def parse(self, text):
# lowercase query
text = text.lower()
tokens = tokenize(text)
# remove stopwords
tokens = [token for token in tokens if token not in self.stopwords]
return tokens
def __init__(self):
self.trie = TokenTrie(name="disease")
if self.trie.is_empty():
diseases_file = open(os.path.join(*[os.path.dirname(__file__), 'data', 'UMLS', 'diseases.txt']))
disease_names = diseases_file.read().split('\n')
count = 0
for disease in disease_names:
self.trie.add(tokenize(disease))
print disease
count += 1
self.trie.save_to_cache()
def __init__(self):
self.trie = TokenTrie(name="symptoms")
if self.trie.is_empty():
symptoms_file = open(os.path.join(*[os.path.dirname(__file__), 'data', 'UMLS', 'diseases.txt']))
symptoms = symptoms_file.read().split('\n')
count = 0
for symptom in symptoms:
(code, name) = symptom.split("\t")
self.trie.add(tokenize(name))
print name
count += 1
self.trie.save_to_cache()
def __init__(self):
self.trie = TokenTrie(name="disease")
if self.trie.is_empty():
diseases_file = open(
os.path.join(*[
os.path.dirname(__file__), 'data', 'UMLS', 'diseases.txt'
]))
disease_names = diseases_file.read().split('\n')
count = 0
for disease in disease_names:
self.trie.add(tokenize(disease))
print disease
count += 1
self.trie.save_to_cache()
def __init__(self):
self.trie = TokenTrie(name="symptoms")
if self.trie.is_empty():
symptoms_file = open(
os.path.join(*[
os.path.dirname(__file__), 'data', 'UMLS', 'diseases.txt'
]))
symptoms = symptoms_file.read().split('\n')
count = 0
for symptom in symptoms:
(code, name) = symptom.split("\t")
self.trie.add(tokenize(name))
print name
count += 1
self.trie.save_to_cache()
def extract(self, text):
sequences = self.trie.scan(tokenize(text))
# assemble sequences into tokens
return [" ".join(seq) for seq in sequences]
def extract(self, text):
sequences = self.trie.scan(tokenize(text))
# assemble sequences into tokens
return [" ".join(seq) for seq in sequences]
