DynamicTypinginPython/merge_state_RQ6.py at main · xiaxinmeng/DynamicTypinginPython · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
import json
import scipy.stats as stats
import os


# decide whether there are Python files in commit files
def decidePy(commitfile):
	flag = False
	for file in commitfile:
		if file.endswith(".py"):
			# print(file)
			flag = True
	return flag


def calORraw(ismerge,isdyn,dic):
	if ismerge == True and isdyn ==True:
		dic["mergeDT"] = dic["mergeDT"] + 1
	if ismerge == False and isdyn == False:
		dic["NmergeNDT"] = dic["NmergeNDT"] + 1
	if ismerge == True and isdyn ==False:
		dic["mergeNDT"] = dic["mergeNDT"] + 1
	if ismerge == False and isdyn == True:
		dic["NmergeDT"] = dic["NmergeDT"] + 1
	return dic


def smooth(OR_raw_data):
	for key in OR_raw_data.keys():
		if OR_raw_data[key] == 0:
			OR_raw_data[key] = OR_raw_data[key] + 1


def runDT(crawlerfile,dynamicfile):
	pulls = json.load(open(crawlerfile,'r'))
	dynDic	= json.load(open(dynamicfile,'r'))


	prefix = crawlerfile.split(".")[0].replace("crawlerResult","dataset")+"/"
	# prefix = '/home/xxm/Desktop/EMSE/dataset/auto-sklearn/'
	# print pull

	OR_raw_data = {"mergeDT":0,"NmergeDT":0,"mergeNDT":0,"NmergeNDT":0}

	for pull in pulls:

		commitfile = pull["commitfile"]
		if decidePy(commitfile):
			ismerge= pull["is_merged"]
			isdyn = False
			# print(type(fixbug))
			for file in commitfile.keys():
				# print pre + file
				if prefix + file in dynDic.keys():
					isdyn = True
					# print(prefix + file)

			OR_raw_data = calORraw(ismerge,isdyn,OR_raw_data)

	# print(OR_raw_data)

	# smooth
	# smooth(OR_raw_data)


	oddsratio, pvalue = stats.fisher_exact([[OR_raw_data["mergeDT"], OR_raw_data["NmergeDT"]], [OR_raw_data["mergeNDT"], OR_raw_data["NmergeNDT"]]])
	return oddsratio,pvalue


def runRDT(crawlerfile,dynamicfile):
	pulls = json.load(open(crawlerfile,'r'))
	dynDic	= json.load(open(dynamicfile,'r'))


	prefix = crawlerfile.split(".")[0].replace("crawlerResult","dataset")+"/"
	# prefix = '/home/xxm/Desktop/EMSE/dataset/auto-sklearn/'
	# print pull

	OR_raw_data = {"mergeDT":0,"NmergeDT":0,"mergeNDT":0,"NmergeNDT":0}

	for pull in pulls:

		commitfile = pull["commitfile"]
		if decidePy(commitfile):
			ismerge= pull["is_merged"]
			isdyn = False
			# print(type(fixbug))
			for file in commitfile.keys():
				# print pre + file
				if prefix + file in dynDic.keys():
					isdyn = True
					# print(prefix + file)

			OR_raw_data = calORraw(ismerge,isdyn,OR_raw_data)

	# print(OR_raw_data)

	# smooth
	# smooth(OR_raw_data)


	oddsratio, pvalue = stats.fisher_exact([[OR_raw_data["mergeDT"], OR_raw_data["NmergeDT"]], [OR_raw_data["mergeNDT"], OR_raw_data["NmergeNDT"]]])
	return oddsratio,pvalue


def runVDT(crawlerfile,dynamicfile):
	pulls = json.load(open(crawlerfile,'r'))
	dynDic	= json.load(open(dynamicfile,'r'))


	prefix = crawlerfile.split(".")[0].replace("crawlerResult","dataset")+"/"
	# prefix = '/home/xxm/Desktop/EMSE/dataset/auto-sklearn/'
	# print pull

	OR_raw_data = {"mergeDT":0,"NmergeDT":0,"mergeNDT":0,"NmergeNDT":0}

	for pull in pulls:

		commitfile = pull["commitfile"]
		if decidePy(commitfile):
			ismerge= pull["is_merged"]
			isdyn = False
			# print(type(fixbug))
			for file in commitfile.keys():
				# print pre + file
				if prefix + file in dynDic.keys():
					if "VDT" in dynDic[prefix + file].keys():
						isdyn = True
					# print(prefix + file)

			OR_raw_data = calORraw(ismerge,isdyn,OR_raw_data)

	# print(OR_raw_data)

	# smooth
	# smooth(OR_raw_data)


	oddsratio, pvalue = stats.fisher_exact([[OR_raw_data["mergeDT"], OR_raw_data["NmergeDT"]], [OR_raw_data["mergeNDT"], OR_raw_data["NmergeNDT"]]])
	return oddsratio,pvalue


def runRQ6():
	RQ6list = [("project","OR","pvalue")]
	crawlerDir = '/home/xxm/Desktop/EMSE/crawlerResult'

	for root, dirs, files in os.walk(crawlerDir):
		for file in files:
			if not file.startswith("."):
				crawlerfile =root+"/"+file
				dynamicfile = crawlerfile.replace("crawlerResult","DTResult")
				oddsratio,pvalue = runDT(crawlerfile,dynamicfile)
				print(file.replace(".json",""),"ismerge","Fisher_exact",oddsratio,pvalue)
				RQ6list.append((file.replace(".json",""),oddsratio,pvalue))
	return RQ6list

# RQ6list = runRQ6()
# print(RQ6list)