Chang self.tags (list) to self.tags_dict (dictionary)

news_classify_tag.py

@@ -38,9 +38,14 @@ class Classifier:
         rez = self.db.store_result()
         tags = list()
         for id, description in rez.fetch_row(maxrows=0):
-            tags.append((id, description))
+            tags.append((int(id), description))
+        self.tags_dict = dict(tags)
+
         self.tags = tags
-        # print(len(tags), tags)
+        # print('tags array = ', len(self.tags), self.tags)
+        # print(self.tags_dict)
+        # print(self.tags_dict[355])
+        # exit(0)
         del tags
 
         # train_data = []
@@ -176,10 +181,13 @@ class Classifier:
         # print(sorted_probabl_probabl)
         for item in sorted_probabl_probabl:
             if item[1] < persantage / 100: continue
-            # print (item[0], item[1], self.tags[item[0] - 1][1].decode ("ascii", 'ignore'),  end=", ")
+            # print (item[0], end=", ")
+            # print(int(item[1] * 1000) / 10, end=", ")
+            # print("item in my tags: ", item[0] - 1)
+            # print(self.tags_dict[item[0]].decode("ascii", 'ignore'),  end=", ")
             vector_accordance.append(
                 (item[0], int(item[1] * 1000) / 10,
-                 self.tags[item[0] - 1][1].decode("ascii", 'ignore')))
+                 self.tags_dict[item[0]].decode("ascii", 'ignore')))
 
         return vector_accordance
 
@@ -247,12 +255,12 @@ class Classifier:
         if file_info == None:
             return False
         file_info.write("number of features = " + str(len(self.vectorizer.get_feature_names())) + '\n')
-        file_info.write("Quantity of tags = " + str(len(self.tags)) + '\n')
+        file_info.write("Quantity of tags = " + str(len(self.tags_dict)) + '\n')
         file_info.write("\ndata_tag_frequency.csv  ---- Model data matrix --- " + \
                         str(self.X_data.shape) + "\n")
         file_info.write("\nDictionary.txt -- Total number words in  is---" + str(
             len(self.vectorizer.get_feature_names())) + '\n')
-        file_info.write("\ntags.txt --- Total number is ---" + str(len(self.tags)) + '\n')
+        file_info.write("\ntags.txt --- Total number is ---" + str(len(self.tags_dict)) + '\n')
         file_info.close()
 
         # save model matrix
@@ -280,7 +288,7 @@ class Classifier:
         file_info_tags = open(directory + "/tags.txt", "w")
         if file_info_tags == None:
             return False
-        for text1, text2 in self.tags:
+        for text1, text2 in self.tags_dict:
             file_info_tags.write(text1 + " " + text2.decode('ascii', "ignore") + "\n")
         file_info_tags.close()
         return True