def f(text):
sentences = sentence.get_sentences(text)
doc = []
for sent in sentences:
#print "%s" % sent.encode('utf8')
words = segment.seg(sent)
words = swfilter.filter(words)
doc.append(words)
rank = TextRank(doc)
rank.solve()
ret = []
for index in rank.top_index(limit=5):
ret.append(sentences[index].strip())
def handle(self, doc):
words = segment.seg(doc)
words = swfilter.filter(words)
return words
def text_preprocess(text):
allowed_words = ['.', ',', '?', '!', '\\', '-', 'n', ';', ' ', 'W']
for sen_id, sentance in enumerate(text):
sentance = (sentance).replace('\n', '.')
sentance = (sentance).replace('\t', '.')
sentance = (sentance).replace('。', '.')
sentance = (sentance).replace('，', ',')
sentance = (sentance).replace('？', '?')
text[sen_id] = sentance
pattern1 = re.compile('[a-zA-Z]+')
pattern2 = re.compile(r'\[.*?\]')
pattern3 = re.compile(r'\.+')
pattern4 = re.compile(r' +')
pattern5 = re.compile(r'…+')
pattern6 = re.compile(r'\\r')
pattern7 = re.compile('[0-9]+')
pattern8 = re.compile(r',+')
pattern9 = re.compile(r'《.*?》')
pattern10 = re.compile(r'。+')
pattern11 = re.compile(r'，+')
pattern12 = re.compile(r'【.*?】')
text = [pattern1.sub("", lines) for lines in text] # 去掉英语字符
text = [pattern2.sub("", lines) for lines in text] # 去掉[]中的部分
text = [pattern3.sub(".", lines) for lines in text] # 去掉...
text = [pattern4.sub(".", lines) for lines in text] # 去掉空格
text = [pattern5.sub(".", lines) for lines in text] # 去掉…
text = [pattern6.sub("", lines) for lines in text] # 去掉空格\r
text = [pattern7.sub("n", lines) for lines in text] # 用n代表数字
text = [pattern8.sub(",", lines) for lines in text] # 去掉,,,
text = [pattern9.sub("", lines) for lines in text] # 去掉《》中的部分
text = [pattern10.sub(".", lines) for lines in text] # 去掉。。。
text = [pattern11.sub(",", lines) for lines in text] # 去掉，，，
text = [pattern12.sub("", lines) for lines in text] # 去掉【】中
text = [pattern3.sub(".", lines) for lines in text] # 去掉...
text_id = 0
max_len = 20
processed_text = []
while (True):
if text_id >= text.__len__():
break
if text[text_id].__len__() <= max_len:
text_id += 1
continue
for i in range(text[text_id].__len__() - max_len):
if text[text_id][i + max_len] in [',', '.', '?']:
text.append(text[text_id][i + max_len + 1:])
text[text_id] = text[text_id][:i + max_len]
text_id += 1
break
if i == text[text_id].__len__() - max_len - 1:
text_id += 1
break
if i == sentence_min_len:
break_sign = 0
for j in range(max_len - 1, -1, -1):
if text[text_id][j] in [',', '.', '。', '，', '\n']:
text.append(text[text_id][j + 1:])
text[text_id] = text[text_id][:j + 1]
text_id += 1
break_sign = 1
break
if break_sign:
break
else:
# text.append(text[text_id][i + max_len + 1:])
text[text_id] = text[text_id][:i + max_len + 1]
text_id += 1
break
for sentance in text:
if if_segment():
sentance_seg = segment.seg(sentance)
else:
sentance_seg = sentance
sentance_seg2 = ['\start']
for word in sentance_seg:
if word in allowed_words or is_chinese(word):
sentance_seg2.append(word)
sentance_seg2.append('\end')
processed_text.append(sentance_seg2)
return processed_text
return cm,accu
def accuracy(cm):
row_num = len(cm)
right_num = 0
for i in range(row_num):
right_num += cm[i][i]
total_num = sum(cm.sum(0))
return float(right_num) / float(total_num)
if __name__ == "__main__":
filename = "/home/chi/PycharmProjects/Seg_AR/data/example"
segment.SENSORLIST = tools.getSensorList(filename)
true_labels = annotation.origin_annotation(filename)
seq_index = []
with open(filename, 'r') as fr:
for line in fr:
row = line.split()
seq_index.append(segment.SENSORLIST.index(row[2]))
sizes=range(10,150,5)
thetas = [0.01,0.05,0.1,0.15,0.2,0.25,0.3,0.35,0.4,0.45,0.5]
for size in sizes:
for theta in thetas:
border_1 = segment.seg(seq_index, size, theta)
vote_labels = annotation.seg_labels(true_labels,border_1)
cm,accu = confusionmatrix(vote_labels,true_labels)
print accu
def select(img):
global ims, para, contour, ps, imggg, C, parts, index, para1, ims1, ps1
# Segmentation
im, cl, d = segment.seg(img)
# Setting values of the global variables
ps = cl.copy()
imggg = im
j = imggg.copy()
ims = imggg.copy()
C = np.zeros(ims.shape, np.uint8)
contour = None
para = True
# Selction of contour
cv2.namedWindow('image', cv2.WINDOW_NORMAL)
cv2.resizeWindow('image', (int(im.shape[1] / 2), int(im.shape[0] / 2)))
cv2.moveWindow('image', 40, 0)
cv2.setMouseCallback('image', draw_c)
while (1):
cv2.imshow('image', ims)
k = cv2.waitKey(1) & 0xFF
if k == ord('q'):
break
cv2.destroyAllWindows()
# Finding all the points on the contour
Cp = cv2.cvtColor(C, cv2.COLOR_BGR2GRAY)
point = cv2.findNonZero(Cp)
# Taking as input the number of parts to which the contour should be divided
num_parts = input(
"In how many parts you want to divide the selected vessel (Please enter an integer <=5): "
)
#print(point.shape)
print("Select the required part and press Q.")
