keywords.py

import nltk
nltk.download('stopwords')
nltk.download('wordnet')
nltk.download('punkt')
from nltk.corpus import stopwords,wordnet
from nltk.tokenize import sent_tokenize
from flashtext import KeywordProcessor
import regex as re
import string
import subprocess
import logging

try:
    import pke
    logging.error("importing pke info")
except:
    logging.error("installing pke info")
    subprocess.run(['pip3', 'install','git+https://github.com/boudinfl/pke.git'])
    subprocess.run(['python3' ,'-m' ,'spacy' ,'download' ,'en'])
    import pke


def tokenize_sentence(text):
    sentences=sent_tokenize(text)
    sentences=[s.strip().lstrip().rstrip() for s in sentences if len(s) > 20]
    return sentences

def get_noun_adj_verb(text):
    output = []
    try:
        extractor = pke.unsupervised.MultipartiteRank()
        extractor.load_document(input=text, language='en',normalization=None)
        # keyphrase candidate selection #'ADJ' 'ADP' 'ADV' 'AUX' 'DET' 'NOUN' 'NUM' 'PART' 'PROPN' 'PUNCT' 'VERB'
        extractor.candidate_selection(pos={'NOUN', 'VERB', 'ADJ'})

        # candidate weighting,
        extractor.candidate_weighting(threshold=0.9,method='average',alpha=1.1)

        #extract top n
        keyphrases = extractor.get_n_best(n=5)

        for val in keyphrases:
            output.append(val[0])
    except Exception as e:
        print("found exception",e)
    return list(set(output))