Modificación clase glove_word_embeddins

corpus/.~lock.train-v2.csv#

-,fmplaza,SINAI-155-1,27.06.2018 17:01,file:///home/fmplaza/.config/libreoffice/4;
\ No newline at end of file

model/glove_word_embedings.py

@@ -149,7 +149,7 @@ class GloveWordEmbednigs(AbstractWordEmbedding):
         self.__word_embeddings.clear()
         self.__word_embeddings.clear()
     
     
     
     
-    def __load_full(self, index):
+    def __load_full(self, index, embeddings_number):
         """Load the full file of word embeddings
         """Load the full file of word embeddings
         
         
         Args:
         Args:
@@ -158,12 +158,21 @@ class GloveWordEmbednigs(AbstractWordEmbedding):
         own_partition = str.partition
         own_partition = str.partition
         own_strip = str.strip        
         own_strip = str.strip        
         with open(self.__path_file, "r", encoding="utf-8") as glove_file:
         with open(self.__path_file, "r", encoding="utf-8") as glove_file:
-            for line in glove_file:
-                glove_fields = own_partition(line, self.__GLOVE_SEPARATOR)
-                glove_vector = fromstring(own_strip(glove_fields[2]), dtype=float, sep=" ")
-                self.__word_indexes[own_strip(glove_fields[0])] = index
-                self.__word_embeddings.append(glove_vector)
-                index += 1
+            if(embeddings_number == None):
+                for line in glove_file:
+                    glove_fields = own_partition(line, self.__GLOVE_SEPARATOR)
+                    glove_vector = fromstring(own_strip(glove_fields[2]), dtype=float, sep=" ")
+                    self.__word_indexes[own_strip(glove_fields[0])] = index
+                    self.__word_embeddings.append(glove_vector)
+                    index += 1
+            elif(embeddings_number!=None):
+                for i in range(embeddings_number):
+                    line = glove_file.readline()
+                    glove_fields = own_partition(line, self.__GLOVE_SEPARATOR)
+                    glove_vector = fromstring(own_strip(glove_fields[2]), dtype=float, sep=" ")
+                    self.__word_indexes[own_strip(glove_fields[0])] = index
+                    self.__word_embeddings.append(glove_vector)
+                    index += 1
     
     
     def __load_only_vocabulary(self, index, vocabulary):
     def __load_only_vocabulary(self, index, vocabulary):
         """Load only the words of the vocabulary
         """Load only the words of the vocabulary
@@ -187,7 +196,7 @@ class GloveWordEmbednigs(AbstractWordEmbedding):
                     index += 1
                     index += 1
                     
                     
                     
                     
-    def load(self, begin_ofset=None, vocabulary=None):
+    def load(self, embeddings_number = None, begin_ofset=None, vocabulary=None):
         """Load the Glove vectors file into memory
         """Load the Glove vectors file into memory
         
         
         Args:
         Args:
@@ -209,7 +218,7 @@ class GloveWordEmbednigs(AbstractWordEmbedding):
             self.__word_embeddings.append([]) #Index 0 is reserved
             self.__word_embeddings.append([]) #Index 0 is reserved
         
         
         if(vocabulary is None):
         if(vocabulary is None):
-            self.__load_full(begin_ofset)
+            self.__load_full(begin_ofset, embeddings_number)
         else:
         else:
             self.__load_only_vocabulary(begin_ofset, vocabulary)
             self.__load_only_vocabulary(begin_ofset, vocabulary)