thesis-anne/NER.py

'''
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

import matplotlib.pyplot as plt
from nltk.tag import StanfordNERTagger
from nltk.tokenize import word_tokenize

class NER:

    def tag_words(text):
        stanford_classifier = 'C:\\Users\\anne.lorenz\\Bachelorarbeit\\StanfordNER\\stanford-ner-2018-02-27\\classifiers\\english.all.3class.distsim.crf.ser.gz'
        stanford_ner_path = 'C:\\Users\\anne.lorenz\\Bachelorarbeit\\StanfordNER\\stanford-ner-2018-02-27\\stanford-ner.jar'
        # create tagger object
        st = StanfordNERTagger(stanford_classifier, stanford_ner_path, encoding='utf-8')

        tokenized_text = word_tokenize(text)
        tagged_words = st.tag(tokenized_text)
        # returns list of tuples (word, tag)
        return tagged_words

    def get_coherent_names(tagged_words):
        continuous_chunk = []
        current_chunk = []

        for token, tag in tagged_words:
            if tag != "O":
                current_chunk.append((token, tag))
            else:
                # if current chunk is not empty
                if current_chunk: 
                    continuous_chunk.append(current_chunk)
                    current_chunk = []
        # put the final current_chunk into the continuous_chunk (if any)
        if current_chunk:
            continuous_chunk.append(current_chunk)
        return continuous_chunk

    def plot_barchart():
        organizations = ['org1', 'org2', 'org3', 'org4', 'org5', 'org6']
        num_mentions = [5, 2, 33, 12, 6, 10]
        #n, bins, patches = plt.hist(num_mentions, 6, normed=1, facecolor='green')
        plt.plot(organizations, num_mentions, 'ro', ms = 10)
        plt.xlabel('companies')
        plt.ylabel('count')
        plt.title('Company mentions in articles')
        plt.grid(True)
        plt.show()

    def find_companies(text):
        #set paths
        java_path = "C:\\Program Files (x86)\\Java\\jre1.8.0_181"
        os.environ['JAVAHOME'] = java_path

        organizations = []
        # create list of (word, tag) tuples
        tagged_words = NER.tag_words(text)
        # put coherent names together
        nes = NER.get_coherent_names(tagged_words)
        nes_coherent = [(" ".join([token for token, tag in ne]), ne[0][1]) for ne in nes]
        #print(nes_coherent)
        for tuple in nes_coherent:
            if tuple[1] == 'ORGANIZATION':
                organizations.append(tuple[0])
        return organizations

if __name__ == '__main__':

    #plot_barchart()
    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.'''
    print(NER.find_companies(text))