def ComputePrecisionK(modelfile, testfile, K_list):
maxParagraphLength = 10
maxParagraphs = 4
#nlabels=1001
#vocabularySize=76391
labels = 8
vocabularySize = 244
model = Model(maxParagraphLength, maxParagraphs, labels, vocabularySize)
testing = DataParser(maxParagraphLength, maxParagraphs, labels,
vocabularySize)
print(testfile)
testing.getDataFromfile(testfile)
print("data loading done")
print("no of test examples: " + str(testing.totalPages))
model.load(modelfile)
print("model loading done")
batchSize = 1
testing.restore()
truePre = []
pred = []
for itr in range(testing.totalPages):
data = testing.nextBatch(1)
truePre.append(data[0])
pre = model.predict(data)
pred.append(pre[0])
precAtK = {}
for itr in K_list:
precAtK[itr] = 0
for i, v in enumerate(pred):
temp = [(labId, labProb) for labId, labProb in enumerate(v)]
# print(temp)
temp = sorted(temp, key=lambda x: x[1], reverse=True)
for ele in K_list:
pBag = 0
for itr in range(ele):
if truePre[i][0][temp[itr][0]] == 1:
pBag += 1
# print(float(pBag)/float(ele))
precAtK[ele] += float(pBag) / float(ele)
f = open("results/precAtK_model3_n", "w")
for key in sorted(precAtK.keys()):
# print(key, precAtK[key]/len(pred))
print(precAtK[key] / len(pred))
f.write(str(key) + "\t" + str(precAtK[key] / len(pred)) + "\n")
f.close()
def ComputeFscore(modelfile, testfile, outputfile):
maxParagraphLength = int(sys.argv[1])
maxParagraphs = int(sys.argv[2])
filterSizes = [int(i) for i in sys.argv[3].split("-")]
num_filters = int(sys.argv[4])
wordEmbeddingDimension = int(sys.argv[5])
# batchSize= int(sys.argv[6])
# epochs= int(sys.argv[7])
# folder_name = sys.argv[8]
# output = sys.argv[9]
lrate = sys.argv[10]
poolLength = int(sys.argv[11])
labels = 8
vocabularySize = 244
model = Model(maxParagraphs, maxParagraphLength, labels, vocabularySize,
filterSizes, num_filters, poolLength, wordEmbeddingDimension,
lrate)
testing = DataParser(maxParagraphs, maxParagraphLength, labels,
vocabularySize)
testing.getDataFromfile(testfile)
model.load(modelfile)
print("loading done")
testing.restore()
truePre = []
pred = []
for itr in range(testing.totalPages):
data = testing.nextBatch(1)
truePre.append(data[0])
pre = model.predict(data)
pred.append(pre[0])
labelsCount = {}
ConfusionMa = {}
fScr = {}
thres = 0.5
valid = int(
len(truePre) * 0.5
) #using first 50% data for threshold tuning - we have merged test and cv files
labelsCount = {}
ConfusionMa = {}
fScr = {}
thresLab = {}
for la in range(labels):
if la % 25 == 0:
print("Current label", la)
t = []
p = []
for i in range(valid):
t.append(truePre[i][0][la])
p.append(pred[i][la])
bestF, bestThre = thresholdTuning(t, p)
t = []
p = []
for i in range(valid, len(truePre)):
t.append(truePre[i][0][la])
p.append(pred[i][la])
p = np.array(p)
fScr[la] = f1_score(t, p >= bestThre)
ConfusionMa[la] = confusion_matrix(t, p > bestThre)
thresLab[la] = bestThre
f = open(outputfile, "a")
output = sys.argv[9]
sum_fscore = 0.0
for i in range(labels):
sum_fscore = sum_fscore + fScr[i]
output = output + "," + str(fScr[i])
output += "," + str(sum_fscore / float(labels - 1))
print("Fscore at " + sys.argv[7] + " epochs: " +
str(sum_fscore / float(labels - 1)))
f.write(output + "\n")
f.close()
def ComputeFscore(modelfile, testfile, outputfile):
maxParagraphLength = 20
maxParagraphs = 10
#nlabels=1001
#vocabularySize=76391
labels = 8
vocabularySize = 244
model = Model(maxParagraphLength, maxParagraphs, labels, vocabularySize)
testing = DataParser(maxParagraphLength, maxParagraphs, labels,
vocabularySize)
testing.getDataFromfile(testfile)
model.load(modelfile)
print("loading done")
testing.restore()
truePre = []
pred = []
for itr in range(testing.totalPages):
data = testing.nextBatch(1)
truePre.append(data[0])
pre = model.predict(data)
pred.append(pre[0])
labelsCount = {}
ConfusionMa = {}
fScr = {}
thres = 0.5
valid = int(
len(truePre) * 0.5
) #using first 50% data for threshold tuning - we have merged test and cv files
labelsCount = {}
ConfusionMa = {}
fScr = {}
thresLab = {}
for la in range(labels):
if la % 25 == 0:
print("Current label", la)
t = []
p = []
for i in range(valid):
t.append(truePre[i][0][la])
p.append(pred[i][la])
bestF, bestThre = thresholdTuning(t, p)
t = []
p = []
for i in range(valid, len(truePre)):
t.append(truePre[i][0][la])
p.append(pred[i][la])
p = np.array(p)
fScr[la] = f1_score(t, p >= bestThre)
ConfusionMa[la] = confusion_matrix(t, p > bestThre)
thresLab[la] = bestThre
f = open(outputfile, "w")
sum_fscore = 0.0
for i in range(labels):
sum_fscore = sum_fscore + fScr[i]
inp = str(i) + "," + str(thresLab[i]) + "," + str(fScr[i]) + "\n"
f.write(inp)
f.write(str(sum_fscore / float(labels - 1)))
print(sum_fscore)
print(sum_fscore / float((labels - 1)))
f.close()
return (sum_fscore / float((labels - 1)))