def save_noun(doc_clean, language):
if language == 'en':
new_doc = []
for doc in doc_clean:
tagged = nltk.pos_tag(doc)
for (word, tag) in tagged:
if not tag.startswith("N"):
doc.remove(word)
else:
continue
new_doc.append(doc)
return new_doc
elif language == 'nl':
nlp = nl_core_news_sm.load()
new_doc = []
for doc in doc_clean:
doc_for_tagging = nlp(doc)
for word in doc_for_tagging:
if str(word) in [
"wer", "wel", "mooi", "onz", "gan", "mak",
"waarschijn", "leuk", "hel"
]:
doc = doc.replace(str(word) + " ", "")
else:
continue
tag = word.pos_
if not tag == "NOUN":
doc = doc.replace(str(word) + " ", "")
else:
continue
new_doc.append(doc)
return new_doc
def extract_tag(text):
nouns = []
nlp = nl_core_news_sm.load()
doc = nlp(text)
for token in doc:
if token.head.pos == NOUN:
nouns.append(("%s %s" % (token.text, token.head.text)).lower())
return nouns
trg[1:].view(-1))
epoch_loss += loss.item()
return epoch_loss / len(iterator)
if __name__ == '__main__':
SEED = 1234
random.seed(SEED)
torch.manual_seed(SEED)
torch.cuda.manual_seed(SEED)
torch.backends.cudnn.deterministic = True
Multi30k.download('data')
spacy_de = nl_core_news_sm.load()
spacy_en = en_core_web_sm.load()
SRC = Field(tokenize=tokenize_de,
init_token='<sos>',
eos_token='<eos>',
lower=True)
TRG = Field(tokenize=tokenize_en,
init_token='<sos>',
eos_token='<eos>',
lower=True)
train, valid, test = TranslationDataset.splits(path='./data/multi30k/',
exts=['.de', '.en'],
fields=[('src', SRC),
('trg', TRG)],
def check_spacy_models(main, lang, pipeline):
if pipeline == 'word_tokenization':
nlp_pipelines = []
nlp_disable = ['tagger', 'parser', 'ner']
elif pipeline in ['sentence_tokenization', 'tokenization']:
nlp_pipelines = ['sentencizer']
nlp_disable = ['tagger', 'parser', 'ner']
elif pipeline in ['pos_tagging', 'lemmatization']:
nlp_pipelines = ['tagger']
nlp_disable = ['parser', 'ner']
# Languages with models
if lang in [
'nld', 'eng', 'fra', 'deu', 'ell', 'ita', 'por', 'spa', 'other'
]:
if f'spacy_nlp_{lang}' in main.__dict__:
if main.__dict__[f'spacy_nlp_{lang}'].pipe_names != nlp_pipelines:
del main.__dict__[f'spacy_nlp_{lang}']
if f'spacy_nlp_{lang}' not in main.__dict__:
# Dutch
if lang == 'nld':
import nl_core_news_sm
main.__dict__[f'spacy_nlp_{lang}'] = nl_core_news_sm.load(
disable=nlp_disable)
# English
elif lang == 'eng':
import en_core_web_sm
main.__dict__[f'spacy_nlp_{lang}'] = en_core_web_sm.load(
disable=nlp_disable)
# French
elif lang == 'fra':
import fr_core_news_sm
main.__dict__[f'spacy_nlp_{lang}'] = fr_core_news_sm.load(
disable=nlp_disable)
# German
elif lang == 'deu':
import de_core_news_sm
main.__dict__[f'spacy_nlp_{lang}'] = de_core_news_sm.load(
disable=nlp_disable)
# Greek (Modern)
elif lang == 'ell':
import el_core_news_sm
main.__dict__[f'spacy_nlp_{lang}'] = el_core_news_sm.load(
disable=nlp_disable)
# Italian
elif lang == 'ita':
import it_core_news_sm
main.__dict__[f'spacy_nlp_{lang}'] = it_core_news_sm.load(
disable=nlp_disable)
# Portuguese
elif lang == 'por':
import pt_core_news_sm
main.__dict__[f'spacy_nlp_{lang}'] = pt_core_news_sm.load(
disable=nlp_disable)
# Spanish
elif lang == 'spa':
import es_core_news_sm
main.__dict__[f'spacy_nlp_{lang}'] = es_core_news_sm.load(
disable=nlp_disable)
# Other Languages
elif lang == 'other':
import en_core_web_sm
main.__dict__[f'spacy_nlp_{lang}'] = en_core_web_sm.load(
disable=nlp_disable)
# Languages without models
else:
# Serbian (Cyrillic) & Serbian (Latin)
if lang in ['srp_cyrl', 'srp_latn']:
main.__dict__['spacy_nlp_srp_cyrl'] = spacy.blank('rs')
main.__dict__['spacy_nlp_srp_latn'] = spacy.blank('rs')
else:
