-
Notifications
You must be signed in to change notification settings - Fork 3
/
al_RequirementAnalysis.py
209 lines (159 loc) · 8.11 KB
/
al_RequirementAnalysis.py
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
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
#!/usr/bin/python
#
# Requirement Analysis via NLP Chunks noun.verb(predicate)
#
__author__ = u'morrj140'
__VERSION__ = u'0.3'
from Logger import *
logger = setupLogging(__name__)
logger.setLevel(INFO)
from nl_lib.Constants import *
from nl_lib.Concepts import Concepts
from nl_lib.TopicsModel import TopicsModel
import nltk
from nltk import tokenize, tag, chunk
from nltk.corpus import webtext
from nltk.collocations import BigramCollocationFinder, TrigramCollocationFinder
from nltk.metrics import BigramAssocMeasures, TrigramAssocMeasures
from nltk.corpus import stopwords
from nltk.corpus import wordnet as wn
from nltk.stem import PorterStemmer, WordNetLemmatizer
from nltk.tokenize import RegexpTokenizer
from itertools import islice
from pattern.vector import count, words, PORTER, LEMMA
from pattern.vector import Document, Model, TFIDF, HIERARCHICAL
from pattern.vector import Vector, distance, NB
from pattern.db import csv
from pattern.en import parse, Sentence, parsetree
from al_lib.Constants import *
from al_lib.ArchiLib import ArchiLib
class Chunks(object):
conceptFile = fileConceptsDocuments
chunkFile = fileConceptsChunks
concepts = None
chunkConcepts = None
def __init__(self, concepts=None):
if concepts is None:
logger.info(u"Loading : %s" % self.conceptFile)
self.concepts = Concepts.loadConcepts(self.conceptFile)
else:
logger.info(u"Using : %s" % concepts.name)
self.concepts = concepts
self.chunkConcepts = Concepts(u"Chunk", u"Chunks")
def getChunkConcepts(self):
return self.chunkConcepts
def createChunks(self):
stop = stopwords.words(u'english')
stop.append(u"This")
stop.append(u"The")
stop.append(u",")
stop.append(u".")
stop.append(u"..")
stop.append(u"...")
stop.append(u".")
stop.append(u";")
stop.append(u"and")
stemmer = PorterStemmer()
lemmatizer = WordNetLemmatizer()
tokenizer = RegexpTokenizer(u"[\w]+")
for document in self.concepts.getConcepts().values():
logger.info(u"%s" % document.name)
d = self.chunkConcepts.addConceptKeyType(document.name, u"Document")
for sentence in document.getConcepts().values():
logger.debug(u"%s(%s)" % (sentence.name, sentence.typeName))
cleanSentence = ' '.join([word for word in sentence.name.split() if word not in stop])
listSentence = list()
for word, pos in nltk.pos_tag(nltk.wordpunct_tokenize(cleanSentence)):
logger.debug(u"Word: " + word + u" POS: " + pos)
if pos[:1] == u"N":
#if True:
lemmaWord = lemmatizer.lemmatize(word)
logger.debug(u"Word: " + word + u" Lemma: " + lemmaWord)
morphWord = wn.morphy(word, wn.NOUN)
if morphWord is not None:
logger.debug(u"Word: " + word + u" Morph: " + morphWord)
synset = wn.synsets(word, pos=u'n')
logger.debug(u"synset : %s" % synset)
if len(synset) != 0:
syn = synset[0]
root = syn.root_hypernyms()
logger.debug(u"root : %s" % root)
mh = syn.member_holonyms()
logger.debug(u"member_holonyms : %s" % mh)
hypernyms = syn.hypernyms()
logger.debug(u"hypernyms : %s" % hypernyms)
if len(hypernyms) > 0:
hyponyms = syn.hypernyms()[0].hyponyms()
logger.debug(u"hyponyms : %s" % hyponyms)
else:
hyponyms = None
listSentence.append((word, lemmaWord, pos, root, hypernyms, hyponyms))
nounSentence = u""
for word in listSentence:
nounSentence += word[1] + u" "
if len(nounSentence) > 2:
e = d.addConceptKeyType(nounSentence, u"NounSentence")
for word in listSentence:
f = e.addConceptKeyType(word[0], word[2])
f.addConceptKeyType(word[1], u"Lemma")
logger.debug(u"%s = %s" % (cleanSentence, type(cleanSentence)))
cleanSentence = unicode(cleanSentence)
pt = parsetree(cleanSentence, relations=True, lemmata=True)
for sentence in pt:
logger.debug(u"relations: %s" % [x for x in sentence.relations])
logger.debug(u"subject : %s" % [x for x in sentence.subjects])
logger.debug(u"verb : %s" % [x for x in sentence.verbs])
logger.debug(u"object : %s" % [x for x in sentence.objects])
if sentence.subjects is not None:
logger.debug(u"Sentence : %s" % sentence.chunks)
for chunk in sentence.chunks:
logger.debug(u"Chunk : %s" % chunk)
relation = unicode(chunk.relation).strip()
role = unicode(chunk.role).strip()
logger.debug(u"Relation : %s" % relation)
logger.debug(u"Role : %s" % role)
for subject in sentence.subjects:
logger.debug(u" Subject.realtion : %s " % subject.relation)
logger.debug(u" Subject : %s " % subject.string)
f = e.addConceptKeyType(subject.string, u"SBJ")
for verb in sentence.verbs:
if verb.relation == subject.relation:
logger.debug(u" Verb.realtion : %s " % verb.relation)
logger.debug(u" Verb : %s " % verb.string)
g = f.addConceptKeyType(verb.string, u"VP")
for obj in sentence.objects:
if obj.relation == verb.relation:
logger.debug(u" Obj.realtion : %s " % obj.relation)
logger.debug(u" Object : %s " % obj.string)
g.addConceptKeyType(obj.string, u"OBJ")
Concepts.saveConcepts(self.chunkConcepts, self.chunkFile)
logger.info(u"Saved : %s" % self.chunkFile)
def requirementAnalysis(fileArchimate=None):
if fileArchimate is None:
fileArchimate = u"/Users/morrj140/Documents/SolutionEngineering/Archimate Models/DVC v38.archimate"
al = ArchiLib(fileArchimate)
conceptsFile = fileConceptsRequirements
searchTypes = list()
searchTypes.append(u"archimate:Requirement")
nl = al.getTypeNodes(searchTypes)
logger.info(u"Find Words in Requirements...")
concepts = Concepts(u"Requirement", u"Requirements")
n = 0
for sentence in nl:
n += 1
logger.debug(u"%s" % sentence)
c = concepts.addConceptKeyType(u"Document" + str(n), u"Document")
d = c.addConceptKeyType(sentence, u"Sentence" + str(n))
if True and sentence is not None:
cleanSentence = ' '.join([word for word in sentence.split(u" ") if word not in stop])
for word, pos in nltk.pos_tag(nltk.wordpunct_tokenize(cleanSentence)):
if len(word) > 1 and pos[0] == u"N":
e = d.addConceptKeyType(word, u"Word")
f = e.addConceptKeyType(pos, u"POS")
Concepts.saveConcepts(concepts, conceptsFile)
logger.info(u"Saved : %s" % conceptsFile)
chunks = Chunks(concepts)
chunks.createChunks()
if __name__ == u"__main__":
fileArchimate = u"/Users/morrj140/Documents/SolutionEngineering/Archimate Models/DVC v38.archimate"
requirementAnalysis(fileArchimate)