def vectorize(corpus):
corpus_ = []
for line in corpus:
corpus_.append(set_sentence(line))
stwf=stopwords.words('french')
stwf.append('les')
stwf.append('rt')
vectorizer = CountVectorizer(stop_words=stwf,decode_error ="ignore")
X = vectorizer.fit_transform(corpus_)
return X.toarray()
def vectorize_(corpus):
corpus_ = []
for sentence in corpus:
sentence = set_sentence(sentence)
corpus_.append(sentence)
return vectorizer.transform(corpus_)
def vectorize_(corpus): corpus_=[] for sentence in corpus: sentence=set_sentence(sentence) corpus_.append(sentence) return vectorizer.transform(corpus_)
import numpy as np
from preprocess import set_sentence
from sklearn.feature_extraction.text import CountVectorizer
import nltk
from nltk.corpus import stopwords
########################################################
# intput_: corpus.txt #
# #
# example: python corpusvectorizer.py corpus.txt #
########################################################
corpus=[]
input_ = sys.argv[1]
fs=open(input_,'r')
lines = fs.readlines()
for line in lines:
line =set_sentence(line)
corpus.append(line)
stwf=stopwords.words('french')
stwf.append('les')
stwf.append('rt')
vectorizer=CountVectorizer(stop_words=stwf,decode_error ="ignore")
X = vectorizer.fit_transform(corpus)
X = X.toarray()
print X