def __init__(self, source, dest):
'''
Constructor
'''
self.src = source
self.dest = dest
self.Dep = DependencyReader()
self.Tree = ParseTreeReader()
self.Chunk = ChunkReader()
self.Stemmer = PorterStemmer()
def stem_string(line):
if line == "":
return ""
p = PorterStemmer()
word = ""
output = ""
for c in line:
if c.isalpha():
word += c.lower()
else:
if word:
output += p.stem(word, 0, len(word) - 1)
word = ''
output += c.lower()
if word:
output += p.stem(word, 0, len(word) - 1)
return output
def stem_string(line):
if line == "":
return ""
p = PorterStemmer()
word = ""
output = ""
for c in line:
if c.isalpha():
word += c.lower()
else:
if word:
output += p.stem(word, 0,len(word)-1)
word = ''
output += c.lower()
if word:
output += p.stem(word, 0,len(word)-1)
return output
def __init__(self, source, dest):
'''
Constructor
'''
self.src = source
self.dest = dest
self.Dep = DependencyReader()
self.Tree = ParseTreeReader()
self.Chunk = ChunkReader()
self.Stemmer = PorterStemmer()
def test(self, test_name):
Stemmer = PorterStemmer()
if test_name == "loading":
words = [
"induction", "inducted", "restimulated", "binding", "binds",
"up-regulate", "mRNA expression", "binding activity"
]
self.load("dev")
print "\n\n----------------------------"
print "Using original string"
for w in words:
cnt = self.count(w)
print w, cnt
print "\n\n----------------------------"
print "Using stem version of string"
for w in words:
w = Stemmer.stem(w, 0, len(w) - 1)
cnt = self.count(w)
print w, cnt
print "\n\n"
class GeniaReader(object):
'''
read all necessary file and convert it to internal format, then save it for latter feature extraction
'''
''' list of extension'''
TXT_EXT = ".txt"
PROTEIN_EXT = ".a1"
TRIGGER_REL_EXT = ".a2"
CHUNK_EXT = ".chk"
MCCCJ_TREE_EXT = ".txt.ss.mcccjtok.mcccj"
MCCCJ_SD_EXT = ".txt.ss.mcccjtok.mcccj.basic.sd"
CORPUS_DIR = ["dev", "train", "test"]
# this folder contains original corpus of bionlp2011: txt, a1, and a2 files
ORIGINAL_DIR = "original"
# this folder contains parsed corpus (tree and dependency) and also chunk file
PARSED_DIR = "parse"
# this folder contains pre-processed text, all proteins are replaced by placeholder
PREPROCESS_DIR = "preprocess"
# this folder contain data source for all docs
DATA_DIR = "data"
# bracket char coding
#BRACKET_CHAR = {'-LRB-':'(', '-RRB-':')', '-RSB-':']', '-LSB-':'[', '-LCB-':'{', '-RCB-':'}'}
def __init__(self, source, dest):
'''
Constructor
'''
self.src = source
self.dest = dest
self.Dep = DependencyReader()
self.Tree = ParseTreeReader()
self.Chunk = ChunkReader()
self.Stemmer = PorterStemmer()
def run(self):
# read all files from dir
for cdir in self.CORPUS_DIR:
print "reading content of " + cdir + " directory"
doc_ids = self.load_save_data(cdir)
print str(len(doc_ids)) + " doc have been read"
# write doc ids to file
fpath = self.dest + '/' + cdir + '_doc_ids.json'
self.write_to_file(doc_ids, fpath)
'''
this function returns list of doc_id for a given cdir
and do:
1. list files under cdir
2. load all necessary file for a given doc_id
3. check it consistency
4. save it as json
'''
def load_save_data(self, cdir):
ext = self.TXT_EXT
doc_ids = self.get_doc_list(
self.get_full_path(self.ORIGINAL_DIR, cdir), ext)
# there is a document that cannot be parsed by mcccj parser
# no event in that document, so we can just skip it
if cdir == "train":
print "Skip PMID-8632999"
doc_ids.remove("PMID-8632999")
for doc_id in doc_ids:
# load doc data
doc = self.load_doc(cdir, doc_id)
# check consistency
self.check_consistency(doc)
# save to file
fpath = self.dest + '/' + self.DATA_DIR + '/' + doc_id + '.json'
self.write_to_file(doc, fpath)
return doc_ids
'''
read document data
and return doc representation
'''
def load_doc(self, cdir, doc_id):
# init variable
triggers = []
events = []
equivs = []
is_test = True
