In sailuh/kaiaulu: Kaiaulu

Introduction

rm(list = ls())
seed <- 1
set.seed(seed)

require(kaiaulu)
require(visNetwork)
require(reactable)
require(data.table)
require(igraph)
require(yaml)
require(stringi)
require(knitr)

Project Configuration File

tool <- parse_config("../tools.yml")
conf <- parse_config("../conf/kaiaulu.yml")

# 3rd Party Tools
perceval_path <- get_tool_project("perceval", tool)
utags_path <- get_tool_project("utags", tool)

# Ctags Line Types
kinds <- get_uctags_line_types(conf)

# Local Git Repo Folder Path
git_repo_path <- get_git_repo_path(conf)

# File Filters
file_extensions <- get_file_extensions(conf)
substring_filepath <- get_substring_filepath(conf)

Construct Collaboration Network

project_git <- parse_gitlog(perceval_path,git_repo_path)
#project_git <- parse_gitlog(perceval_path,git_repo_path,save_path)
#project_git <- readRDS(save_path)

Filter files

project_git <- project_git  %>%
  filter_by_file_extension(file_extensions,"file_pathname")  %>% 
  filter_by_filepath_substring(substring_filepath,"file_pathname")

project_git$author_datetimetz <- as.POSIXct(project_git$author_datetimetz,
                                              format = "%a %b %d %H:%M:%S %Y %z", tz = "UTC")
project_git$author_datetimetz <- as.POSIXct(project_git$committer_datetimetz,
                                              format = "%a %b %d %H:%M:%S %Y %z", tz = "UTC")

Entity analysis requires a much longer time to process than file analysis, and reason why the associated function provides a progress bar. In the interest of this demo, we use only 500 changes of the git log, but time slices could also be used.

#project_git_slice <- project_git[author_datetimetz >= as.POSIXct("2019-01-01", format = "%Y-%m-%d",tz = "UTC") & author_datetimetz < as.POSIXct("2019-12-31", format = "%Y-%m-%d",tz = "UTC")]
#project_git_slice <- head(project_git,500)

changed_entities <- parse_gitlog_entity(git_repo_path,utags_path,project_git,kinds,progress_bar = TRUE)
##changed_entities <- readRDS("~/Desktop/apr_full_gitlog_filtered_by_last_file_change.rds")
kable(head(changed_entities))

Identity Match

project_log <- list(project_git=changed_entities)
project_log <- identity_match(project_log,
                              name_column = c("author_name_email"),
                              assign_exact_identity,
                              use_name_only=TRUE,
                              label = "raw_name"
                              )
id_project_git <- project_log[["project_git"]]

Visualizing the Git Log

Authors, Committers, Entities and Commits

Author-Entity Network

project_collaboration_network <- transform_gitlog_to_entity_bipartite_network(last(id_project_git,
                                                                                   1000),
                                                                              mode = "author-entity")

project_collaboration_network <- igraph::graph_from_data_frame(d=project_collaboration_network[["edgelist"]], 
                      directed = TRUE, 
                      vertices = project_collaboration_network[["nodes"]])

visIgraph(project_collaboration_network,randomSeed = 1)

project_commit_network <- transform_gitlog_to_entity_bipartite_network(id_project_git,
                                                                              mode ="commit-entity")
plot_project_commit_network <- igraph::graph_from_data_frame(d=project_commit_network[["edgelist"]], 
                      directed = TRUE, 
                      vertices = project_commit_network[["nodes"]])
visIgraph(plot_project_commit_network,randomSeed = 1)

Bipartite Projections

co_change_network <- bipartite_graph_projection(project_commit_network,
                                                mode = FALSE,
                                                weight_scheme_function = weight_scheme_sum_edges)

plot_co_change_network <- igraph::graph_from_data_frame(d=co_change_network[["edgelist"]], 
                      directed = FALSE, 
                      vertices = co_change_network[["nodes"]])

#co_change_network <- igraph::bipartite_projection(project_commit_network,
#                                          multiplicity = TRUE,
#                                          which = FALSE) # FALSE is the file projection
visIgraph(plot_co_change_network,randomSeed = 1)

## Co-Change adjacency matrix 


table_co_change_network <- igraph::bipartite_projection(plot_project_commit_network,
                                          multiplicity = TRUE,
                                          which = FALSE) # FALSE is the file projection

co_change_matrix <- as_adjacency_matrix(table_co_change_network,attr = "weight",sparse = F)
kable(co_change_matrix[1:10,1:10])

#co_change_matrix <- as_adjacency_matrix(co_change_network,attr = "weight",sparse = F)
#kable(co_change_matrix[1:10,1:10])

project_collaboration_network <- transform_gitlog_to_entity_bipartite_network(id_project_git,
                                                                              mode = "author-entity")

#plot_project_collaboration_network <- igraph::graph_from_data_frame(d=project_collaboration_network[["edgelist"]], 
#                      directed = TRUE, 
#                      vertices = project_collaboration_network[["nodes"]])

#author_network <- igraph::bipartite_projection(project_collaboration_network,
#                                          multiplicity = TRUE,
#                                          which = TRUE) # FALSE is the file projection

author_network <- bipartite_graph_projection(project_collaboration_network,
                                                mode = TRUE,
                                                weight_scheme_function = weight_scheme_sum_edges)

plot_author_network <- igraph::graph_from_data_frame(d=author_network[["edgelist"]], 
                      directed = FALSE, 
                      vertices = author_network[["nodes"]])

visIgraph(plot_author_network,randomSeed = 1)

Temporal Networks

project_temporal_collaboration_network <- transform_gitlog_to_entity_temporal_network(id_project_git,mode = "author",lag = "all_lag",weight_scheme_function = weight_scheme_cum_temporal)
project_temporal_collaboration_network <- igraph::graph_from_data_frame(d=project_temporal_collaboration_network[["edgelist"]], 
                      directed = TRUE, 
                      vertices = project_temporal_collaboration_network[["nodes"]])
visIgraph(project_temporal_collaboration_network,randomSeed = 1)