small change to the model

clust.py

@@ -1,10 +1,7 @@
 from infBack import get_vect as gv
+from sklearn.feature_extraction.text import TfidfVectorizer
 import numpy as np
-from sklearn.feature_extraction.text import TfidfTransformer
-from sklearn.feature_extraction.text import CountVectorizer
-from sklearn import cluster
-from matplotlib import pyplot
-import numpy as np
+
 
 def stopWrdList():
     sw = open('stop.words')
@@ -13,6 +10,8 @@ def stopWrdList():
     return [l.strip('\n\r') for l in prue[0]]
 
 
+voc = ["ine", "pri", "pan", "prd", "pt", "pvem", "verde", "movimiento", "ciudadano", "panal", "alianza", "morena", "partido", "encuentro", "social", "electoral"]
+
 stop_words = stopWrdList()
 
 dataVect = gv()
@@ -21,36 +20,12 @@ dataVect = np.array(dataVect)
 
 corpus = dataVect[:, 2]
 
-vectorizer = CountVectorizer(stop_words=stop_words)
-transformer = TfidfTransformer(smooth_idf=False)
+vectorizer = TfidfVectorizer(strip_accents='ascii', analyzer='word', stop_words=stop_words, vocabulary=voc)
 
 X = vectorizer.fit_transform(corpus)
 
-del dataVect, corpus, stop_words
+del dataVect, stop_words, vectorizer  # , corpus
 
 J = X.toarray()
 
-tf_idf = transformer.fit_transform(J)
-
-tf_idf_matrix = tf_idf.toarray()
-
-k = 2
-kmeans = cluster.KMeans(n_clusters=k)
-kmeans.fit(J)
-
-labels = kmeans.labels_
-centroids = kmeans.cluster_centers_
-
-for i in range(k):
-    # select only data observations with cluster label == i
-    ds = J[np.where(labels == i)]
-    # plot the data observations
-    pyplot.plot(ds[:, 0], ds[:, 1], 'o')
-    # plot the centroids
-    lines = pyplot.plot(centroids[i, 0], centroids[i, 1], 'kx')
-    # make the centroid x's bigger
-    pyplot.setp(lines, ms=15.0)
-    pyplot.setp(lines, mew=2.0)
-pyplot.show()
-
-print(X.toarray())
+print(J)

infBack.py

@@ -27,6 +27,8 @@ def get_vect():
     return impDat
 
 
+# print(len(get_vect()))
+
 
 # this section of the code show how to extract relevant data from the dictionaries
 """