# path for original file
ori_fpath = self.get_full_path(self.ORIGINAL_DIR, cdir) + '/' + doc_id
txt = self.get_text(ori_fpath + self.TXT_EXT)
proteins = self.get_protein(ori_fpath + self.PROTEIN_EXT)
if cdir != 'test':
triggers, events, equivs = self.get_trigger_relation(
ori_fpath + self.TRIGGER_REL_EXT)
is_test = False
# path for parsed file
parsed_fpath = self.get_full_path(self.PARSED_DIR, cdir) + '/' + doc_id
chunks = self.get_chunk(parsed_fpath + self.CHUNK_EXT)
tree = self.get_tree_mcccj(parsed_fpath + self.MCCCJ_TREE_EXT)
dep = self.get_dependency(parsed_fpath + self.MCCCJ_SD_EXT)
# path for preprocess file
pre_fpath = self.get_full_path(self.PREPROCESS_DIR,
cdir) + '/' + doc_id
sentences = self.get_sentences(pre_fpath + self.TXT_EXT)
# create doc representation
doc = {
"doc_id": doc_id,
"test": is_test,
"path1": ori_fpath,
"path2": parsed_fpath,
"nsen": len(tree),
"txt": txt,
"sen": sentences,
"protein": proteins,
"equiv": equivs,
"trigger": triggers,
"event": events,
"chunk": chunks,
"tree": tree,
"dep": dep
}
return doc
'''
update/add offset of word
offset is relative position in the abstract
and add stem of word
'''
def update_word_info(self, txt, sentences):
search_offset = 0
for sentence in sentences:
for word in sentence:
string = word["string"]
#if string in self.BRACKET_CHAR:
# string = self.BRACKET_CHAR[string]
start = txt.find(string, search_offset)
if start == -1:
# try to convert back " into ''
# in parser " are represented as '' so we need to convert back to original char
# but there are some cases that '' is actually '' as in => 4'',6-Diamidino-2-phenylindole
string = string.replace("\"", "\'\'")
start = txt.find(string, search_offset)
if start == -1:
print string
print sentence
raise ValueError("string not found")
word["string"] = string
end = start + len(string)
# add offset
word["start"] = start
word["end"] = end
# add stem using porter stemmer
word["stem"] = self.Stemmer.stem(string, 0, len(string) - 1)
search_offset = end
return sentences
'''
write to file
'''
def write_to_file(self, doc_to_write, fpath):
with open(fpath, 'w') as fout:
fout.write(json.dumps(doc_to_write))
'''
check consistency for chunk, tree, and dep data type
they must have same number of line and number of word for each line
'''
def check_consistency(self, doc):
chunck = doc["chunk"]
tree = doc["tree"]
dep = doc["dep"]
# check number of sentence
#print "number of sentence:", len(chunck), len(tree),len(dep)
if len(chunck) != len(tree) or len(tree) != len(dep):
raise ValueError(
"Chunck, Tree and Dep has different number of sentence")
# check number of line
for i in range(0, len(chunck)):
#print i, "number of words: ", chunck[i]["nword"], tree[i]["nword"], dep[i]["nword"]
if chunck[i]["nword"] != tree[i]["nword"] or tree[i][
"nword"] != dep[i]["nword"]:
print tree[i]
print chunck[i]
print dep[i]
raise ValueError("Different number of word in sentence " +
str(i) + " doc: " + doc["doc_id"])
'''
print to screen document representation
'''
def print_doc(self, doc):
print "doc id: ", doc["doc_id"]
print "is test: ", doc["test"]
print "ori path: ", doc["path1"]
print "parsed path: ", doc["path2"]
print "number of sentence:", doc["nsen"]
print doc["txt"]
print "Sentences:"
for sen in doc["sen"]:
print sen
print "Proteins:"
for line in doc["protein"].values():
print line
print "Equivs:"
for line in doc["equiv"]:
print line
print "Triggers:"
for line in doc["trigger"].values():
print line
print "Events:"
for line in doc["event"].values():
print line
print "Chunks:"
for line in doc["chunk"]:
print line
print "Trees:"
for line in doc["tree"]:
print line
print "Dependencies:"
for line in doc["dep"]:
print line
'''
return list of file names in cdir directory
'''
def get_doc_list(self, cdir, ext_filter):
return [
d.rstrip(ext_filter) for d in os.listdir(cdir)
if d.endswith(ext_filter)
]
'''
