def tfidf(max_features=5000,prefix="extraction-",begin=1, end=26):
# get stopwords
sf = open('chi_stopwords.txt','r')
stopwords = [x.strip() for x in sf.read().split(',')]
vectorizer=tv(max_features=max_features)#tokenizer=tokenizer)
d={}
st=time.time()
d,txt=getText(prefix=prefix,begin=begin,end=end)
getdatatime=time.time()
print getdatatime-st
corpus={}
for i in range(len(txt)):#d.items():
#corpus.append(" ".join(jieba.cut(line.split(',')[0],cut_all=False)))
corpus[i]=(' '.join(jieba.cut(txt[i],cut_all=False)))
tfidf=vectorizer.fit_transform(corpus.values()).toarray()
print tfidf.shape
voc=vectorizer.get_feature_names()
wordssum = tfidf.sum(axis=0)
index=range(len(voc))
index = [index for (y,x,index) in sorted(zip(wordssum,voc,index),reverse=True) if x.encode('utf-8') not in stopwords]
print time.time() - st
voc_sorted = [voc[i] for i in index]
tfidfret = []
print time.time()-getdatatime
return tfidf,voc,txt
def tfidf(max_features=5000, prefix="extraction-", begin=1, end=26):
# get stopwords
sf = open('chi_stopwords.txt', 'r')
stopwords = [x.strip() for x in sf.read().split(',')]
vectorizer = tv(max_features=max_features) #tokenizer=tokenizer)
d = {}
st = time.time()
d, txt = getText(prefix=prefix, begin=begin, end=end)
getdatatime = time.time()
print getdatatime - st
corpus = {}
for i in range(len(txt)): #d.items():
#corpus.append(" ".join(jieba.cut(line.split(',')[0],cut_all=False)))
corpus[i] = (' '.join(jieba.cut(txt[i], cut_all=False)))
tfidf = vectorizer.fit_transform(corpus.values()).toarray()
print tfidf.shape
voc = vectorizer.get_feature_names()
wordssum = tfidf.sum(axis=0)
index = range(len(voc))
index = [
index
for (y, x, index) in sorted(zip(wordssum, voc, index), reverse=True)
if x.encode('utf-8') not in stopwords
]
print time.time() - st
voc_sorted = [voc[i] for i in index]
tfidfret = []
print time.time() - getdatatime
return tfidf, voc, txt
def cluster(self, processed_text):
vector = tv(use_idf=True)
self.matrix = vector.fit_transform(processed_text)
self.model = km(n_clusters=clusters, n_init=1000)
self.model.fit(self.matrix)
self.model_pred = km(n_clusters=clusters, n_init=1000)
self.model_pred.fit_predict(self.matrix)
return vector
def tfidf(max_features=10000,path="/home/tingyubi/20w/data/",prefix="extraction-",begin=1, end=26):
### get stopwords
sf = open('chi_n.txt','r')
stopwords = [x.strip().decode('utf-8') for x in sf.read().split('\n')]
sf.close()
### load data
d={}
st=time.time()
d,txt=getText(prefix=prefix,begin=begin,end=end)
getdatatime=time.time()
print "Loading data cost "+str(getdatatime-st)+" seconds."
### cut text
corpus={}
for i in range(len(txt)):#d.items():
#corpus.append(" ".join(jieba.cut(line.split(',')[0],cut_all=False)))
corpus[i]=(' '.join(jieba.cut(txt[i],cut_all=False)))
jsonfile = "tfidf_cut_"+prefix+str(begin)+"_"+str(end)+".json"
f = open(jsonfile,'w')
json.dump(corpus,f)
#f = open(jsonfile,'r')
#corpus = json.load(f)
f.close()
### tfidf vectorizer
vectorizer=tv(max_features=max_features,stop_words=stopwords)#tokenizer=tokenizer)
tfidf=vectorizer.fit_transform(corpus.values())#.toarray()
print "Tfidf vectorizing cost "+str(time.time()-getdatatime)+" seconds."
#print tfidf.shape
voc=vectorizer.get_feature_names()
### sorting vocabulary
#wordssum = tfidf.sum(axis=0)
#index=range(len(voc))
#index = [index for (y,x,index) in sorted(zip(wordssum,voc,index),reverse=True) if x.encode('utf-8') not in stopwords]
#voc_sorted = [voc[i] for i in index]
### save to json file
#jsonfile = "tfidf_"+prefix+str(begin)+"_"+str(end)+".json"
#data={}
#data['vocabulary']=voc
#data['tfidf']=tfidf.tolist()
#with open(jsonfile,'w') as f:
# json.dump(data,f)
#f.close()
### save to pickle file
pklfile = "tfidf_"+prefix+str(begin)+"_"+str(end)+".mat"
f = open(pklfile,'wb')
cPickle.dump(tfidf,f,-1)
f.close()
vocfile = "tfidf_"+prefix+str(begin)+"_"+str(end)+".voc"
f = open(vocfile,'w')
voca=voc
f.write("\n".join(voca).encode('utf-8'))
f.close()
return tfidf,voc,txt
def __init__(self, revisoes, ngram_range=(1, 1)):
self.vetorizador = tv(ngram_range=ngram_range)
self.revisoes = revisoes
self.vetorizar()
print("\nTFIDFVectorizer concluiu a vetorização de %s." %
str(ngram_range))
# load data
d = {}
st = time.time()
d, txt = getText(prefix=args.prefix, begin=args.begin, end=args.end)
getdatatime = time.time()
print "Loading data cost " + str(getdatatime - st) + " seconds."
