def experiemnt_three(dbFileName, meanFlag, outputStrParam, clusterFlag):
from sklearn import cluster
import plotter
clusteringType = None
if clusterFlag:
clusteringType = cluster.KMeans(n_clusters=13)
else:
clusteringType = cluster.AgglomerativeClustering(n_clusters=13)
print "Performing experiemnt # 3: Clustering score into two clusters "
versionAndCodeQualityDict = DEFT.getValuesFrom_CodingStandard(dbFileName)
sanitizedVersions = sanityCheck.getCodeQualityofVersions(versionAndCodeQualityDict, meanFlag)
sanitizedVersions_CQ = sanitizedVersions
# print "Sanitized versions that will be used in study ", len(sanitizedVersions)
# print "Sanitized versions ..." , sanitizedVersions
NonZero_sanitizedVersionsWithScore = sanityCheck.getNonZeroVulnerbailityScoreOfSelectedVersions(sanitizedVersions)
# print "zzzz", len(NonZero_sanitizedVersionsWithScore)
### dyumping scores ...
brokenDict = utility.getVScoreList(NonZero_sanitizedVersionsWithScore)
onlyTheNonZeroSanitizedVersionIDs, onlyTheNonZeroSanitizedVScores = brokenDict[0], brokenDict[1]
# print "lalalaa ", onlyTheNonZeroSanitizedVScores
# strOfScoresToDump=""
# for elem in onlyTheNonZeroSanitizedVScores:
# strOfScoresToDump = strOfScoresToDump + str(elem) + "," + "\n"
###
# IO_.writeStrToFile("scores_for_clustering_measure.csv", strOfScoresToDump)
reshapedNonZerSanitizedScores = np.reshape(onlyTheNonZeroSanitizedVScores, (-1, 1))
clusteringType.fit(reshapedNonZerSanitizedScores)
labelsFroVersions = clusteringType.labels_
if clusterFlag:
centroids = clusteringType.cluster_centers_
print "And the centroids are .... ", centroids
NonZer_Santized_versionDictWithLabels = utility.clusterByKmeansLabel(
onlyTheNonZeroSanitizedVersionIDs, labelsFroVersions
)
##### plotting clusters start
# low_cluster_y, high_cluster_y = utility.plotClusterByLabel( onlyTheNonZeroSanitizedVersionIDs , labelsFroVersions, NonZero_sanitizedVersionsWithScore)
# low_cluster_x = [ 22.35294118 for x in low_cluster_y]
# hig_cluster_x = [ 50.82030058 for x in high_cluster_y]
# plotter.createClusterPlots(low_cluster_x, low_cluster_y, hig_cluster_x, high_cluster_y)
##### plottign clusters end
else:
print "No centroids for Aggolomerative clustering"
NonZer_Santized_versionDictWithLabels = utility.clusterByAggoloLabel(
onlyTheNonZeroSanitizedVersionIDs, labelsFroVersions
)
print "And the labels are .... "
print len(labelsFroVersions)
cluster_labels = clusteringType.fit_predict(reshapedNonZerSanitizedScores)
silhouette_avg = silhouette_score(reshapedNonZerSanitizedScores, cluster_labels)
print "Silhouette average---> ", silhouette_avg
##############################
themegaFile_All = outputStrParam + "_" + "culsterified_non_zero_all-CQ-HL.csv"
IO_.dumpIntoClusterifiedFile(themegaFile_All, sanitizedVersions_CQ, NonZer_Santized_versionDictWithLabels, False)
def experiemnt_correlation(dbFileName, meanFlag, outputStrParam, clusterFlag):
import correlation
from sklearn import cluster
clusteringType = None
if clusterFlag:
clusteringType = cluster.KMeans(n_clusters=2)
else:
clusteringType = cluster.AgglomerativeClustering(n_clusters=2)
print "Performing experiemnt # Correlation: Clustering score into two clusters "
versionAndCodeQualityDict = DEFT.getValuesFrom_CodingStandard(dbFileName)