return text from txt file of given fpath
'''
def get_text(self, fpath):
with open(fpath, 'r') as fin:
txt = fin.read()
return txt
'''
return protein dict
pretein representation:
'T84' : ['T84', 'Negative_regulation', '2665', '2673', 'decrease']
'''
def get_protein(self, fpath):
proteins = {}
with open(fpath, 'r') as fin:
for line in fin:
line = line.rstrip('\n')
p = re.split("\\t|\\s+", line, 4)
proteins[p[0]] = p
return proteins
'''
return trigger dictionary, event dictionary and equiv tuple
trigger
id : (id, trigger type, start idx, end idx, trigger text)
event tuple
id : (id, event type, trigger_id, theme1 id, theme2 id, cause id)
equiv tuple: (protein1, protein2)
e
'''
def get_trigger_relation(self, fpath):
triggers = {}
events = {}
equivs = []
with open(fpath, 'r') as fin:
for line in fin:
line = line.rstrip('\n')
# process trigger
if line[0] == 'T':
t = re.split("\\t|\\s+", line, 4)
triggers[t[0]] = t
# process event
elif line[0] == 'E':
evt = re.split("\\t|\\s+", line)
eid = evt[0]
etype, _, trigid = evt[1].partition(':')
theme1 = evt[2].split(':')[1]
theme2 = ""
cause = ""
if len(evt) > 3:
argtype, _, argid = evt[3].partition(':')
if argtype == 'Theme2':
theme2 = argid
cause = ""
elif argtype == 'Cause':
theme2 = ""
cause = argid
events[eid] = list(
(eid, etype, trigid, theme1, theme2, cause))
# process equiv
elif line[0] == '*':
equiv = re.split("\\t|\\s", line)
equivs.append(tuple(equiv[2:]))
return triggers, events, equivs
'''
return chunk data
'''
def get_chunk(self, fpath):
return self.Chunk.read(fpath)
'''
return parse tree data
'''
def get_tree_mcccj(self, fpath):
return self.Tree.read(fpath)
'''
return sentences of a document
get_tree_mcccj must be called first
'''
def get_sentences(self, preprocess_txt_fpath, check=False):
pre_txt = self.get_text(preprocess_txt_fpath)
sentences = self.update_word_info(pre_txt, self.Tree.sentences)
if check:
for sentence in sentences:
for word in sentence:
if pre_txt[word["start"]:word["end"]] != word["string"]:
print pre_txt[word["start"]:word["end"]], "=>", word
#raise ValueError("string in txt and word do not match")
return sentences
'''
return dependency data
'''
def get_dependency(self, fpath):
return self.Dep.read(fpath)
'''
cdir: dev, train, or test
ctype: original or parsed
'''
def get_full_path(self, ctype, cdir):
return self.src + '/' + ctype + '/' + cdir
class GeniaReader(object):
'''
read all necessary file and convert it to internal format, then save it for latter feature extraction
'''
''' list of extension'''
TXT_EXT = ".txt"
PROTEIN_EXT = ".a1"
TRIGGER_REL_EXT = ".a2"
CHUNK_EXT = ".chk"
MCCCJ_TREE_EXT = ".txt.ss.mcccjtok.mcccj"
MCCCJ_SD_EXT = ".txt.ss.mcccjtok.mcccj.basic.sd"
CORPUS_DIR = ["dev","train","test"]
# this folder contains original corpus of bionlp2011: txt, a1, and a2 files
ORIGINAL_DIR = "original"
# this folder contains parsed corpus (tree and dependency) and also chunk file
PARSED_DIR = "parse"
# this folder contains pre-processed text, all proteins are replaced by placeholder
PREPROCESS_DIR = "preprocess"
# this folder contain data source for all docs
DATA_DIR = "data"
# bracket char coding
#BRACKET_CHAR = {'-LRB-':'(', '-RRB-':')', '-RSB-':']', '-LSB-':'[', '-LCB-':'{', '-RCB-':'}'}
def __init__(self, source, dest):
'''
Constructor
'''
self.src = source
self.dest = dest
self.Dep = DependencyReader()
self.Tree = ParseTreeReader()
self.Chunk = ChunkReader()
self.Stemmer = PorterStemmer()
def run(self):
# read all files from dir
for cdir in self.CORPUS_DIR:
print "reading content of " + cdir + " directory"
doc_ids = self.load_save_data(cdir)
print str(len(doc_ids)) + " doc have been read"
# write doc ids to file
fpath = self.dest + '/' + cdir + '_doc_ids.json'
self.write_to_file(doc_ids, fpath)
'''
this function returns list of doc_id for a given cdir
and do:
1. list files under cdir
