def ComputePrecisionK(modelfile, testfile, K_list):
CURRENT_DIR = os.path.dirname(os.path.abspath("./WikiCategoryLabelling/"))
sys.path.append(os.path.dirname(CURRENT_DIR + "/WikiCategoryLabelling/"))
maxParagraphLength = 250
maxParagraphs = 10
labels = 1001
vocabularySize = 76390
model = Model(maxParagraphLength, maxParagraphs, labels, vocabularySize)
testing = DataParser(maxParagraphLength, maxParagraphs, labels,
vocabularySize)
testing.getDataFromfile(testfile)
print("data loading done")
print("no of test examples: " + str(testing.totalPages))
model.load(modelfile)
print("model loading done")
batchSize = 10
testing.restore()
truePre = []
pred = []
for i in range(math.ceil(testing.totalPages / batchSize)):
if i < testing.totalPages / batchSize:
data = testing.nextBatch(batchSize)
else:
data = testing.nextBatch(testing.totalPages % batchSize)
truePre.extend(data[0])
pre = model.predict(data)
pred.extend(pre[0].tolist())
avgPrecK = [0] * len(K_list)
for i, p in enumerate(pred):
sortedL = sorted(range(len(p)), key=p.__getitem__, reverse=True)
for k, K in enumerate(K_list):
labelK = sortedL[:K]
precK = 0
for l in labelK:
if truePre[i][l] == 1:
precK += 1
avgPrecK[k] += precK / float(K)
avgPrecK = [float(a) / len(pred) for a in avgPrecK]
for p in avgPrecK:
print(str(p))
def ComputeFscore(modelfile, testfile, outputfile):
CURRENT_DIR = os.path.dirname(os.path.abspath("./WikiCategoryLabelling/"))
sys.path.append(os.path.dirname(CURRENT_DIR + "/WikiCategoryLabelling/"))
maxParagraphLength = 250
maxParagraphs = 10
labels = 1000
vocabularySize = 150000
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()
truePre.append(data[0])
pre = model.predict(data)
pred.append(pre[0])
labelsCount = {}
ConfusionMa = {}
fScr = {}
thres = 0.5
valid = int(len(truePre) * 0.35)
labelsCount = {}
ConfusionMa = {}
fScr = {}
thresLab = {}
for la in range(1000):
if la % 25 == 0:
print("Currnet label", la)
t = []
p = []
for i in range(valid):
t.append(truePre[i][la])
p.append(pred[i][la])
bestF, bestThre = thresholdTuning(t, p)
t = []
p = []
for i in range(valid, len(truePre)):
t.append(truePre[i][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")
for i in range(1000):
inp = str(i) + "," + str(thresLab[i]) + "," + str(fScr[i]) + "\n"
f.write(inp)
f.close()