def generate_data(self,text):
if isinstance(text,str):
sens = tools.seperate_sentences(text)
else:
sens = text
words =[]
sen_words = []
for sen in sens:
wp = tools.sen_pog( sen)
tmp = []
for w,p in wp:
if "n" in p or "v" in p or "m" in p:
tmp.append(w)
if w not in words:
words.append(w)
sen_words.append(tmp)
vector = []
for sen_w in sen_words:
tmp =[0]*len(words)
for i in range(len(words)):
w= words[i]
if w in sen_w:
tmp[i] = 1
vector.append(tmp)
return words,vector
def preprocess(self,text):
sens_words, sens_tag = [], []
sens = tools.seperate_sentences(text)
for sen in sens:
tmp_words, tmp_tag = [], []
for w, t in tools.sen_pog(sen):
tmp_words.append(w)
tmp_tag.append(t)
sens_words.append(tmp_words)
sens_tag.append(tmp_tag)
return sens, sens_words, sens_tag
def vectorize(self, text):
sens = tools.seperate_sentences(text)
matrix = []
for sen in sens:
tmp = tools.sen_pog(sen)
pog_tmp = []
for w, p in tmp:
if p == "n" or "v" in p:
pog_tmp.append(w)
matrix.append(pog_tmp)
tr_res = self.tr.textrank_matrix(matrix)
def text2pic(text):
sens = tools.seperate_sentences(text)
nodes = []
nodes_dict = {}
sen_words =[]
sen_noun_words =[]
for sen in sens:
wp = tools.sen_pog(sen)
tmp_w =[]
tmp_p = []
tmp_noun =[]
for w,p in wp:
if "n" in p or "v" in p or "m" in p:
if w not in nodes:
nodes.append(w)
if w not in nodes_dict.keys():
nodes_dict[w] = 0
nodes_dict[w]+=1
tmp_noun.append(w)
# tmp.append([w,p])
tmp_w.append(w)
tmp_p.append(p)
sen_noun_words.append(tmp_noun)
sen_words .append([tmp_w,tmp_p])
# nodes = []
# tmp = sorted(nodes_dict.items(), key= lambda d:d[1],reverse=True)
# for var,count in tmp:
# nodes.append(var)
#
# print(tmp)
matrix = [[0]*len(nodes) for var in range(len(nodes))]
for k in range(len(sen_noun_words)):
var = sen_noun_words[k]
for i in range(len(var)-1):
for j in range(i+1,len(var)):
#
matrix[nodes.index(var[i])][nodes.index(var[j])] += 1
matrix[nodes.index(var[j])][nodes.index(var[i])] += 1
# nouni_index = sen_words[k][0].index(var[i])
# nounj_index = sen_words[k][0].index(var[j])
# if nouni_index == nounj_index-1 and True:
# matrix[nodes.index(var[i])][nodes.index(var[j])] +=1
# matrix[nodes.index(var[j])][nodes.index(var[i])] +=1
# else:
# for p in sen_words[k][1][nouni_index:nounj_index]:
# if "v" in p or "m" in p:
# matrix[nodes.index(var[i])][nodes.index(var[j])] += 1
# matrix[nodes.index(var[j])][nodes.index(var[i])] += 1
# break
return matrix,nodes
def sum2pic(text,nodes):
sens = tools.seperate_sentences(text)
sen_n =[]
sen_w =[]
sen_p = []
# nodes_dict = {}
for sen in sens:
wp = tools.sen_pog(sen)
tmp_sen_n =[]
tmp_sen_w = []
tmp_sen_p =[]
for w,p in wp:
if ("n" in p or "v" in p or "m" in p )and w in nodes:
tmp_sen_n.append(w)
# if w not in nodes_dict.keys():
# nodes_dict[w] = 0
# nodes_dict[w] += 1
tmp_sen_w.append(w)
tmp_sen_p.append(p)
sen_n.append(tmp_sen_n)
sen_w.append(tmp_sen_w)
sen_p.append(tmp_sen_p)
# nodes = []
# tmp = sorted(nodes_dict.items(), key=lambda d: d[1], reverse=True)
# for var, count in tmp:
# nodes.append(var)
# print(tmp)
matrix = [[0]*len(nodes) for var in range(len(nodes))]
for i in range(len(sen_n)):
for j in range(len(sen_n[i])):
for k in range(j+1,len(sen_n[i])):
# nouni_index = sen_w[i].index(sen_n[i][j])
# nounj_index = sen_w[i].index(sen_n[i][k])
matrix[nodes.index(sen_n[i][j])][nodes.index(sen_n[i][k])] += 1
matrix[nodes.index(sen_n[i][k])][nodes.index(sen_n[i][j])] += 1
# if nouni_index == nounj_index-1 and True :
# matrix[nodes.index(sen_n[i][j])][nodes.index(sen_n[i][k])] +=1
# matrix[nodes.index(sen_n[i][k])][nodes.index(sen_n[i][j])] +=1
# for p in sen_p[i][nouni_index:nounj_index+1]:
# if "v" in p or "m" in p:
# matrix[nodes.index(sen_n[i][j])][nodes.index(sen_n[i][k])] += 1
# matrix[nodes.index(sen_n[i][k])][nodes.index(sen_n[i][j])] += 1
# break
return matrix