sanitizedVersions = sanityCheck.getCodeQualityofVersions(
versionAndCodeQualityDict, meanFlag)
sanitizedVersions_CQ = sanitizedVersions
#print "Sanitized versions that will be used in study ", len(sanitizedVersions)
#print "Sanitized versions ..." , sanitizedVersions
NonZero_sanitizedVersionsWithScore = sanityCheck.getNonZeroVulnerbailityScoreOfSelectedVersions(
sanitizedVersions)
#print "zzzz", len(NonZero_sanitizedVersionsWithScore)
brokenDict = utility.getVScoreList(NonZero_sanitizedVersionsWithScore)
onlyTheNonZeroSanitizedVersionIDs, onlyTheNonZeroSanitizedVScores = brokenDict[
0], brokenDict[1]
#print "lalalaa ", onlyTheNonZeroSanitizedVScores
reshapedNonZerSanitizedScores = np.reshape(onlyTheNonZeroSanitizedVScores,
(-1, 1))
clusteringType.fit(reshapedNonZerSanitizedScores)
labelsFroVersions = clusteringType.labels_
if clusterFlag:
centroids = clusteringType.cluster_centers_
print "And the centroids are .... ", centroids
NonZer_Santized_versionDictWithLabels = utility.clusterByKmeansLabel(
onlyTheNonZeroSanitizedVersionIDs, labelsFroVersions)
else:
print "No centroids for Aggolomerative clustering"
NonZer_Santized_versionDictWithLabels = utility.clusterByAggoloLabel(
onlyTheNonZeroSanitizedVersionIDs, labelsFroVersions)
#print "And the labels are .... "
#print labelsFroVersions
#print "versionDictWithLabels"
#print len(versionDictWithLabels)
onlyHighV_Scores_Dict = utility.getH_Scores_ForCorr(
NonZer_Santized_versionDictWithLabels,
NonZero_sanitizedVersionsWithScore)
correlation.performCorrBasedOnIndiMetrics(onlyHighV_Scores_Dict,
sanitizedVersions_CQ)
def experiemnt_correlation(dbFileName, meanFlag, outputStrParam, clusterFlag):
import correlation
from sklearn import cluster
clusteringType = None
if clusterFlag:
clusteringType = cluster.KMeans(n_clusters=2)
else:
clusteringType = cluster.AgglomerativeClustering(n_clusters=2)
print "Performing experiemnt # Correlation: Clustering score into two clusters "
versionAndCodeQualityDict = DEFT.getValuesFrom_CodingStandard(dbFileName)
sanitizedVersions = sanityCheck.getCodeQualityofVersions(versionAndCodeQualityDict, meanFlag)
sanitizedVersions_CQ = sanitizedVersions
# print "Sanitized versions that will be used in study ", len(sanitizedVersions)
# print "Sanitized versions ..." , sanitizedVersions
NonZero_sanitizedVersionsWithScore = sanityCheck.getNonZeroVulnerbailityScoreOfSelectedVersions(sanitizedVersions)
# print "zzzz", len(NonZero_sanitizedVersionsWithScore)
brokenDict = utility.getVScoreList(NonZero_sanitizedVersionsWithScore)
onlyTheNonZeroSanitizedVersionIDs, onlyTheNonZeroSanitizedVScores = brokenDict[0], brokenDict[1]
# print "lalalaa ", onlyTheNonZeroSanitizedVScores
reshapedNonZerSanitizedScores = np.reshape(onlyTheNonZeroSanitizedVScores, (-1, 1))
clusteringType.fit(reshapedNonZerSanitizedScores)
labelsFroVersions = clusteringType.labels_
if clusterFlag:
centroids = clusteringType.cluster_centers_
print "And the centroids are .... ", centroids
NonZer_Santized_versionDictWithLabels = utility.clusterByKmeansLabel(
onlyTheNonZeroSanitizedVersionIDs, labelsFroVersions
)
else:
print "No centroids for Aggolomerative clustering"
NonZer_Santized_versionDictWithLabels = utility.clusterByAggoloLabel(
