def evaluateVSM(targeEventFile, collFolder,k,relevTh,vsmClassifierFileName,topK):
'''
docs = []
try:
classifierFile = open(vsmClassifierFileName,"rb")
classifier = pickle.load(classifierFile)
classifierFile.close()
except:
f = open(targeEventFile,'r')
for url in f:
url = url.strip()
d = Document(url)
if d:
docs.append(d)
f.close()
docsTF = []
for d in docs:
wordsFreq = getFreq(d.getWords())
docsTF.append(wordsFreq)
classifier = VSMClassifier(docsTF,relevTh)
evalres = []
for j in range(k):
fn = collFolder+str(j)+'.txt'
f = codecs.open(fn, encoding='utf-8')
ftext = f.read()
r = classifier.calculate_score(ftext)[0]
evalres.append(r)
f.close()
'''
evaluator = Evaluate()
evaluator.buildVSMClassifier(targeEventFile,vsmClassifierFileName,relevTh,topK)
collFiles = []
for j in range(k):
fn = collFolder+str(j)+'.txt'
f = codecs.open(fn, encoding='utf-8')
ftext = f.read()
o = myObj()
o.text = ftext
collFiles.append(o)
res = evaluator.evaluateFC(collFiles)
#f = open(collFolder+'evaluationRes_VSM.txt','w')
#f.write('\n'.join([str(r) for r in res]))
#f.close()
#print sum(res)
return res
def evaluateVSM(targeEventFile, collFolder,k,relevTh,vsmClassifierFileName,topK):
'''
docs = []
try:
classifierFile = open(vsmClassifierFileName,"rb")
classifier = pickle.load(classifierFile)
classifierFile.close()
except:
f = open(targeEventFile,'r')
for url in f:
url = url.strip()
d = Document(url)
if d:
docs.append(d)
f.close()
docsTF = []
for d in docs:
wordsFreq = getFreq(d.getWords())
docsTF.append(wordsFreq)
classifier = VSMClassifier(docsTF,relevTh)
evalres = []
for j in range(k):
fn = collFolder+str(j)+'.txt'
f = codecs.open(fn, encoding='utf-8')
ftext = f.read()
r = classifier.calculate_score(ftext)[0]
evalres.append(r)
f.close()
'''
evaluator = Evaluate()
evaluator.buildVSMClassifier(targeEventFile,vsmClassifierFileName,relevTh,topK)
collFiles = []
for j in range(k):
fn = collFolder+str(j)+'.txt'
f = codecs.open(fn, encoding='utf-8')
ftext = f.read()
o = myObj()
o.text = ftext
collFiles.append(o)
res = evaluator.evaluateFC(collFiles)
#f = open(collFolder+'evaluationRes_VSM.txt','w')
#f.write('\n'.join([str(r) for r in res]))
#f.close()
#print sum(res)
return res
def evaluateClassifier(classifierFile,cf,k):
evaluator = Evaluate()
evaluator.buildClassifier("posFile","negFolder",classifierFile)
collFiles = []
for j in range(k):
fn = cf+str(j)+'.txt'
f = codecs.open(fn, encoding='utf-8')
ftext = f.read()
o = myObj()
o.text = ftext
collFiles.append(o)
res = evaluator.evaluateFC(collFiles)
f = open(cf+'evaluationRes_Classf.txt','w')
f.write('\n'.join([str(r) for r in res]))
f.close()
print sum(res)
def evaluateClassifier(classifierFile,cf,k):
evaluator = Evaluate()
evaluator.buildClassifier("posFile","negFolder",classifierFile)
collFiles = []
for j in range(k):
fn = cf+str(j)+'.txt'
f = codecs.open(fn, encoding='utf-8')
ftext = f.read()
o = myObj()
o.text = ftext
collFiles.append(o)
res = evaluator.evaluateFC(collFiles)
f = open(cf+'evaluationRes_Classf.txt','w')
f.write('\n'.join([str(r) for r in res]))
f.close()
print sum(res)
elif ct == 'e':
#eventRelevantPages = eventFC(crawlParams)
pagesDir = outputDir + "/event-webpages/"
logDataFilename = pagesDir + "event-logData.txt"
outputURLsFilename = pagesDir + "event-Output-URLs.txt"
evalFilename = pagesDir + "event-evaluateData.txt"
rp = eventFC(crawlParams)
#if not os.path.exists(outputDir):
# os.makedirs(outputDir)
if not os.path.exists(pagesDir):
os.makedirs(pagesDir)
f = open(logDataFilename, "w")
furl = open(outputURLsFilename, "w")
for p in rp:
f.write(str(p.pageId) + "," + str(p.pageUrl[2]) + "\n")
#furl.write(p.pageUrl[1].encode("utf-8")+","+str(p.estimatedScore)+"\n")
furl.write(p.pageUrl[1].encode("utf-8") + "\n")
ftext = open(pagesDir + str(p.pageId) + ".txt", "w")
ftext.write(p.text.encode("utf-8"))
ftext.close()
f.close()
furl.close()
res = evaluator.evaluateFC(rp)
writeEvaluation(res, evalFilename)
print sum(res)
print len(res)
#eventRelevantPages = eventFC(crawlParams)
pagesDir=outputDir+"/event-webpages/"
logDataFilename=pagesDir+"event-logData.txt"
outputURLsFilename=pagesDir+"event-Output-URLs.txt"
evalFilename=pagesDir+"event-evaluateData.txt"
rp = eventFC(crawlParams)
#if not os.path.exists(outputDir):
# os.makedirs(outputDir)
if not os.path.exists(pagesDir):
os.makedirs(pagesDir)
f = open(logDataFilename,"w")
furl = open(outputURLsFilename,"w")
for p in rp:
f.write(str(p.pageId) + "," + str(p.pageUrl[2]) + "\n")
#furl.write(p.pageUrl[1].encode("utf-8")+","+str(p.estimatedScore)+"\n")
furl.write(p.pageUrl[1].encode("utf-8")+"\n")
ftext = open(pagesDir+str(p.pageId) + ".txt", "w")
ftext.write(p.text.encode("utf-8"))
ftext.close()
f.close()
furl.close()
res = evaluator.evaluateFC(rp)
writeEvaluation(res,evalFilename)
print sum(res)
print len(res)
