def action(self, tweets_list):
corpus = []
for tweet in tweets_list:
#corpus += [t["text"]]
tweet_str = tweet["text"].encode("utf-8")
tweet_str = unicode(tweet_str, 'utf-8')
corpus.append(tweet_str)
print(corpus)
vectorizer = CountVectorizer()
X = vectorizer.fit_transform(corpus)
M, P = X.shape
dist_corpus = euclidean_distances(X)
stwf = stopwords.words('french')
stwf.append('les')
vectorizer = CountVectorizer(stop_words=stwf)
X = vectorizer.fit_transform(corpus)
dico = vectorizer.vocabulary_
#Tous les print regroupés ici
print("Results of Birch algorithm")
clusters = birch_algo(X.toarray(), None)
quit()
def action(self, tweets_list):
corpus = []
for tweet in tweets_list:
#corpus += [t["text"]]
tweet_str = tweet["text"].encode("utf-8")
tweet_str = unicode(tweet_str,'utf-8')
corpus.append(tweet_str)
print(corpus)
vectorizer = CountVectorizer()
X = vectorizer.fit_transform(corpus)
M,P=X.shape
dist_corpus=euclidean_distances(X)
stwf=stopwords.words('french')
stwf.append('les')
vectorizer=CountVectorizer(stop_words=stwf)
X = vectorizer.fit_transform(corpus)
dico=vectorizer.vocabulary_
#Tous les print regroupés ici
print("Results of Birch algorithm")
clusters = birch_algo(X.toarray(), None)
quit()
xx, yy = np.meshgrid(xx, yy)
n_centres = np.hstack((np.ravel(xx)[:, np.newaxis],
np.ravel(yy)[:, np.newaxis]))
# Generate blobs to do a comparison between MiniBatchKMeans and Birch.
X, y = make_blobs(n_samples=100000, centers=n_centres, random_state=0)
# Use all colors that matplotlib provides by default.
colors_ = cycle(colors.cnames.keys())
fig = plt.figure(figsize=(12, 4))
fig.subplots_adjust(left=0.04, right=0.98, bottom=0.1, top=0.9)
#Compute clustering with Birch with and without the final clustering step and plot.
labels1, centroids1, n_clusters1 = birch_algo(X, clustering=None)
labels2, centroids2, n_clusters2 = birch_algo(X, clustering=100)
labels = labels1, labels2
centroids = centroids1, centroids2
n_clusters = n_clusters1, n_clusters2
final_step = ['without global clustering', 'with global clustering']
#plot the results of birch with and without clustering.
for i in range(0, 2):
ind = i + 1
ax = fig.add_subplot(1, 3, ind +1)
for this_centroids, k, col in zip(centroids[i], range(n_clusters[i]), colors_ ):
mask = labels[i] == k