From 67946e6e109f667c765d4645cd7bb5964bccc620 Mon Sep 17 00:00:00 2001
From: mjgaughan <mgaughan@proton.me>
Date: Tue, 23 Apr 2024 13:59:06 -0500
Subject: [PATCH] further specification of model and formula

---
 R/readmeRDDAnalysis.R | 46 +++++++++++++++++++++++++++++++------------
 1 file changed, 33 insertions(+), 13 deletions(-)

diff --git a/R/readmeRDDAnalysis.R b/R/readmeRDDAnalysis.R
index a57e4e3..bde791e 100644
--- a/R/readmeRDDAnalysis.R
+++ b/R/readmeRDDAnalysis.R
@@ -34,10 +34,11 @@ for (i in 2:nrow(readme_df)){
 #filter out the windows of time that we're looking at
 window_num <- 8
 windowed_data <- expanded_data |>
-  filter(week >= (26 - window_num) & week <= (26 + window_num)) |>
-  mutate(D = ifelse(week > 26, 1, 0))
+  filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
+  mutate(D = ifelse(week > 27, 1, 0))
 #scale the age numbers 
 windowed_data$scaled_project_age <- scale(windowed_data$age_of_project)
+windowed_data$week_offset <- windowed_data$week - 27
 #separate out the cleaning d
 all_actions_data <- windowed_data[which(windowed_data$observation_type == "all"),]
 mrg_actions_data <- windowed_data[which(windowed_data$observation_type == "mrg"),]
@@ -54,18 +55,37 @@ qqplot(all_actions_data$count, y)
 # lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc
 library(lme4)
 # https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
-# (D |upstream_vcs_link) or (week | upstream_vcs_link)
-poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (week || upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
-summary(poisson_all_model)
-poisson_residuals <- residuals(poisson_all_model)
-qqnorm(poisson_residuals)
+#making some random data 
+sampled_data <- readme_df[sample(nrow(readme_df), 220), ]
+expanded_sample_data <- expand_timeseries(sampled_data[1,])
+for (i in 2:nrow(sampled_data)){
+  expanded_sample_data <- rbind(expanded_sample_data, expand_timeseries(sampled_data[i,]))
+}
+windowed_sample_data <- expanded_sample_data |>
+  filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
+  mutate(D = ifelse(week > 27, 1, 0))
+windowed_sample_data$scaled_project_age <- scale(windowed_sample_data$age_of_project)
+windowed_sample_data$week_offset <- windowed_sample_data$week - 27
+all_actions_sample_data <- windowed_sample_data[which(windowed_sample_data$observation_type == "all"),]
+#test model
+test_model <- lmer(count ~ D * I(week_offset) + scaled_project_age + (D * I(week_offset)|upstream_vcs_link),  data=all_actions_sample_data, REML=FALSE)
+summary(test_model)
+#plot results
+p <- ggplot(all_actions_sample_data, aes(x=week_offset, y=count, color=upstream_vcs_link), show.legend = FALSE) +
+  geom_point(size=3, show.legend = FALSE) +
+  geom_line(aes(y=predict(test_model)), show.legend = FALSE) +
+  theme_bw() 
+p
+##end of the model testing and plotting section
+all_model <- lmer(count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset)| upstream_vcs_link), data=all_actions_data, REML=FALSE)
+summary(all_model)
+all_residuals <- residuals(all_model)
+qqnorm(all_residuals)
 # for visualization, may have to run model for each project and then identify top 5 projects for RDD graphs 
-#
-# 
-poisson_mrg_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (week |upstream_vcs_link), data=mrg_actions_data, family = poisson(link = "log"))
-summary(poisson_mrg_model)
-poisson_mrg_residuals <- residuals(poisson_mrg_model)
-qqnorm(poisson_mrg_residuals)
+mrg_model <- lmer(count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset)| upstream_vcs_link), data=mrg_actions_data, REML=FALSE)
+summary(mrg_model)
+mrg_residuals <- residuals(mrg_model)
+qqnorm(mrg_residuals)
 # Performance: 
 
 library(merTools)