rm(list=ls())
set.seed(424242) 

library(readr)
library(ggplot2)
library(tidyverse)

#primary analysis for cross-sectional community metrics 
overall_data <- read_csv('../final_data/deb_full_data.csv',show_col_types = FALSE)
octo_data <- read_csv('../final_data/deb_octo_data.csv', show_col_types = FALSE)
readme_data <- read_csv("../final_data/deb_readme_roster.csv", show_col_types = FALSE)
contributing_data <- read_csv("../final_data/deb_contribfile_roster.csv", show_col_types = FALSE)

overall_data$mmt <- (((overall_data$collaborators * 2)+ overall_data$contributors) / (overall_data$contributors + overall_data$collaborators))
mean(overall_data$mmt)
hist(overall_data$mmt, probability = TRUE)

#the basic stuff for the overall data 
overall_data$mmt <- (((overall_data$collaborators * 2)+ overall_data$contributors) / (overall_data$contributors + overall_data$collaborators))
mean(overall_data$mmt)
hist(overall_data$mmt, probability = TRUE)

#some new variables around age
#overall_data$new.age <- as.numeric(cut(overall_data$age_of_project/365, breaks=c(0,7.524197,10.323056,13.649367,17), labels=c(1,2,3,4)))
#table(overall_data$new.age)
#overall_data$new.age.factor <- as.factor(overall_data$new.age)
overall_data$scaled_age <- scale(overall_data$age_of_project)

#model
mmtmodel1 <- lm(underproduction_mean ~ mmt + scaled_age, data=overall_data)
summary(mmtmodel1)
qqnorm(residuals(mmtmodel1))

#clean octo data
octo_data <- filter(octo_data, total_contrib != 0)
# below this is the analysis for the octo data
octo_data$new.age <- as.numeric(cut(octo_data$age_of_project/365, breaks=c(0,7.524197,10.323056,13.649367,17), labels=c(1,2,3,4)))
table(octo_data$new.age)
octo_data$new.age.factor <- as.factor(octo_data$new.age)
octo_data$scaled_age <- scale(octo_data$age_of_project)

octo_data$mmt <- (((octo_data$collaborators * 2)+ octo_data$contributors) / (octo_data$contributors + octo_data$collaborators))
mean(octo_data$mmt)
hist(octo_data$mmt)
head(octo_data)

#getting the mmt-equivalent for both issue activity as well as wiki contrib activity
octo_data$issue_mmt <- ((octo_data$issue_contrib_count * 2) + (octo_data$total_contrib - octo_data$issue_contrib_count)) / (octo_data$total_contrib)
octo_data$sqrt_issue_mmt <- sqrt(octo_data$issue_mmt)
#right skewed data, need to transform
octo_data$wiki_mmt <- ((octo_data$wiki_contrib_count * 2) + (octo_data$total_contrib - octo_data$wiki_contrib_count)) / (octo_data$total_contrib)
hist(octo_data$wiki_mmt)

#getting some of the information in about whether projects have specific files 
readme_did_roster <- read_csv("../final_data/deb_readme_did.csv", show_col_types = FALSE)
contrib_did_roster <- read_csv("../final_data/deb_contrib_did.csv", show_col_types = FALSE)
octo_data <- octo_data |>
  mutate(has_readme = as.numeric(upstream_vcs_link %in% readme_did_roster$upstream_vcs_link)) |>
  mutate(has_contrib = as.numeric(upstream_vcs_link %in% contrib_did_roster$upstream_vcs_link))
overall_data <- overall_data |>
  mutate(has_readme = as.numeric(upstream_vcs_link %in% readme_did_roster$upstream_vcs_link)) |>
  mutate(has_contrib = as.numeric(upstream_vcs_link %in% contrib_did_roster$upstream_vcs_link))


#below are the models for the octo data, there should be analysis for each one
octo_mmtmodel1 <- lm(underproduction_mean ~ mmt + scaled_age + has_readme + has_contrib, data=octo_data)
summary(octo_mmtmodel1)

issue_mmtmodel1 <- lm(underproduction_mean ~ issue_mmt + scaled_age + has_readme + has_contrib, data=octo_data)
summary(issue_mmtmodel1)
qqnorm(residuals(issue_mmtmodel1))

wiki_mmtmodel1 <- lm(underproduction_mean ~ wiki_mmt + scaled_age + has_readme + has_contrib, data=octo_data)
summary(wiki_mmtmodel1)
qqnorm(residuals(wiki_mmtmodel1))

