Make Save Method for data analysis:

- info .txt
- Frequency_matrix.csv -- model matrix
- Dictionary.txt
- tags.txt

news_classify_tag.py

@@ -4,6 +4,7 @@
 import numpy as np
 import _mysql
 
+
 # test submodule commit
 
 # noinspection PyUnresolvedReferences
@@ -17,7 +18,7 @@ class Classifier:
         except ImportError:
             print ('You have import flowing packages: sklearn & nltk & re.')
 
-        stopwords = set (nltk.corpus.stopwords.words('english'))
+        stopwords = set (nltk.corpus.stopwords.words ('english'))
         stopwords.update (['from:', 'subject:', 'writes:', 'writes', 'click', 'here', 'page', 'origin'])
 
         if corpus is not None:
@@ -113,8 +114,8 @@ class Classifier:
         if data_text == '':
             data_text = self.tag_train_text
         self.trained_model = self.vectorizer.fit_transform (data_text)
-        print ("number of feaches =", len (self.vectorizer.get_feature_names ()))
-        print ("Quontety of tags = ", len (self.tags))
+        print ("number of features =", len (self.vectorizer.get_feature_names ()))
+        print ("Quantity of tags = ", len (self.tags))
         self.tag_frequency_matrix_compute ()
         return self.trained_model
 
@@ -172,6 +173,21 @@ class Classifier:
 
     def save(self):
         import os
+
+        # save info data
+        file_info = open ("info_model.txt", 'w')
+        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 ("\ndata_tag_frequency.csv  ---- Model data matrix --- " + \
+                         str (self.trained_model.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.close ()
+
+        # save model matrix
         file_tag_frequency = 'data_tag_frequency.csv'
         if os.path.isfile (file_tag_frequency):
             os.remove (file_tag_frequency)
@@ -182,6 +198,22 @@ class Classifier:
         np.savetxt (file_tag_frequency, self.tag_frequency_matrix, delimiter=';', fmt='%1.4f')
         print ("Data is saved into file: " + file_tag_frequency + " " + str (
             int (os.stat (file_tag_frequency).st_size / 1024)) + 'kB')
+
+        # save dictionary
+        file_info_dictionaries = open ("Dictionary.txt", "w")
+        if file_info_dictionaries == None:
+            return False
+        for line in self.vectorizer.get_feature_names ():
+            file_info_dictionaries.write (line + "\n")
+        file_info_dictionaries.close ()
+
+        # save tags
+        file_info_tags = open ("tags.txt", "w")
+        if file_info_tags == None:
+            return False
+        for text1, text2 in self.tags:
+            file_info_tags.write (text1 + " " + text2.decode ('ascii', "ignore") + "\n")
+        file_info_tags.close ()
         return True
 
 
@@ -218,7 +250,7 @@ if __name__ == "__main__":
         tags_classif = Classifier (host='localhost', port=8080, user='root', password='password', db='news')
     # the method is not implicated
     tags_classif.teach_model ()
-    # tags_classif.save ()
+    tags_classif.save ()
     # exit(0)
 
     sql1 = '''SELECT rez.news_id , rez.title, rez.description