lead_generator.py

def update_prospects(self):

    self.df_es = self.get_reviews(gt=True)
    nlp = spacy.load('en')
    nlp_sent = spacy.load('appreviews/appclass')
    matcher = Matcher(nlp.vocab)
    matcher.add("feednoun", None, [{POS: 'NOUN', 'LOWER': 'feed'}])
    matcher.add("follow", None, [{'LOWER': 'follow'}, {LEMMA: 'relation'}])
    matcher.add("follows", None, [{'LOWER': 'follow'}, {'LOWER': 'relationships'}])
    matcher.add("follows", None, [{'LOWER': 'follow'}, {LEMMA: 'relationships'}])

    prospect = {}
    for row in tqdm(self.df_es.index):
        text = self.df_es['text'][row]
        doc = nlp(text)
        for sent in doc.sents:
            #         print(sent)
            sent_an = sent.as_doc()
            matches = matcher(sent_an)
            if len(matches) > 0:
                sent = nlp_sent(doc.text).cats['NEG']
                if sent > 0.3:
                    already_pros = prospect.get(row)
                    if already_pros == 0 or already_pros is None:
                        prospect[row] = 1
                else:
                    already_pros = prospect.get(row)
                    if already_pros is None:
                        prospect[row] = 0
            else:
                already_pros = prospect.get(row)
                if already_pros is None:
                    prospect[row] = 0

    self.df_es['prospect'] = list(prospect.values())
    df_prospects = self.df_es[self.df_es['prospect'] == 1]