Added a filter to obtain only pertinent news

2017-11-10 11:17:27 -06:00 · 2017-11-10 11:17:27 -06:00 · 39377b0bf9
parent f9830e61d2
commit 39377b0bf9
1 changed files with 15 additions and 1 deletions
--- a/clust.py
+++ b/clust.py
@ -28,4 +28,18 @@ del dataVect, stop_words, vectorizer  # , corpus

 J = X.toarray()

-print(J)
+# print(J)
+
+index = []
+
+for x in range(0, len(J)):
+    if sum(J[x]) != 0:
+        index.append(x)
+
+index = tuple(index)
+
+electCorp = [corpus[x] for x in index]
+
+del corpus
+
+print(electCorp)