def train(self):
rsl = []
files = listdir(self.path)
reader = InputData(self.dataset_type, self.path)
corpus = plsa.Corpus()
for filename in files:
vectors=[]
question = reader.readFile(filename)
id = question["id"]
self.data[id]=[ref["text"] for ref in question["referenceAnswers"]]
for r in question["referenceAnswers"]:
rid=r["id"]
references=[ sr["text"] for sr in r["studentAnswers"]]
"""
for ans in question["student_answers"]:
if ans["id"]==rid:
references.append(ans["text"])
#references=[ self.stemmer.stem(sr["text"]) for sr in r["studentAnswers"]]
"""
references.append(r["text"])
corpus.addBaseline(references)
#print corpus.getVector()
vectors.append(corpus.getVector())
corpus.reset()
self.model[id]=vectors
return
def test(self,mode,inputdir,outputdir):
head = ["id","grade" ,"Accuracy","Predicted"]
self.mode=mode
rsl=[]
files = listdir(inputdir)
reader = InputData(self.dataset_type, inputdir)
for filename in files:
question = reader.readFile(filename)
id = question["id"]
stuAns = []
for r in question["referenceAnswers"]:
for sr in r["studentAnswers"]:
stuAns.append(sr)
for sr in question["otherStudentAnswers"]:
stuAns.append(sr)
for sr in stuAns:
grade=""
if self.nonDomain.test(sr["text"]):
if mode==2 or mode==3:
grade="incorrect"
if mode==5:
grade="non_domain"
rsl.append({"id": sr["id"],"Accuracy":sr["accuracy"],"Predicted":grade,"grade":"NA"})
print rsl[len(rsl)-1]
continue
if self.contradictBigram.isContradictory(id,sr["text"]) or self.contradict.isContradictory(self.modeler.getReferences(id),sr["text"]):
if mode==2:
grade="incorrect"
if mode==3 or mode==5:
grade="contradictory"
rsl.append({"id": sr["id"],"Accuracy":sr["accuracy"],"Predicted":grade,"grade":"NA"})
print rsl[len(rsl)-1]
continue
score=self.modeler.grade(id,sr["text"])
if self.datamode== "beetle":
self.irr.build(self.modeler.getReferences(id))
if self.irr.isIrrelevent(sr["text"]):
score=-1
grade=self.predict(score)
rsl.append({"id": sr["id"],"Accuracy":sr["accuracy"],"Predicted":grade,"grade":score})
print rsl[len(rsl)-1]
output(outputdir, head, rsl)