count) #0
 var(all_actions_data$count) # 268.4449