63 lines
3.3 KiB
Python
63 lines
3.3 KiB
Python
'''
|
|
Named Entity Recognition (NER)
|
|
==============================
|
|
|
|
Stanford NER takes a text as input and returns a list of entities
|
|
like persons, organizations and countries, e.g.
|
|
'''
|
|
|
|
import os
|
|
|
|
from nltk.tag import StanfordNERTagger
|
|
from nltk.tokenize import word_tokenize
|
|
|
|
class NER:
|
|
#set paths
|
|
java_path = "C:\\Program Files (x86)\\Java\\jre1.8.0_181"
|
|
os.environ['JAVAHOME'] = java_path
|
|
|
|
stanford_classifier = 'C:\\Users\\anne.lorenz\\Bachelorarbeit\\Stanford'
|
|
'NER\\stanford-ner-2018-02-27\\classifiers\\english.all.3class.distsim.crf.ser.gz'
|
|
stanford_ner_path = 'C:\\Users\\anne.lorenz\\Bachelorarbeit\\Stanford'
|
|
'NER\\stanford-ner-2018-02-27\\stanford-ner.jar'
|
|
|
|
def search_organizations(text):
|
|
# create tagger object
|
|
st = StanfordNERTagger(stanford_classifier, stanford_ner_path, encoding='utf-8')
|
|
|
|
tokenized_text = word_tokenize(text)
|
|
classified_text = st.tag(tokenized_text)
|
|
return classified_text
|
|
|
|
if __name__ == '__main__':
|
|
text = '''BANGKOK, Sept 22 (Reuters) - Southeast Asian stock markets
|
|
\nmostly fell in light volumes on Tuesday as energy shares
|
|
tracked \nfalls in global oil prices, while weaknesses in banking shares
|
|
\namid concerns about loans to an ailing steel firm sent the Thai
|
|
\nindex to a one-week closing low. \nBangkok's SET index shed nearly
|
|
1 percent after four \nsessions of gains. The index closed at 1,379.32,
|
|
its lowest \nclosing since Sept. 15. \nShares of Krung Thai Bank Pcl,
|
|
the most actively \ntraded by turnover, dropped 2.8 percent to a near
|
|
one-month low, \nreflecting potential impact of loans to Sahaviriya Steel
|
|
\nIndustries Pcl on the bank's earnings. \nMaybank Kim Eng Securities
|
|
downgraded Krung Thai Bank to \n\"hold\" from \"buy\". \n\"Even as exposure
|
|
to SSI loans will be fully provisioned, \nKTB's NPL coverage will still be
|
|
lower than 130 percent, the \ndesired level we think and hence the need for
|
|
more provisioning \nin the following quarters,\" the broker said in a report.
|
|
\nSSI shares plunged 20 percent and Siam Commercial Bank \n, among its
|
|
creditors, dropped 1 percent. The steel firm \nand its three creditors
|
|
agreed on Monday to consider options to \nrestructure debt worth over
|
|
50 billion baht ($1.40 \nbillion). \nStocks in Malaysia extended their
|
|
slides for a third \nsession, Singapore gave up early gains and Indonesia
|
|
\nhit a near one-week low, all with trading volumes below \nthe 30-day
|
|
average ahead of a public holiday on Thursday. \nAmong top losers in the
|
|
region, Indonesia's Perusahaan Gas \nNegara was down 4.4 percent and
|
|
Singapore's Keppel \nCorp was down 2.5 percent as crude oil prices fell
|
|
\namid uncertainty over global demand. \nFor Asian Companies click.'''
|
|
|
|
classified_text = search_organizations(text)
|
|
|
|
# print organizations
|
|
for tuple in classified_text:
|
|
if tuple[1] == "ORGANIZATION":
|
|
print(tuple) |