def getBadOfWords(sentence):
metapy.log_to_stderr()
doc = metapy.index.Document()
# doc.content("I said that I can't believe that it only costs $19.95!")
doc.content(sentence)
tok = metapy.analyzers.ICUTokenizer(suppress_tags=True)
tok.set_content(doc.content()) # this could be any string
# Here, we can see that the LengthFilter is consuming our original ICUTokenizer.
# It modifies the token stream by only emitting tokens
# that are of a minimum length of 2 and a maximum length of 30.
tok = metapy.analyzers.LengthFilter(tok, min=2, max=30)
tok.set_content(doc.content()) # this could be any string
# Stopword removal and stemming
tok = metapy.analyzers.ListFilter(tok, "lemur-stopwords.txt",
metapy.analyzers.ListFilter.Type.Reject)
tok.set_content(doc.content())
tokens = [token for token in tok]
cleanSentence = ""
for word in tokens:
cleanSentence += word
cleanSentence += " "
return cleanSentence
def test_upload_submission(self):
metapy.log_to_stderr()
"""
This is the unit test that actually submits the results to the
leaderboard. If there is an error (on either end of the submission),
the unit test is failed, and the failure string is also reproduced
on the leaderboard.
"""
req = {
'token': os.environ.get('GITLAB_API_TOKEN'),
'alias': os.environ.get('COMPETITION_ALIAS') or 'Anonymous',
'results': []
}
for cfg_file in self.cfgs:
res = {'error': None}
with open(cfg_file, 'r') as fin:
cfg_d = pytoml.load(fin)
res['dataset'] = cfg_d['dataset']
print("\nRunning on {}...".format(res['dataset']))
timeout_len = cfg_d['timeout']
try:
with Timeout(timeout_len):
res['results'] = self.get_results(cfg_file)
except Timeout.Timeout:
error_msg = "Timeout error: {}s".format(timeout_len)
res['error'] = error_msg
res['results'] = []
req['results'].append(res)
response = requests.post(self.submission_url, json=req)
jdata = response.json()
print(jdata)
self.assertTrue(jdata['submission_success'])
import metapy
metapy.log_to_stderr()
class TextProcessor:
keywords = {'About', 'WorkExperience', 'Education', 'Certificates', 'Awards', 'Groups'}
document = None
tokenizer = None
top_N = 5
frequency_map = dict()
sentence_token_map = dict()
def __init__(self, top_n=5):
self.document = metapy.index.Document()
self.tokenizer = metapy.analyzers.ICUTokenizer(suppress_tags=True)
self.tokenizer = metapy.analyzers.LengthFilter(self.tokenizer, min=2, max=30)
self.tokenizer = metapy.analyzers.ListFilter(self.tokenizer, \
"data/lemur-stopwords.txt",\
metapy.analyzers.ListFilter.Type.Reject)
self.top_N = top_n
def split_sentences(self, text):
sentences = []
if (text != None and text != ''):
for line in text.split('\n'):
if ('. ') in line and 'ltd. ' not in line.lower():
pieces = line.split('. ')
for piece in pieces:
sentences.append(piece)
else:
