preprocesamiento_articulos.py

import pandas as pd
import numpy as np
import nltk
from nltk.tokenize import word_tokenize, RegexpTokenizer
from nltk.corpus import stopwords
from nltk.stem import SnowballStemmer

from sklearn.feature_extraction.text import CountVectorizer
import csv
import re

nltk.download('stopwords')
nltk.download('punkt')
stopwords_es = stopwords.words('spanish')
spanish_stemmer = SnowballStemmer('spanish')


def remove_html_markup(s):
    tag = False
    quote = False
    out = ""

    for c in s:
            if c == '<' and not quote:
                tag = True
            elif c == '>' and not quote:
                tag = False
            elif (c == '"' or c == "'") and tag:
                quote = not quote
            elif not tag:
                out = out + c

    return out

def remove_URL(s):
    """Remove URLs from a sample string"""
    return re.sub(r"http\S+", "", s)    
    
def eliminar_puntuacion(articulo):
    deletetion_symbols = ['!','(',')',"'",'-','[',']','{','}',';',':','"','“','’','”',"'",'`','‘','``','\\' ,'/','|',',','|','<','>','.','..','...','?','@',"#",'$','^','&','*','_','~','+','%','=','¿','¡',"''"]
    new_articulo = ""
    for x in articulo:
        if x not in deletetion_symbols:
            new_articulo += x
    return new_articulo  

def eliminar_stopwords(articulo):

    articulo_splitted=articulo.split()
    new_articulo = ""
    for x in articulo_splitted:
        if x not in stopwords_es:
            new_articulo += " " + x
    return new_articulo  

def obtener_raices(articulo):

    articulo_splitted=articulo.split()
    new_articulo = ""
    for x in articulo_splitted:
        x_new = spanish_stemmer.stem(x)
        new_articulo += " " + x_new
    return new_articulo 
    
def limpieza_articulos(df):
    
    df_titulos=pd.DataFrame(df['titulo'], columns=['titulo'])
    # Colocando texto en minusculas
    df_titulos['titulo']= df_titulos['titulo'].apply(lambda x: x.lower())
    # Eliminando signos de puntuacion
    df_titulos['titulo']= df_titulos['titulo'].apply(lambda x: eliminar_puntuacion(x))
    # Eliminando palabras vacias (stopwords) utilizando el corpus para estos fines que tiene nltk
    df_titulos['titulo']= df_titulos['titulo'].apply(lambda x: eliminar_stopwords(x))
    all_text = ' '. join(df_titulos['titulo'])
    vocab= np.unique(word_tokenize(all_text))
    return vocab