Add histogram plots for pairwise changed git files

Author: JohT

cypher/General_Enrichment/Add_file_name and_extension.cypher

@@ -1,10 +1,10 @@
- // Add "name", "extension" and "extensionExtended" properties to File nodes
+ // Add "name", "extension" and "extensionExtended" properties to File nodes. Supports Git:File nodes with "relativePath" property.
 
  MATCH (file:File)
- WHERE file.fileName IS NOT NULL
+ WHERE (file.fileName IS NOT NULL OR file.relativePath IS NOT NULL)
    AND file.name IS NULL // Don't override an already existing "name" property
   WITH *
-      ,file.fileName AS fileName
+      ,coalesce(file.fileName, file.relativePath) AS fileName
   WITH *
       ,last(split(fileName, '/')) AS fileNameWithoutPath
   WITH *

cypher/GitLog/Add_CHANGED_TOGETHER_WITH_relationships_to_git_files.cypher

@@ -32,9 +32,8 @@ UNWIND fileCombinations AS fileCombination
       ,count(DISTINCT commitHash)      AS updateCommitCount
       ,collect(DISTINCT commitHash)    AS updateCommitHashes
 // Deactivated: 
-// Filter out file pairs that where changed not very often together 
-// In detail: More than 0.1 per mille compared to overall commit count
-// WHERE updateCommitCount > globalUpdateCommitCount * 0.001 
+// Filter out file pairs that weren't changed very often together 
+WHERE updateCommitCount > 2
  WITH *
      ,fileCombination[0] AS firstFile
      ,fileCombination[1] AS secondFile
@@ -65,7 +64,7 @@ UNWIND fileCombinations AS fileCombination
 // Create the new relationship "CHANGED_TOGETHER_WITH" and set the property "updateCommitCount" on it
  CALL (firstFile, secondFile, updateCommitCount, updateCommitHashes, updateCommitMinConfidence, updateCommitSupport, updateCommitLift, updateCommitJaccardSimilarity) {
        MERGE (firstFile)-[pairwiseChange:CHANGED_TOGETHER_WITH]-(secondFile)
-         SET pairwiseChange.updateCommitCount             = updateCommitCount
+         SET pairwiseChange.updateCommitCount             = toInteger(updateCommitCount)
             ,pairwiseChange.updateCommitHashes            = updateCommitHashes
             ,pairwiseChange.updateCommitMinConfidence     = updateCommitMinConfidence
             ,pairwiseChange.updateCommitSupport           = updateCommitSupport

cypher/GitLog/List_git_files_that_were_changed_together_with_another_file.cypher

@@ -2,10 +2,10 @@
 
 MATCH (firstGitFile:Git&File&!Repository)-[gitChange:CHANGED_TOGETHER_WITH]-(secondGitFile:Git&File&!Repository)
 MATCH (gitRepository:Git&Repository)-[:HAS_FILE]->(firstGitFile)
-UNWIND gitChange.commitHashes AS commitHash
+UNWIND gitChange.updateCommitHashes AS commitHash
   WITH gitRepository.name + '/' + firstGitFile.relativePath AS filePath
       ,count(DISTINCT commitHash)                           AS commitCount
-      ,sum(firstGitFile.updateCommitCount)           AS fileUpdateCount
+      ,sum(firstGitFile.updateCommitCount)                  AS fileUpdateCount
   WITH *
       // Out of all the times the file was touched, how often did it co-occur with other files?
       ,CASE WHEN fileUpdateCount > 0 THEN toFloat(commitCount) / fileUpdateCount ELSE 0.0 END AS coChangeRate

cypher/GitLog/List_pairwise_changed_files.cypher

@@ -0,0 +1,21 @@
+// List pairs of files that were changed together. Requires Add_CHANGED_TOGETHER_WITH_relationships_to_git_files.cypher to run first.
+
+MATCH (firstFile:Git:File)-[pairwiseChange:CHANGED_TOGETHER_WITH]-(secondFile:Git:File)
+WHERE elementId(firstFile) < elementId(secondFile)
+ WITH *
+     ,coalesce(firstFile.relativePath, firstFile.fileName)    AS firstFileName
+     ,coalesce(secondFile.relativePath, secondFile.fileName)  AS secondFileName
+RETURN firstFileName
+      ,secondFileName
+      ,firstFile.name + '<br>' + secondFile.name              AS filePairLineBreak
+      ,firstFileName + '<br>' + secondFileName                AS filePairWithRelativePathLineBreak
+      ,firstFile.name + '↔' + secondFile.name                 AS filePair
+      ,firstFileName + '↔' + secondFileName                   AS filePairWithRelativePath
+      ,firstFile.extension                                    AS firstFileExtension
+      ,secondFile.extension                                   AS secondFileExtension
+      ,firstFile.extension + '↔' + secondFile.extension       AS fileExtensionPair
+      ,toInteger(pairwiseChange.updateCommitCount)            AS updateCommitCount
+      ,pairwiseChange.updateCommitMinConfidence               AS updateCommitMinConfidence
+      ,pairwiseChange.updateCommitSupport                     AS updateCommitSupport
+      ,pairwiseChange.updateCommitLift                        AS updateCommitLift
+      ,pairwiseChange.updateCommitJaccardSimilarity           AS updateCommitJaccardSimilarity

cypher/GitLog/List_pairwise_changed_files_with_dependencies.cypher

@@ -1,4 +1,4 @@
-// List pair of files that were changed together and that have a declared dependency between each other.
+// List pair of files that were changed together and that have a declared dependency between each other. Requires Add_CHANGED_TOGETHER_WITH_relationships_to_git_files.cypher and Add_CHANGED_TOGETHER_WITH_relationships_to_code_files.cypher to run first.
 
 MATCH (firstCodeFile:File)-[dependency:DEPENDS_ON]->(secondCodeFile:File)
 MATCH (firstCodeFile)-[pairwiseChange:CHANGED_TOGETHER_WITH]-(secondCodeFile)