如何让我的深度学习聊天机器人使用正确的数据集路径？

Question

I am trying to get the code from a deeplearning chatbot to work. This chatbot uses pytorch and the dataset from Cornell movie corpus. But the code can't seem to find the path to the dataset, and I don't know how to code it in. This is the source for the deeplearning chatbot code [https://colab.research.google.com/github/pytorch/tutorials/blob/gh-pages/_downloads/chatbot_tutorial.ipynb][1]

This is as far as I've gotten with it.

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals

import torch
from torch.jit import script, trace
import torch.nn as nn
from torch import optim
import torch.nn.functional as F
import csv
import random
import re
import os
import unicodedata
import codecs
from io import open
import itertools
import math


USE_CUDA = torch.cuda.is_available()
device = torch.device("cuda" if USE_CUDA else "cpu")

corpus_name = "cornell movie-dialogs corpus"
corpus = os.path.join("data", corpus_name)

def printLines(file, n=10):
    with open(file, 'rb') as datafile:
        lines = datafile.readlines()
    for line in lines[:n]:
        print(line)

printLines(os.path.join(corpus, "movie_lines.txt"))

And this is my error log

D:\Documents\Python\python pycharm files\pythonProject4\3.9 Chatbot.py:26: SyntaxWarning: 'str' object is not callable; perhaps you missed a comma?
  corpus = "D:\Documents\Python\intents\cornell_movie_dialogs_corpus.zip\cornell movie-dialogs corpus\\"("data", corpus_name)
Traceback (most recent call last):
  File "D:\Documents\Python\python pycharm files\pythonProject4\3.9 Chatbot.py", line 26, in <module>
    corpus = "D:\Documents\Python\intents\cornell_movie_dialogs_corpus.zip\cornell movie-dialogs corpus\\"("data", corpus_name)
TypeError: 'str' object is not callable

I hope there is a solution that doesn't alter the source code too much, but any tips or help are welcome.

Answer 1

I solved my problem by removing anything but the cornell movie-dialogs corpus map. And then replacing the word "data" in line 26 with the directory of that map. This fixed it for me