main.__dict__[f'spacy_nlp_{lang}'] = spacy.blank(
wordless_conversion.to_iso_639_1(main, lang))
if 'sentencizer' in nlp_pipelines:
nlp = main.__dict__[f'spacy_nlp_{lang}']
if 'sentencizer' not in nlp.pipe_names:
nlp.add_pipe(nlp.create_pipe('sentencizer'))
def check_spacy_models(main, lang, pipeline):
if lang == 'other':
lang = 'eng'
if pipeline == 'word_tokenization':
nlp_pipelines = []
nlp_disable = ['tagger', 'parser', 'ner']
elif pipeline in ['tokenization', 'sentence_tokenization']:
nlp_pipelines = ['sbd']
nlp_disable = ['tagger', 'parser', 'ner']
elif pipeline in ['pos_tagging', 'lemmatization']:
nlp_pipelines = ['tagger']
nlp_disable = ['parser', 'ner']
if lang in ['nld', 'eng', 'fra', 'deu', 'ell', 'ita', 'por', 'spa']:
if f'spacy_nlp_{lang}' in main.__dict__:
if main.__dict__[f'spacy_nlp_{lang}'].pipe_names != nlp_pipelines:
del main.__dict__[f'spacy_nlp_{lang}']
if f'spacy_nlp_{lang}' not in main.__dict__:
# Dutch
if lang == 'nld':
import nl_core_news_sm
main.__dict__[f'spacy_nlp_{lang}'] = nl_core_news_sm.load(
disable=nlp_disable)
# English
elif lang == 'eng':
import en_core_web_sm
main.__dict__[f'spacy_nlp_{lang}'] = en_core_web_sm.load(
disable=nlp_disable)
# French
elif lang == 'fra':
import fr_core_news_sm
main.__dict__[f'spacy_nlp_{lang}'] = fr_core_news_sm.load(
disable=nlp_disable)
# German
elif lang == 'deu':
import de_core_news_sm
main.__dict__[f'spacy_nlp_{lang}'] = de_core_news_sm.load(
disable=nlp_disable)
# Greek (Modern)
elif lang == 'ell':
import el_core_news_sm
main.__dict__[f'spacy_nlp_{lang}'] = el_core_news_sm.load(
disable=nlp_disable)
# Italian
elif lang == 'ita':
import it_core_news_sm
main.__dict__[f'spacy_nlp_{lang}'] = it_core_news_sm.load(
disable=nlp_disable)
# Portuguese
elif lang == 'por':
import pt_core_news_sm
main.__dict__[f'spacy_nlp_{lang}'] = pt_core_news_sm.load(
disable=nlp_disable)
# Spanish
elif lang == 'spa':
import es_core_news_sm
main.__dict__[f'spacy_nlp_{lang}'] = es_core_news_sm.load(
disable=nlp_disable)
if 'sbd' in nlp_pipelines:
nlp = main.__dict__[f'spacy_nlp_{lang}']
if 'sbd' not in nlp.pipe_names:
nlp.add_pipe(nlp.create_pipe('sentencizer'))
nlp_en = en_core_web_sm.load()
import de_core_news_sm
nlp_de = de_core_news_sm.load()
import es_core_news_sm
nlp_es = es_core_news_sm.load()
import it_core_news_sm
nlp_it = it_core_news_sm.load()
import pt_core_news_sm
nlp_pt = pt_core_news_sm.load()
import nl_core_news_sm
nlp_nl = nl_core_news_sm.load()
# global variables
wnl = WordNetLemmatizer()
html_parser = HTMLParser()
stopword_list = []
language = ""
def init_lib(lang):
global stopword_list, language
nltk.download('stopwords')
nltk.download('wordnet')
nltk.download('punkt')
language = lang
import pandas as pd
import csv
import spacy
import json
from spacy import displacy
from collections import Counter
from sklearn.feature_extraction.text import CountVectorizer
import nl_core_news_sm
nlp = nl_core_news_sm.load()
df = pd.read_csv('dutch-news-articles.csv')
categories = df['category'].unique()
def export_named_entities(categories):
for category in categories:
df_category = df.loc[df['category'] == category]
all_named_entities = df_category['content'].apply(
get_all_named_entities)
sum_named_entities = count_named_entities(all_named_entities)
create_json(category, sum_named_entities)
def get_all_named_entities(row):
doc = nlp(row)
items = []
for entity in doc.ents:
if entity.label_ != 'CARDINAL' and entity.label_ != 'DATE' and entity.label_ != 'QUANTITY' and entity.label_ != 'TIME' and entity.label_ != 'ORDINAL' and entity.label_ != 'PERCENT' and entity.label_ != 'MONEY':
items.append(entity.text)
print(items)