2. load all necessary file for a given doc_id
3. check it consistency
4. save it as json
'''
def load_save_data(self, cdir):
ext = self.TXT_EXT
doc_ids = self.get_doc_list(self.get_full_path(self.ORIGINAL_DIR,cdir), ext)
# there is a document that cannot be parsed by mcccj parser
# no event in that document, so we can just skip it
if cdir == "train":
print "Skip PMID-8632999"
doc_ids.remove("PMID-8632999")
for doc_id in doc_ids:
# load doc data
doc = self.load_doc(cdir, doc_id)
# check consistency
self.check_consistency(doc)
# save to file
fpath = self.dest + '/' + self.DATA_DIR + '/' + doc_id + '.json'
self.write_to_file(doc, fpath)
return doc_ids
'''
read document data
and return doc representation
'''
def load_doc(self, cdir, doc_id):
# init variable
triggers = []
events = []
equivs = []
is_test = True
# path for original file
ori_fpath = self.get_full_path(self.ORIGINAL_DIR,cdir) + '/' + doc_id
txt = self.get_text(ori_fpath + self.TXT_EXT)
proteins = self.get_protein(ori_fpath + self.PROTEIN_EXT)
if cdir != 'test':
triggers, events, equivs = self.get_trigger_relation(ori_fpath + self.TRIGGER_REL_EXT)
is_test = False
# path for parsed file
parsed_fpath = self.get_full_path(self.PARSED_DIR,cdir) + '/' + doc_id
chunks = self.get_chunk(parsed_fpath + self.CHUNK_EXT)
tree = self.get_tree_mcccj(parsed_fpath + self.MCCCJ_TREE_EXT)
dep = self.get_dependency(parsed_fpath + self.MCCCJ_SD_EXT)
# path for preprocess file
pre_fpath = self.get_full_path(self.PREPROCESS_DIR, cdir) + '/' + doc_id
sentences = self.get_sentences(pre_fpath + self.TXT_EXT)
# create doc representation
doc = {"doc_id": doc_id,
"test": is_test,
"path1": ori_fpath,
"path2": parsed_fpath,
"nsen": len(tree),
"txt":txt,
"sen": sentences,
"protein":proteins,
"equiv":equivs,
"trigger":triggers,
"event":events,
"chunk":chunks,
"tree":tree,
"dep":dep}
return doc
'''
update/add offset of word
offset is relative position in the abstract
and add stem of word
'''
def update_word_info(self, txt, sentences):
search_offset = 0
for sentence in sentences:
for word in sentence:
string = word["string"]
#if string in self.BRACKET_CHAR:
# string = self.BRACKET_CHAR[string]
start = txt.find(string, search_offset)
if start == -1:
# try to convert back " into ''
# in parser " are represented as '' so we need to convert back to original char
# but there are some cases that '' is actually '' as in => 4'',6-Diamidino-2-phenylindole
string = string.replace("\"","\'\'")
start = txt.find(string, search_offset)
if start == -1:
print string
print sentence
raise ValueError("string not found")
word["string"] = string
end = start + len(string)
# add offset
word["start"] = start
word["end"] = end
# add stem using porter stemmer
word["stem"] = self.Stemmer.stem(string, 0, len(string)-1)
search_offset = end
return sentences
'''
write to file
'''
def write_to_file(self, doc_to_write, fpath):
with open(fpath, 'w') as fout:
fout.write(json.dumps(doc_to_write))
'''
check consistency for chunk, tree, and dep data type
they must have same number of line and number of word for each line
'''
def check_consistency(self, doc):
chunck = doc["chunk"]
tree = doc["tree"]
dep = doc["dep"]
# check number of sentence
#print "number of sentence:", len(chunck), len(tree),len(dep)
if len(chunck) != len(tree) or len(tree) != len(dep):
raise ValueError("Chunck, Tree and Dep has different number of sentence")
# check number of line
for i in range(0,len(chunck)):
#print i, "number of words: ", chunck[i]["nword"], tree[i]["nword"], dep[i]["nword"]
if chunck[i]["nword"] != tree[i]["nword"] or tree[i]["nword"] != dep[i]["nword"]:
print tree[i]
print chunck[i]
print dep[i]
raise ValueError("Different number of word in sentence " + str(i) + " doc: " + doc["doc_id"])
'''
print to screen document representation
'''
def print_doc(self, doc):
