def WordAveraging(sent, WV, dim):
summ = [0.0] * dim
A = 0.0
sent_A = preprocessor1(re.sub(r"[\n(\[\])]", "", sent)).split(" ")
for word in sent_A:
if word in WV: #and word not in stop:
A = A + 1.0
for i in range(0, len(WV[word])):
summ[i] = summ[i] + float((WV[word])[i])
if A != 0:
for i in range(0, dim):
summ[i] = summ[i] / A
return summ
def WordAveraging(sent, WV, dim):
summ = [0.0] * (dim)
#summ.extend([1])
A = 0.0;
sent_A=preprocessor1(re.sub(r"[\n(\[\])]", "", sent)).split(" ")
for word in sent_A:
if word in WV : #and word not in stop:
A = A + 1.0
for i in range(0, dim):
summ[i] = summ[i] + float((WV[word])[i])
if A != 0:
#A = 1
for i in range(0, dim):
summ[i] = summ[i] / A
#print len(summ)
return summ;
def readTree_att_Scalar(filePath, W1, WV, dim, hierarchyType, attScaler, activationFunc):
EDUs = {}
EDUs_main = {}
if os.path.exists(filePath):
if os.stat(filePath).st_size > 0 :
file_1 = open(filePath, "r")
for line in file_1:
line = re.sub(r"[\n(\[\])]", "", line)
arr = re.split("\s*,\s*",line)
arr2 = re.split("\'", line)
relation = arr2[len(arr2)-2]
hierarchy = arr2[len(arr2)-4]
if arr[0] == arr[1]:
if int(arr[0]) / 10 != 0:
arr[0] = "9" + arr[0]
vector = WordAveraging(preprocessor1(re.sub(r"[\n,.:'(\[\])]", "", arr2[1])), WV, dim)
#vector = tanh(vector)
if hierarchy == hierarchyType:
vector = np.multiply(attScaler, vector)
EDUs_main [arr[0]] = ClassNode.Node(True, False, 0, 0, "", hierarchy, relation, vector, "")
EDUs[arr[0]] = "hi"
else:
numconcat = ""
for num in range(int(arr[0]), int(arr[1])+1):
if num/10 !=0 :
num="9"+str(num)
numconcat += `int(num)`
childs={}
i=1
numconcat2 = numconcat
EDUitem = sortEduKey(EDUs_main.keys(), reverse=True)
for key in EDUitem:
key = str(key)
if numconcat!='' and key in numconcat:
childs[i] = EDUs_main[key].vector
if i==1:
rightChild = key
EDUs_main[key].child = "right"
elif i==2:
leftChild = key
EDUs_main[key].child = "left"
#print len(childs[i]), key
i = 2
numconcat = numconcat.replace(key,"")
del EDUs[key]
EDUs[numconcat2]="hi"
vector = feedforward_act(np.concatenate([childs[2], childs[1]], 0), W1, activationFunc)
if hierarchy == hierarchyType:
vector = np.multiply(attScaler, vector)
EDUs_main[numconcat2]=ClassNode.Node(False, False, leftChild, rightChild, "" , hierarchy, relation, vector, "")
eduKey=EDUs.keys()
eduKey.sort()
if len(eduKey)>1:
vector = feedforward_act(np.concatenate([EDUs_main[eduKey[0]].vector, EDUs_main[eduKey[1]].vector], 0), W1, activationFunc)
EDUs[eduKey[0]+eduKey[1]] = "hi"
EDUs_main[eduKey[0]].child = "left"
EDUs_main[eduKey[1]].child = "right"
if hierarchy == hierarchyType:
vector = np.multiply(attScaler, vector)
EDUs_main[eduKey[0]+eduKey[1]] = ClassNode.Node(False, True, eduKey[0], eduKey[1],"", "", "", vector, "")
del EDUs[eduKey[0]]
del EDUs[eduKey[1]]
return EDUs_main
else:
return EDUs_main
def readTree_att_NSWeight(filePath, W1, WV, dim, WSat, WNu, activationFunc):
#print filePath
EDUs = {}
EDUs_main = {}
if os.path.exists(filePath):
if os.stat(filePath).st_size > 0 :
file_1 = open(filePath, "r")
for line in file_1:
line = re.sub(r"[\n(\[\])]", "", line)
arr = re.split("\s*,\s*",line)
arr2 = re.split("\'", line)
relation = arr2[len(arr2)-2]
hierarchy = arr2[len(arr2)-4]
if arr[0] == arr[1]:
if int(arr[0]) / 10 != 0:
arr[0] = "9" + arr[0]
vector = WordAveraging(preprocessor1(re.sub(r"[\n,.:'(\[\])]", "", arr2[1])), WV, dim)
#print vector
if np.absolute(max(vector))>2:
print "vayyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyy"
if np.sum(np.absolute(vector))/dim >=0.8:
for item in EDUs_main.keys():
print item, " ", EDUs_main[item].vector
print "khodaaaaaaaaaaaaaaaaaa"
#vector = tanh (vector)
EDUs_main [arr[0]] = ClassNode.Node(True, False, 0, 0, "", hierarchy, relation, vector, "")
EDUs[arr[0]] = "hi"
else:
numconcat = ""
for num in range(int(arr[0]), int(arr[1])+1):
if num/10 !=0 :
num="9"+str(num)
numconcat += `int(num)`
childs={}
i=1
numconcat2 = numconcat
EDUitem = sortEduKey(EDUs_main.keys(), reverse=True)
for key in EDUitem:
key = str(key)
if numconcat!='' and key in numconcat:
childs[i] = EDUs_main[key].vector
#print key, " ", childs[i]
childs[i] = apply_attention(childs[i], EDUs_main[key].nodeHierarchy, WNu, WSat, activationFunc)
if np.sum(np.absolute(childs[i])) / dim >= 0.8:
for item in EDUs_main.keys():
print item, " ", EDUs_main[item].vector
print key, " ", childs[i]
print "khodaaaaaaaaaaaaaaaaaa"
if i==1:
rightChild = key
EDUs_main[key].child = "right"
elif i==2:
leftChild = key
EDUs_main[key].child = "left"
i = 2
numconcat = numconcat.replace(key,"")
del EDUs[key]
EDUs[numconcat2]="hi"
vector = feedforward_act(np.concatenate([childs[2], childs[1]], 0), W1, activationFunc)
EDUs_main[numconcat2]=ClassNode.Node(False, False, leftChild, rightChild, "" , hierarchy, relation, vector, "")
eduKey=EDUs.keys()
eduKey.sort()
if len(eduKey)>1:
EDU_0 = apply_attention(EDUs_main[eduKey[0]].vector, EDUs_main[eduKey[0]].nodeHierarchy, WNu, WSat, activationFunc)
EDU_1 = apply_attention(EDUs_main[eduKey[1]].vector, EDUs_main[eduKey[1]].nodeHierarchy, WNu, WSat, activationFunc)
vector = feedforward_act(np.concatenate([EDU_0, EDU_1], 0), W1, activationFunc)
EDUs[eduKey[0]+eduKey[1]] = "hi"
EDUs_main[eduKey[0]].child = "left"
EDUs_main[eduKey[1]].child = "right"
# if hierarchy == "Nucleus":
# vector = np.matmul(vector, WNu)
# elif hierarchy == "Satellite":
# vector = np.matmul(vector, WSat)
EDUs_main[eduKey[0]+eduKey[1]] = ClassNode.Node(False, True, eduKey[0], eduKey[1],"", "", "", vector, "")
del EDUs[eduKey[0]]
del EDUs[eduKey[1]]
return EDUs_main
else:
return EDUs_main