Update create_movie_corpus.py

create_movie_corpus.py

@@ -1,5 +1,7 @@
-    #make corpus
-import sqlite3
+"""this file is used in conjunction with the cornell movie dialogue corpus as mentioned below to make a corpus for chatterbot training data"""
+
+"""NOTE: for this file to work the "movie_lines.txt" file must be placed in the same folder as this file"""
+import sqlite3 #standard library 
 #this file makes use of the Cornell movie lines corpus which can be found at : https://www.cs.cornell.edu/~cristian/Cornell_Movie-Dialogs_Corpus.html
 
 
@@ -12,7 +14,9 @@ def get_text(row):
         row = row[1:]
     return row
 
-"""the yml file that this file creates requires the first few lines to be in a format similar to, but not the same as the rest of the file, this function creates that"""
+"""the yml file that this file creates requires the first few lines to be in a format similar to, but not the same as the rest of the file, this function creates that
+
+NOTE: as this function opens the file in "write" mode it means that it deletes any other copy of the corpus in the same folder""""
 def make_initial():
     with open("movie_lines_corpus.yml",'w') as corp:
         corp.write("categories:\n")
@@ -65,7 +69,7 @@ with open("movie_lines_corpus.yml",'a') as corp:
                 corp.write("- - {}".format(text))
             line_counter += 1
             corp.write("\n")
-            if line_counter == 100000:  #this value can be changed, this will change the size of the corpus
+            if line_counter == 100:  #this value can be changed, this will change the size of the corpus
                 break
 
 """THE FILE CREATED BY THIS CALLED 'movie_lines_corpus.yml' MUST BE MOVED TO THE 'custom' FOLDER IN THE CHATTERBOT LIBRARY FOLDER TO WORK"""