fit models to subset data

110124_supp_analysis/110124_supp_analysis.Rproj

@@ -0,0 +1,13 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX

110124_supp_analysis/contrib_supp_analysis.r

@@ -1,7 +1,7 @@
-#library(tidyverse)
-#library(plyr)
+library(tidyverse)
+library(plyr)
 
-contrib_df <- read_csv("110124_contrib_strict_subset.csv")
+contrib_df <- read_csv("110124_contrib_length_subset.csv")
 #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]
@@ -43,9 +43,10 @@ mrg_actions_data <- windowed_data[which(windowed_data$observation_type == "mrg")
 all_actions_data$logged_count <- log(all_actions_data$count)
 all_actions_data$log1p_count <- log1p(all_actions_data$count)
 
-#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)
-#saveRDS(all_gmodel, "0711_contrib_all_01.rda")
+all_gmodel <- glmer.nb(count ~ D * week_offset  + (D * week_offset | upstream_vcs_link),
+              control=glmerControl(optimizer="bobyqa",
+                                           optCtrl=list(maxfun=2e5)), nAGQ=0, data=all_actions_data)
+summary(all_gmodel)
+saveRDS(all_gmodel, "110224_contrib_length_subset.rda")
 
 #all_residuals <- residuals(all_gmodel)

110124_supp_analysis/readme_supp_analysis.R

@@ -1,10 +1,6 @@
-library(readr)
+library(tidyverse)
 library(plyr)
-library(lme4)
-library(stringr)
-library(tidyr)
-
-readme_df <- read_csv("110124_supp_analysis/110124_readme_strict_subset.csv")
+readme_df <- read_csv("110124_readme_strict_subset.csv")
 
 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]
@@ -58,3 +54,13 @@ var(all_actions_data$count)
 mean (all_actions_data$count) 
 sd (all_actions_data$count)
 median(all_actions_data$count) 
+
+library(lme4)
+all_log1p_gmodel <- glmer.nb(log1p_count ~ D * week_offset + (D * week_offset | upstream_vcs_link), data=all_actions_data, nAGQ=1,  control=glmerControl(optimizer="bobyqa", optCtrl=list(maxfun=1e5)))
+
+summary(all_log1p_gmodel)
+saveRDS(all_log1p_gmodel, "110224_log1p_readme_subset.rda")
+
+all_gmodel <- glmer.nb(count ~ D * week_offset + (D * week_offset | upstream_vcs_link), data=all_actions_data, nAGQ=1,  control=glmerControl(optimizer="bobyqa", optCtrl=list(maxfun=1e5)))
+summary(all_gmodel)
+saveRDS(all_gmodel, "110224_readme_subset.rda")