print "doc id: ", doc["doc_id"]
print "is test: ", doc["test"]
print "ori path: ", doc["path1"]
print "parsed path: ", doc["path2"]
print "number of sentence:", doc["nsen"]
print doc["txt"]
print "Sentences:"
for sen in doc["sen"]:
print sen
print "Proteins:"
for line in doc["protein"].values():
print line
print "Equivs:"
for line in doc["equiv"]:
print line
print "Triggers:"
for line in doc["trigger"].values():
print line
print "Events:"
for line in doc["event"].values():
print line
print "Chunks:"
for line in doc["chunk"]:
print line
print "Trees:"
for line in doc["tree"]:
print line
print "Dependencies:"
for line in doc["dep"]:
print line
'''
return list of file names in cdir directory
'''
def get_doc_list(self, cdir, ext_filter):
return [d.rstrip(ext_filter) for d in os.listdir(cdir) if d.endswith(ext_filter)]
'''
return text from txt file of given fpath
'''
def get_text(self, fpath):
with open(fpath, 'r') as fin:
txt = fin.read()
return txt
'''
return protein dict
pretein representation:
'T84' : ['T84', 'Negative_regulation', '2665', '2673', 'decrease']
'''
def get_protein(self, fpath):
proteins = {}
with open(fpath, 'r') as fin:
for line in fin:
line = line.rstrip('\n')
p = re.split("\\t|\\s+",line,4)
proteins[p[0]] = p
return proteins
'''
return trigger dictionary, event dictionary and equiv tuple
trigger
id : (id, trigger type, start idx, end idx, trigger text)
event tuple
id : (id, event type, trigger_id, theme1 id, theme2 id, cause id)
equiv tuple: (protein1, protein2)
e
'''
def get_trigger_relation(self, fpath):
triggers = {}
events = {}
equivs = []
with open(fpath, 'r') as fin:
for line in fin:
line = line.rstrip('\n')
# process trigger
if line[0] == 'T':
t = re.split("\\t|\\s+",line,4)
triggers[t[0]] = t
# process event
elif line[0] == 'E':
evt = re.split("\\t|\\s+",line)
eid = evt[0]
etype,_,trigid = evt[1].partition(':')
theme1 = evt[2].split(':')[1]
theme2 = ""
cause = ""
if len(evt) > 3:
argtype,_,argid = evt[3].partition(':')
if argtype == 'Theme2':
theme2 = argid
cause = ""
elif argtype == 'Cause':
theme2 = ""
cause = argid
events[eid] = list((eid, etype, trigid, theme1, theme2, cause))
# process equiv
elif line[0] == '*':
equiv = re.split("\\t|\\s",line)
equivs.append(tuple(equiv[2:]))
return triggers, events, equivs
'''
return chunk data
'''
def get_chunk(self, fpath):
return self.Chunk.read(fpath)
'''
return parse tree data
'''
def get_tree_mcccj(self, fpath):
return self.Tree.read(fpath)
'''
return sentences of a document
get_tree_mcccj must be called first
'''
def get_sentences(self, preprocess_txt_fpath, check = False):
pre_txt = self.get_text(preprocess_txt_fpath)
sentences = self.update_word_info(pre_txt, self.Tree.sentences)
if check:
for sentence in sentences:
for word in sentence:
if pre_txt[word["start"]:word["end"]] != word["string"]:
print pre_txt[word["start"]:word["end"]], "=>", word
#raise ValueError("string in txt and word do not match")
return sentences
'''
return dependency data
'''
def get_dependency(self, fpath):
return self.Dep.read(fpath)
'''
cdir: dev, train, or test
ctype: original or parsed
'''
def get_full_path(self, ctype, cdir):
return self.src + '/' + ctype + '/' + cdir
def __init__(self, source):
super(TriggerDictionary, self).__init__(source)
self.Stemmer = PorterStemmer()
class TriggerDictionary(Dictionary):
def __init__(self, source):
super(TriggerDictionary, self).__init__(source)
self.Stemmer = PorterStemmer()
def load(self, corpus_dir):
"""
Load a trigger dictionary data
corpus_dir is dev, train, or mix
"""
if corpus_dir not in self.CORPUS_DIR:
raise ValueError("wrong value. choose 'dev', 'train', or 'mix'")
fpath = self.src + '/' + self.DICT_DIR + '/' + corpus_dir + self.TDICT_SUFIX_EXT
if not os.path.exists(fpath):
print "Trigger dictionary data is not exist"
print "Now building new trigger dictionary data ..."
