def getTrain4Test(self, indexCV=0):
dataTrain = [[], [], []]
dataValid = [[], [], []]
with open(
os.path.join(UtilPath.Datasets(), self.project,
self.typeDataset, self.release4Test,
"train" + str(indexCV) + ".csv")) as f:
train = csv.reader(f)
for i, row in enumerate(train):
dataTrain[0].append(row[0])
dataTrain[1].append([float(x) for x in row[2:]])
dataTrain[2].append(int(row[1]))
dataTrain[1] = np.array(dataTrain[1])
dataTrain[2] = np.array(dataTrain[2])
print(dataTrain[1].shape)
with open(
os.path.join(UtilPath.Datasets(), self.project,
self.typeDataset, self.release4Test,
"valid" + str(indexCV) + ".csv")) as f:
valid = csv.reader(f)
for i, row in enumerate(valid):
dataValid[0].append(row[0])
dataValid[1].append([float(x) for x in row[2:]])
dataValid[2].append(int(row[1]))
dataValid[1] = np.array(dataValid[1])
dataValid[2] = np.array(dataValid[2])
print(dataValid[1].shape)
return np.concatenate([dataTrain[1], dataValid[1]
]), np.concatenate([dataTrain[2], dataValid[2]],
0)
def setUp(self):
name = "cassandra20200615"
mode = "train"
repositories = [{
"name": "cassandra20200615",
"url": "",
"CommitTarget": "",
"filterFile": "",
"codeIssueJira": "",
"projectJira": ""
}]
parameters = {}
option = {
"name": name,
"mode": mode,
"repositories": repositories,
"parameters": parameters #needless when to infer.
}
option = Option(option)
self.dataset = Dataset(option.getRepositorieImproved())
self.repository = repositories[0]
print(
os.path.join(UtilPath.Test(), "testDataset",
self.repository["name"], "repository"))
self.gr = GitRepository(
os.path.join(UtilPath.Test(), "testDataset",
self.repository["name"], "repository"))
def testCalculateLOC(self):
with open(
os.path.join(UtilPath.Test(), "testDataset",
self.repository["name"], "loc.csv")) as f:
reader = csv.reader(f)
datasTest = [row for row in reader][1:]
for dataTest in datasTest:
pathFile = os.path.join(UtilPath.Test(), "testDataset",
self.repository["name"], "repository",
dataTest[18]).replace("/", "\\")
with self.subTest(pathFile=pathFile):
data = Data(self.gr, pathFile,
self.dataset.getCommitsBug(self.repository))
self.assertEqual(data.calculateLOC(), int(dataTest[0]))
def __init__(self, project, typeDataset, release4Test, purpose):
self.project = project
self.typeDataset = typeDataset
self.release4Test = release4Test
self.porpose = purpose
print(UtilPath.Datasets(), self.project, self.typeDataset,
self.release4Test)
def do(self):
self.checkGPU()
os.makedirs(UtilPath.ResultAction(self.option["idExperiment"]),
exist_ok=True)
modeler = Modeler(UtilPath.ResultAction(self.option["idExperiment"]))
dataset = Dataset(self.option["project"], self.option["typeDataset"],
self.option["release4test"], self.option["purpose"])
if self.option["purpose"] == "test":
xTrain4Test, yTrain4Test = dataset.getTrain4Test()
xTest4Test, yTest4Test = dataset.getTest4Test()
json_open = open(self.option["pathHP"], 'r')
hp = json.load(json_open)
modeler.test(xTrain4Test, yTrain4Test, xTest4Test, yTest4Test,
self.option["modelAlgorithm"], hp)
elif self.option["purpose"] == "search":
xTrain4Search, yTrain4Search = dataset.getTrain4Search()
xValid4Search, yValid4Search = dataset.getValid4Search()
modeler.search(xTrain4Search, yTrain4Search, xValid4Search,
yValid4Search, self.option["modelAlgorithm"],
self.option["time2search"])
def getTest4Test(self, indexCV=0):
dataTest = [[], [], []]
with open(
os.path.join(UtilPath.Datasets(), self.project,
self.typeDataset, self.release4Test,
"test.csv")) as f:
test = csv.reader(f)
for i, row in enumerate(test):
dataTest[0].append(row[0])
dataTest[1].append([float(x) for x in row[2:]])
dataTest[2].append(int(row[1]))
dataTest[1] = np.array(dataTest[1])
dataTest[2] = np.array(dataTest[2])
print(dataTest[1].shape)
return dataTest[1], dataTest[2]
def getValid4Search(self, indexCV=0):
dataValid = [[], [], []]
with open(
os.path.join(UtilPath.Datasets(), self.project,
self.typeDataset, self.release4Test,
"valid" + str(indexCV) + ".csv")) as f:
valid = csv.reader(f)
for i, row in enumerate(valid):
dataValid[0].append(row[0])
dataValid[1].append([float(x) for x in row[2:]])
dataValid[2].append(int(row[1]))
dataValid[1] = np.array(dataValid[1])
dataValid[2] = np.array(dataValid[2])
#print(dataValid[1].shape)
#print(dataValid[2].shape)
return dataValid[1], dataValid[2]
def getTrain4Search(self, indexCV=0):
dataTrain = [[], [], []]
with open(
os.path.join(UtilPath.Datasets(), self.project,
self.typeDataset, self.release4Test,
"train" + str(indexCV) + ".csv")) as f:
train = csv.reader(f)
for i, row in enumerate(train):
#print(item["id"])
dataTrain[0].append(row[0])
dataTrain[1].append([float(x) for x in row[2:]])
dataTrain[2].append(int(row[1]))
dataTrain[1] = np.array(dataTrain[1])
dataTrain[2] = np.array(dataTrain[2])
#print(dataTrain[1].shape)
#print(dataTrain[2].shape)
return dataTrain[1], dataTrain[2]
from src.manager import Maneger
from src.utility import UtilPath
import datetime
option={
"date" : datetime.datetime.now().strftime('%Y%m%d%H%M%S'),
"project" : "linuxtools",
"release4test" : "2",
"variableDependent" : "isBuggy",
"purpose" : "test",
"modelAlgorithm" : "DNN",
"pathModel" : "",
"pathHP" : UtilPath.Datasets()+"/"+"linuxtools/isBuggy/2/hpDNN.json"
}
option["idExperiment"] = \
option["project"] + "_" \
+ option["variableDependent"] + "_" \
+ option["release4test"] + "_" \
+ option["modelAlgorithm"] + "_" \
+ option["date"]
maneger = Maneger(option)
maneger.do()