#these next three are looking at mmt as an outcome of other factors
mmt_outcome_model <- lm(mmt ~ scaled_age + as.factor(has_readme) + as.factor(has_contrib), data = octo_data)
summary(mmt_outcome_model)

all_mmt_outcome_model <- lm(mmt ~ scaled_age + as.factor(has_readme) + as.factor(has_contrib), data = overall_data)
summary(all_mmt_outcome_model)

govdoc_issuesmmt <- lm(issue_mmt ~ scaled_age + as.factor(has_readme) + as.factor(has_contrib), data=octo_data)
summary(govdoc_issuesmmt)

library(texreg) #my little "lib"

texreg(list(octo_mmtmodel1, issue_mmtmodel1, wiki_mmtmodel1), stars=NULL, digits=2,
       custom.model.names=c( 'M1: MMT','M2: issue contrib.', 'M3: wiki contrib.'  ), 
       custom.coef.names=c('(Intercept)', 'MMT', 'scaled_age', 'has readme', 'has contrib', 'Issue MMT', 'Wiki MMT'), 
       use.packages=FALSE, table=FALSE, ci.force = TRUE)

#below here is the analysis for the readme.md data 
cor.test(octo_data$mmt, octo_data$has_readme)
cor.test(octo_data$mmt, octo_data$has_contrib)
cor.test(octo_data$has_readme, octo_data$has_contrib)

#using the groupings and estimates from the ranef coefficients from D as data
#pulling in the group data for the ranef coefficients 
rm_grouping <- read_csv('051224_readme_grouped.csv',show_col_types = FALSE)
contrib_grouping <- read_csv('051224_contrib_grouped.csv', show_col_types = FALSE)
rm_grouping <- rm_grouping |>
  rename(upstream_vcs_link = level)|>
  mutate(factored_group = as.factor(ranef_grouping))
contrib_grouping <- contrib_grouping |>
  rename(upstream_vcs_link = level) |>
  mutate(factored_group = as.factor(ranef_grouping))
grouped_rm <- left_join(rm_grouping, overall_data, by="upstream_vcs_link")
grouped_contrib <- left_join(contrib_grouping, overall_data, by="upstream_vcs_link")
rm_did <- read_csv('../final_data/deb_readme_did.csv',show_col_types = FALSE)
contrib_did <- read_csv('../final_data/deb_contrib_did.csv', show_col_types = FALSE)
grouped_rm <- left_join(grouped_rm, rm_did, by="upstream_vcs_link")
grouped_contrib <- left_join(grouped_contrib, contrib_did, by="upstream_vcs_link")
# also looking at how long each project has had a specific governance document
# calculate in terms of July 6, 2020 (when underproduction metrics were collected)
library(chron)
dtparts = t(as.data.frame(strsplit(as.character(grouped_rm$event_date),' ')))
thetimes = chron(dates=dtparts[,1],times=dtparts[,2], format=c('y-m-d','h:m:s'))
typeof(thetimes)
how_long_has_file <- difftime(as.Date("2020-07-06"), as.Date(grouped_rm$event_date), units = "days")
grouped_rm <- grouped_rm |>
  mutate(formatted_event_time = chron(dates=dtparts[,1],times=dtparts[,2], format=c('y-m-d','h:m:s'))) |>
  mutate(event_delta = difftime(as.chron("2020-07-06"), formatted_event_time, units = "days"))
#now doing it for the contrib_data 
contrib_dtparts = t(as.data.frame(strsplit(as.character(grouped_contrib$event_date),' ')))
grouped_contrib <- grouped_contrib |>
  mutate(formatted_event_time = chron(dates=contrib_dtparts[,1],times=contrib_dtparts[,2], format=c('y-m-d','h:m:s'))) |>
  mutate(event_delta = difftime(as.chron("2020-07-06"), formatted_event_time, units = "days"))
#test with linear model, there should be an interaction between how long the project has had a document and its grouping, no?
grouping_model_rm <- lm(underproduction_mean ~ event_delta*factored_group + mmt + scaled_age, data=grouped_rm)
summary(grouping_model_rm)
qqnorm(residuals(grouping_model_rm))
grouping_model_contrib <- lm(underproduction_mean ~ event_delta*factored_group + mmt + scaled_age, data=grouped_contrib)
summary(grouping_model_contrib)
qqnorm(residuals(grouping_model_contrib))