self.build()
with open(fpath, 'r') as f:
self.data = json.loads(f.read())
def count(self, word, ttype=""):
"""
return number of word occurrence in dictionary
"""
if self.data == {}:
raise ValueError("Dictionary data has not been loaded")
# get counter
ttype_cnt = self.data.get(word.lower(), None)
retval = 0
if ttype_cnt != None:
if ttype != "":
retval = ttype_cnt.get(ttype, 0)
else:
# get count for all event type
for v in ttype_cnt.itervalues():
retval += v
return retval
def build(self):
"""
build all trigger dictionaries (dev, train, and mix)
and save it to dict folder
"""
for cdir in self.CORPUS_DIR:
print "building " + cdir + " trigger dictionary"
fpath = self.src + '/' + self.DICT_DIR + '/' + cdir + self.TDICT_SUFIX_EXT
with open(fpath, 'w') as f:
f.write(json.dumps(self.build_dict(cdir)))
def build_dict(self, corpus_dir):
"""
add trigger word to dictionary, including multi-word trigger
ex.
triggers: "Negative Regulator", "Expression"
store in dict:
"Negative Regulator" <== bigram version
"Negative" <== head of bigram
"Expression" <== standard unigram
"""
if corpus_dir not in self.CORPUS_DIR:
raise ValueError("wrong value. choose 'dev', 'train', or 'mix'")
# init document builder
doc_builder = DocumentBuilder(self.src)
# init default dict with counter
td = defaultdict(Counter)
# get list of document
doc_ids = self.get_doc_ids(corpus_dir)
for doc_id in doc_ids:
o_doc = doc_builder.build(doc_id)
for i in range(0, len(o_doc.sen)):
o_sen = o_doc.sen[i]
for twn in o_sen.trigger:
w = o_sen.words[twn]
ttype = w['type']
string = w['string'].lower()
stem = w['stem'].lower()
# skip short word
if len(string) < 4: continue
# adding unigram text and stem to dictionary
td[string][ttype] += 1
td[stem][ttype] += 1
# check full text
# add to dict if it's multi-word
full_string = o_sen.trigger_text[twn]
if ' ' in full_string:
td[full_string][ttype] += 1
print "the dictionary contains:", len(td), "trigger words"
return dict(td)
def get_triggers(self, doc_id):
"""
return list of trigger from document
"""
fpath = self.src + '/' + self.DATA_DIR + '/' + doc_id + self.DATA_EXT
with open(fpath, 'r') as f:
doc = json.loads(f.read())
return doc["trigger"]
def test(self, test_name):
if test_name == "loading":
trigger = {
"Negative Regulator": "Negative_regulation",
"Negative": "Negative_regulation",
"Regulator": "Negative_regulation",
"binds": "Binding",
"mRNA expression": "Transcription",
"mRNA": "Transcription"
}
print "\n\n----------------------------"
print "Using original string"
self.load("mix")
for t, ttype in trigger.iteritems():
cnt1 = self.count(t)
cnt2 = self.count(t, ttype)
print t, "All", cnt1
print t, ttype, cnt2
print "\n\n----------------------------"
print "Using stem version of string"
for t, ttype in trigger.iteritems():
t = self.Stemmer.stem(t, 0, len(t) - 1)
cnt1 = self.count(t)
cnt2 = self.count(t, ttype)
print t, "All", cnt1
print t, ttype, cnt2
print "\n\n"