parts = np.array_split(point, int(num_parts), axis=0)
colbgr = [(193, 182, 255), (255, 0, 102), (255, 128, 0), (0, 255, 255),
(10, 200, 10)]
Cparts = np.zeros(C.shape)
for i, part in enumerate(parts):
if (i >= 5):
cv2.drawContours(Cparts, part, -1, (255, 255, 255), 5)
else:
cv2.drawContours(Cparts, part, -1, colbgr[i], 5)
# Global variables
para1 = True
ps1 = Cparts
ims1 = ps1.copy()
parts = np.array_split(point, int(num_parts), axis=0)
# At max supports 10 parts
if (int(num_parts) <= 1 or int(num_parts) > 10):
num_parts = 1
C_parts_selected = parts[0]
return (C_parts_selected, d)
# Selecting the part if number of parts <=10
cv2.namedWindow('image1', cv2.WINDOW_NORMAL)
cv2.resizeWindow('image1', (int(im.shape[1] / 2), int(im.shape[0] / 2)))
cv2.moveWindow('image1', 40, 0)
cv2.setMouseCallback('image1', draw_part)
while (1):
cv2.imshow('image1', ims1)
k = cv2.waitKey(1) & 0xFF
if k == ord('q'):
break
cv2.destroyAllWindows()
C_parts_selected = parts[index]
return C_parts_selected, d
def handle(self, doc):
words = segment.seg(doc)
#words = swfilter.filter(list(words))
return list(words)
#!/usr/bin/env python3
import segment as sg
inputSylla = ""
output = ""
#print(sg.seg("ektygcmqcqlg"))
#print(sg.seg("wygdgdrndhqa"))
inputSylla = input()
while inputSylla != "#":
ans = sg.seg(inputSylla)
for i in range(0,len(ans)-1):
print(ans[i],end="")
print("")
inputSylla = input()
#print(sg.seg("wygdgdrndhqa"))
while True:
#read input
if inputSylla[-1] == "#":
inputSylla = ""
inp_ch = input("Please input char:")
if inp_ch != "" and inp_ch[0].isdigit():
#if input is a number
print("Choose :" + on_screen[int(inp_ch)][0] + str(on_screen[int(inp_ch)][1]))
output += on_screen[int(inp_ch)][0]
inputSylla = inputSylla[on_screen[int(inp_ch)][1]:]
else:
#update input Sylla
inputSylla += inp_ch
print(sg.seg(inputSylla))
#max incorrection pattern
screen = []
it = 4
counter = 0
flag = True
while it >= 0 and flag:
tp_list = []
for wubi_line in sg.wubi:
if wubi_line[0].startswith(inputSylla[0:it]):
wubi_code = int(wubi_line[1])
if wubi_code in sg.uni_map:
tp_list.append([sg.wd_map[wubi_code],it,sg.uni_map[wubi_code]])
counter += 1
pg.pg_init()
# 将教育经历的两个属性合并
'''for ele in segment.seg(pg.get_edu()):
print len(ele)'''
# 测试
'''for mlist in segment.seg(pg.get_edu()):
for ele in mlist:
for x in ele:
output_file.write(x+' ')
output_file.write('\t||\t')
output_file.write('\n')
'''
raw = list()
people = pg.get_edu(0, 0)
raw = map(lambda x: x[0] + x[1], segment.seg(people))
topic_model.build_lsi(raw)
'''topic_model._build_corpus(raw)
tfidf = topic_model._build_tfidf()
corpus_tfidf = tfidf[topic_model.corpus]
for ele in corpus_tfidf:
print ele
'''
'''for ele in topic_model.dictionary.token2id:
output_file.write(ele+' ')'''
# -*- encoding:"utf-8"-*-
# coding=utf-8
import tools
import segment
filename = "G:/Seg_AR/data/annotated"
segment.SENSORLIST = tools.getSensorList(filename)
seq_index = []
with open(filename, "r") as fr:
for line in fr:
row = line.split()
seq_index.append(segment.SENSORLIST.index(row[2]))
print len(seq_index)
borders = segment.seg(seq_index)
print len(borders)
print borders
from __future__ import absolute_import
import codecs
import segment
import pg
output_file = codecs.open("data/seg_data1.txt", 'wb', encoding='utf-8')
pg.pg_init()
# print segment.seg(pg.get_edu())
bias = 1000
counter = 0
raw = '1'
while len(raw) != 0:
raw = pg.get_edu(bias, counter)
for mlist in segment.seg(raw):
for ele in mlist:
for x in ele:
output_file.write(x+' ')
output_file.write('\t')
output_file.write('\n')
counter += 1
'''raw = pg.get_edu(bias, counter)
for mlist in segment.seg(raw):
for ele in mlist:
for x in ele:
output_file.write(x+' ')
output_file.write('\t||\t')
output_file.write('\n')'''
