Update preprocesamiento_articulos.py
Browse files
preprocesamiento_articulos.py
CHANGED
|
@@ -1,10 +1,12 @@
|
|
| 1 |
import pandas as pd
|
| 2 |
import numpy as np
|
|
|
|
| 3 |
from nltk.tokenize import word_tokenize, RegexpTokenizer
|
| 4 |
from nltk.corpus import stopwords
|
| 5 |
from sklearn.feature_extraction.text import CountVectorizer
|
| 6 |
import csv
|
| 7 |
|
|
|
|
| 8 |
stopwords_es = stopwords.words('spanish')
|
| 9 |
|
| 10 |
def eliminar_puntuacion(articulo):
|
|
|
|
| 1 |
import pandas as pd
|
| 2 |
import numpy as np
|
| 3 |
+
import nltk
|
| 4 |
from nltk.tokenize import word_tokenize, RegexpTokenizer
|
| 5 |
from nltk.corpus import stopwords
|
| 6 |
from sklearn.feature_extraction.text import CountVectorizer
|
| 7 |
import csv
|
| 8 |
|
| 9 |
+
nltk.download('stopwords')
|
| 10 |
stopwords_es = stopwords.words('spanish')
|
| 11 |
|
| 12 |
def eliminar_puntuacion(articulo):
|