def txt2matrix_fortrain(ann_dir,mytrain,tag_included,filename,curpath):
txt_files=readfromdir.get_file_list(ann_dir,['txt'])
print "there's "+ str(len(txt_files))+" in total!"
i=0
for txt_file in txt_files:
i+=1
# read files
myraw=codecs.open(txt_file).read()
match=re.search('^(.*)\.txt',txt_file)
name=match.group(1)
ann_file=name+'_new.ann'
print "reading file from",txt_file,ann_file,"..."
myann=codecs.open(ann_file,"r")
#print myann
# output features
text_tagged=labeling.ann_tagging(myann,myraw,tag_included)
lines=" ".join(text_tagged.split(r'[;\n]'))
sents=nltk.sent_tokenize(lines)
lines=" ### ".join(sents)
term_list, tag_list,index_list=t2c.txt2conll(lines,1) # "1" here represents it's a training texts with annoatioin; "0" represents raw texts
sents=" ".join(term_list).split("###")
type_list=[]
pos_list=[]
# extract umls concepts:
j=0
for sent in sents:
if j>=len(term_list):
break
metamap_output=umls_identify.formating_for_metamap(curpath,sent,filename)
one_sent_term,type_list=umls_identify.label_umls_cui(metamap_output,sent)
pos_list=POS.pos_tagging(one_sent_term)
pos_list.append(".")
type_list.append("O")
terms=sent.split()
sent_id=0
for t in terms:
if term_list[j]== "###":
j=j+1
term=term_list[j]
lemma=st.stem(term)
#vector=word2vec.ouput_embedding(model,term.lower(),50)
bc=BrownClustering.bc_indexing(term.lower(),bc_index)
print>> mytrain, term_list[j]+"\t"+lemma+"\t"+pos_list[sent_id]+"\t"+type_list[sent_id]+"\t"+bc+"\t"+index_list[j]+"\t"+tag_list[j]
sent_id+=1
j=j+1
print>>mytrain
if i%5==0:
print str(i) +" files finished"
def txt2matrix_fortrain(ann_dir, mytrain, tag_included, filename, curpath):
txt_files = readfromdir.get_file_list(ann_dir, ['txt'])
print "there's " + str(len(txt_files)) + " in total!"
i = 0
for txt_file in txt_files:
i += 1
# read files
myraw = codecs.open(txt_file).read()
match = re.search('^(.*)\.txt', txt_file)
name = match.group(1)
ann_file = name + '_new.ann'
print "reading file from", txt_file, ann_file, "..."
myann = codecs.open(ann_file, "r")
#print myann
# output features
text_tagged = labeling.ann_tagging(myann, myraw, tag_included)
lines = " ".join(text_tagged.split(r'[;\n]'))
sents = nltk.sent_tokenize(lines)
lines = " ### ".join(sents)
term_list, tag_list, index_list = t2c.txt2conll(
lines, 1
) # "1" here represents it's a training texts with annoatioin; "0" represents raw texts
sents = " ".join(term_list).split("###")
type_list = []
pos_list = []
# extract umls concepts:
j = 0
for sent in sents:
if j >= len(term_list):
break
metamap_output = umls_identify.formating_for_metamap(
curpath, sent, filename)
one_sent_term, type_list = umls_identify.label_umls_cui(
metamap_output, sent)
pos_list = POS.pos_tagging(one_sent_term)
pos_list.append(".")
type_list.append("O")
terms = sent.split()
sent_id = 0
for t in terms:
if term_list[j] == "###":
j = j + 1
term = term_list[j]
lemma = st.stem(term)
#vector=word2vec.ouput_embedding(model,term.lower(),50)
bc = BrownClustering.bc_indexing(term.lower(), bc_index)
print >> mytrain, term_list[j] + "\t" + lemma + "\t" + pos_list[
sent_id] + "\t" + type_list[
sent_id] + "\t" + bc + "\t" + index_list[
j] + "\t" + tag_list[j]
sent_id += 1
j = j + 1
print >> mytrain
if i % 5 == 0:
print str(i) + " files finished"