# cut words
corpus = {}
for i in range(len(txt)): #d.items():
#corpus.append(" ".join(jieba.cut(line.split(',')[0],cut_all=False)))
corpus[i] = (' '.join(jieba.cut(txt[i], cut_all=False)))
# tfidf
vectorizer = tv(max_features=args.max_features,
stop_words=stopwords) #tokenizer=tokenizer)
tfidf = vectorizer.fit_transform(corpus.values()).toarray()
print tfidf.shape
voc = vectorizer.get_feature_names()
print "Tfidf calculating cost " + str(time.time() - getdatatime) + " seconds."
# sorting according to tfidf
wordssum = tfidf.sum(axis=0)
index = range(len(voc))
index = [
index for (y, x, index) in sorted(zip(wordssum, voc, index), reverse=True)
] #if x not in stopwords]
voc_sorted = [voc[i] for i in index]
f = open(args.outputfile, 'w')
for x in voc_sorted:
f.write(x.encode("utf-8") + "\n")
# load data
d={}
st=time.time()
d,txt=getText(prefix=args.prefix,begin=args.begin,end=args.end)
getdatatime=time.time()
print "Loading data cost "+ str(getdatatime-st)+" seconds."
# cut words
corpus={}
for i in range(len(txt)):#d.items():
#corpus.append(" ".join(jieba.cut(line.split(',')[0],cut_all=False)))
corpus[i]=(' '.join(jieba.cut(txt[i],cut_all=False)))
# tfidf
vectorizer=tv(max_features=args.max_features,stop_words=stopwords)#tokenizer=tokenizer)
tfidf=vectorizer.fit_transform(corpus.values()).toarray()
print tfidf.shape
voc=vectorizer.get_feature_names()
print "Tfidf calculating cost "+str(time.time() - getdatatime)+" seconds."
# sorting according to tfidf
wordssum = tfidf.sum(axis=0)
index = range(len(voc))
index = [index for (y,x,index) in sorted(zip(wordssum,voc,index),reverse=True)] #if x not in stopwords]
voc_sorted = [voc[i] for i in index]
f=open(args.outputfile,'w')
for x in voc_sorted:
f.write(x.encode("utf-8")+"\n")
f.close()
#return tfidf,voc,txt
print("Accuracy: %0.2f (+/- %0.2f)" %
(train_scores.mean(), train_scores.std() * 2))
test_scores = classifier.score(X_test, y_test)
print('Test Scores')
print(test_scores)
print("Accuracy: %0.2f (+/- %0.2f)" %
(test_scores.mean(), test_scores.std() * 2))
print('')
'''
Train a SGD classifier using unigram representation
with tf-idf, predict sentiments on imdb_te.csv, and write
output to unigram.output.txt
'''
vectorizer = tv(encoding='utf-8',
strip_accents='unicode',
ngram_range=(1, 1),
decode_error='replace')
vector_data = vectorizer.fit_transform(train_text)
model_selector = model_selection
X_train, X_test, y_train, y_test = model_selector.train_test_split(
vector_data, labels, stratify=labels, test_size=0.2)
classifier = sgd(loss='hinge', penalty='l1')
classifier.fit(X_train, y_train)
train_scores = classifier.score(X_train, y_train)
print('TF-IDF Unigram Results')
print('Train Scores')
print(train_scores)
print("Accuracy: %0.2f (+/- %0.2f)" %
def build_tfidf(corpus): vec = tv() tfidfs = vec.fit_transform(corpus) print (tfidfs.shape) return (tfidfs,vec)
# Import the necessary packages for preforming similarity between texts.
from sklearn.metrics.pairwise import cosine_similarity as cs
from sklearn.feature_extraction.text import TfidfVectorizer as tv
# Load the texts - The original & The generated
gensis = open('../Genesis.txt','r').read().split('\r')
model_gensis = open('../Model_Genesis.txt','r').read().split('\n')
# Initialize
TfV = tv()
TfV.fit(gensis)
Y = TfV.transform(gensis)
# Check for every sentence the similarity
similaritySum = 0
for sentence in model_gensis:
X = TfV.transform([sentence])
print(sentence)
print(gensis[cs(X, Y).argmax()])
print(' ')
similaritySum = cs(X, Y).max()
# Calculate the similarity
similarity = similaritySum/7
print('The similarity between the original text - Genesis - and the model is: ' , similarity)
def build_tfidf(corpus): tfidfs = tv(corpus) return tfidfs
