add dataset-visualiser.py

preprocessing.py

@@ -163,11 +163,17 @@ def fix_class(folder):
         if label.startswith('0000'):
             with open(os.path.join(folder, label), 'r+') as f:
                 lines = f.readlines()
+                truncated = False
                 for i in range(0, len(lines)):
-                    l = lines[i]
-                    lines[i] = f'2{l[1:]}'
-                f.seek(0)  # rewind
-                f.writelines(lines)
+                    if len(lines[i]) < 25:
+                        print(lines[i])
+                        truncated = True
+                        lines.pop(i)
+                if truncated:
+                    f.truncate(0)
+                    f.seek(0)
+                    f.writelines(lines)
+                f.close()
 
 
 if __name__ == '__main__':