onlyTheNonZeroSanitizedVersionIDs, labelsFroVersions
)
# print "And the labels are .... "
# print labelsFroVersions
# print "versionDictWithLabels"
# print len(versionDictWithLabels)
onlyHighV_Scores_Dict = utility.getH_Scores_ForCorr(
NonZer_Santized_versionDictWithLabels, NonZero_sanitizedVersionsWithScore
)
correlation.performCorrBasedOnIndiMetrics(onlyHighV_Scores_Dict, sanitizedVersions_CQ)
def experiemnt_three(dbFileName, meanFlag, outputStrParam, clusterFlag):
from sklearn import cluster
import plotter
clusteringType = None
if clusterFlag:
clusteringType = cluster.KMeans(n_clusters=13)
else:
clusteringType = cluster.AgglomerativeClustering(n_clusters=13)
print "Performing experiemnt # 3: Clustering score into two clusters "
versionAndCodeQualityDict = DEFT.getValuesFrom_CodingStandard(dbFileName)
sanitizedVersions = sanityCheck.getCodeQualityofVersions(
versionAndCodeQualityDict, meanFlag)
sanitizedVersions_CQ = sanitizedVersions
#print "Sanitized versions that will be used in study ", len(sanitizedVersions)
#print "Sanitized versions ..." , sanitizedVersions
NonZero_sanitizedVersionsWithScore = sanityCheck.getNonZeroVulnerbailityScoreOfSelectedVersions(
sanitizedVersions)
#print "zzzz", len(NonZero_sanitizedVersionsWithScore)
### dyumping scores ...
brokenDict = utility.getVScoreList(NonZero_sanitizedVersionsWithScore)
onlyTheNonZeroSanitizedVersionIDs, onlyTheNonZeroSanitizedVScores = brokenDict[
0], brokenDict[1]
#print "lalalaa ", onlyTheNonZeroSanitizedVScores
#strOfScoresToDump=""
#for elem in onlyTheNonZeroSanitizedVScores:
# strOfScoresToDump = strOfScoresToDump + str(elem) + "," + "\n"
###
#IO_.writeStrToFile("scores_for_clustering_measure.csv", strOfScoresToDump)
reshapedNonZerSanitizedScores = np.reshape(onlyTheNonZeroSanitizedVScores,
(-1, 1))
clusteringType.fit(reshapedNonZerSanitizedScores)
labelsFroVersions = clusteringType.labels_
if clusterFlag:
centroids = clusteringType.cluster_centers_
print "And the centroids are .... ", centroids
NonZer_Santized_versionDictWithLabels = utility.clusterByKmeansLabel(
onlyTheNonZeroSanitizedVersionIDs, labelsFroVersions)
##### plotting clusters start
#low_cluster_y, high_cluster_y = utility.plotClusterByLabel( onlyTheNonZeroSanitizedVersionIDs , labelsFroVersions, NonZero_sanitizedVersionsWithScore)
#low_cluster_x = [ 22.35294118 for x in low_cluster_y]
#hig_cluster_x = [ 50.82030058 for x in high_cluster_y]
#plotter.createClusterPlots(low_cluster_x, low_cluster_y, hig_cluster_x, high_cluster_y)
##### plottign clusters end
else:
print "No centroids for Aggolomerative clustering"
NonZer_Santized_versionDictWithLabels = utility.clusterByAggoloLabel(
onlyTheNonZeroSanitizedVersionIDs, labelsFroVersions)
print "And the labels are .... "
print len(labelsFroVersions)
cluster_labels = clusteringType.fit_predict(reshapedNonZerSanitizedScores)
silhouette_avg = silhouette_score(reshapedNonZerSanitizedScores,
cluster_labels)
print "Silhouette average---> ", silhouette_avg
##############################
themegaFile_All = outputStrParam + "_" + "culsterified_non_zero_all-CQ-HL.csv"
IO_.dumpIntoClusterifiedFile(themegaFile_All, sanitizedVersions_CQ,
NonZer_Santized_versionDictWithLabels, False)
