Merge remote-tracking branch 'origin/master'

src/data/embeddings.py

@@ -276,6 +276,7 @@ class StorageEmbeddings:
             self._add_emebeddings_supervised(docs, labels, config['reduction'], config['max_label_space'], vocs)
         return self
 
+
     def predict(self, config, docs):
         if config['supervised'] and config['unsupervised']:
             return self._concatenate_embeddings(docs)
@@ -288,3 +289,4 @@ class StorageEmbeddings:
             for lang in docs.keys():
                 _r[lang] = docs[lang].dot(self.lang_U[lang])
         return _r
+

src/data/supervised.py

@@ -12,6 +12,7 @@ def zscores(x, axis=0): #scipy.stats.zscores does not avoid division by 0, which
 
 def supervised_embeddings_tfidf(X,Y):
     tfidf_norm = X.sum(axis=0)
+    tfidf_norm[tfidf_norm==0] = 1
     F = (X.T).dot(Y) / tfidf_norm.T
     return F