深度学习聊天机器人特定索引错误列表索引超出范围
Deep learning chatbot specific Index error list index out of range
我正在尝试学习如何使用 pytorch 制作深度学习聊天机器人的教程。然而，这段代码对我来说相当复杂，它已经停止并出现“IndexError：列表索引超出范围”。我查看了错误并了解了它通常意味着什么的要点，但是看到这段代码对我来说非常复杂，我不知道如何解决错误。
这是源码教程：[https://colab.research.google.com/github/pytorch/tutorials/blob/gh-pages/_downloads/chatbot_tutorial.ipynb#scrollTo=LTzdbPF-OBL9][1]
第 198 行似乎是导致错误的原因
return len(p[0].split(' ')) < MAX_LENGTH and len(p[1].split(' ')) < MAX_LENGTH
这是错误日志
Start preparing training data ...
Reading lines...
Traceback (most recent call last):
File "D:\Documents\Python\python pycharm files\pythonProject4.9 Chatbot.py", line 221, in <module>
voc, pairs = loadPrepareData(corpus, corpus_name, datafile, save_dir)
File "D:\Documents\Python\python pycharm files\pythonProject4.9 Chatbot.py", line 209, in loadPrepareData
pairs = filterPairs(pairs)
File "D:\Documents\Python\python pycharm files\pythonProject4.9 Chatbot.py", line 202, in filterPairs
return [pair for pair in pairs if filterPair(pair)]
File "D:\Documents\Python\python pycharm files\pythonProject4.9 Chatbot.py", line 202, in <listcomp>
return [pair for pair in pairs if filterPair(pair)]
File "D:\Documents\Python\python pycharm files\pythonProject4.9 Chatbot.py", line 198, in filterPair
return len(p[0].split(' ')) < MAX_LENGTH and len(p[1].split(' ')) < MAX_LENGTH
IndexError: list index out of range
Read 442563 sentence pairs
Process finished with exit code 1
这是我从 pycharm 复制到错误块的代码。鉴于它是一个巨大的代码，我无法复制整个代码。其余代码可以在上面的 github 来源 link 中找到。
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("D:\Documents\Python\intents", 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"))
# Splits each line of the file into a dictionary of fields
def loadLines(fileName, fields):
lines = {}
with open(fileName, 'r', encoding='iso-8859-1') as f:
for line in f:
values = line.split(" +++$+++ ")
# Extract fields
lineObj = {}
for i, field in enumerate(fields):
lineObj[field] = values[i]
lines[lineObj['lineID']] = lineObj
return lines
# Groups fields of lines from `loadLines` into conversations based on *movie_conversations.txt*
def loadConversations(fileName, lines, fields):
conversations = []
with open(fileName, 'r', encoding='iso-8859-1') as f:
for line in f:
values = line.split(" +++$+++ ")
# Extract fields
convObj = {}
for i, field in enumerate(fields):
convObj[field] = values[i]
# Convert string to list (convObj["utteranceIDs"] == "['L598485', 'L598486', ...]")
lineIds = eval(convObj["utteranceIDs"])
# Reassemble lines
convObj["lines"] = []
for lineId in lineIds:
convObj["lines"].append(lines[lineId])
conversations.append(convObj)
return conversations
# Extracts pairs of sentences from conversations
def extractSentencePairs(conversations):
qa_pairs = []
for conversation in conversations:
# Iterate over all the lines of the conversation
for i in range(len(conversation["lines"]) - 1): # We ignore the last line (no answer for it)
inputLine = conversation["lines"][i]["text"].strip()
targetLine = conversation["lines"][i+1]["text"].strip()
# Filter wrong samples (if one of the lists is empty)
if inputLine and targetLine:
qa_pairs.append([inputLine, targetLine])
return qa_pairs
# Define path to new file
datafile = os.path.join(corpus, "formatted_movie_lines.txt")
delimiter = '\t'
# Unescape the delimiter
delimiter = str(codecs.decode(delimiter, "unicode_escape"))
# Initialize lines dict, conversations list, and field ids
lines = {}
conversations = []
MOVIE_LINES_FIELDS = ["lineID", "characterID", "movieID", "character", "text"]
MOVIE_CONVERSATIONS_FIELDS = ["character1ID", "character2ID", "movieID", "utteranceIDs"]
# Load lines and process conversations
print("\nProcessing corpus...")
lines = loadLines(os.path.join(corpus, "movie_lines.txt"), MOVIE_LINES_FIELDS)
print("\nLoading conversations...")
conversations = loadConversations(os.path.join(corpus, "movie_conversations.txt"),
lines, MOVIE_CONVERSATIONS_FIELDS)
# Write new csv file
print("\nWriting newly formatted file...")
with open(datafile, 'w', encoding='utf-8') as outputfile:
writer = csv.writer(outputfile, delimiter=delimiter)
for pair in extractSentencePairs(conversations):
writer.writerow(pair)
# Print a sample of lines
print("\nSample lines from file:")
printLines(datafile)
# Default word tokens
PAD_token = 0 # Used for padding short sentences
SOS_token = 1 # Start-of-sentence token
EOS_token = 2 # End-of-sentence token
class Voc:
def __init__(self, name):
self.name = name
self.trimmed = False
self.word2index = {}
self.word2count = {}
self.index2word = {PAD_token: "PAD", SOS_token: "SOS", EOS_token: "EOS"}
self.num_words = 3 # Count SOS, EOS, PAD
def addSentence(self, sentence):
for word in sentence.split(' '):
self.addWord(word)
def addWord(self, word):
if word not in self.word2index:
self.word2index[word] = self.num_words
self.word2count[word] = 1
self.index2word[self.num_words] = word
self.num_words += 1
else:
self.word2count[word] += 1
# Remove words below a certain count threshold
def trim(self, min_count):
if self.trimmed:
return
self.trimmed = True
keep_words = []
for k, v in self.word2count.items():
if v >= min_count:
keep_words.append(k)
print('keep_words {} / {} = {:.4f}'.format(
len(keep_words), len(self.word2index), len(keep_words) / len(self.word2index)
))
# Reinitialize dictionaries
self.word2index = {}
self.word2count = {}
self.index2word = {PAD_token: "PAD", SOS_token: "SOS", EOS_token: "EOS"}
self.num_words = 3 # Count default tokens
for word in keep_words:
self.addWord(word)
MAX_LENGTH = 10 # Maximum sentence length to consider
# Turn a Unicode string to plain ASCII, thanks to
#
def unicodeToAscii(s):
return ''.join(
c for c in unicodedata.normalize('NFD', s)
if unicodedata.category(c) != 'Mn'
)
# Lowercase, trim, and remove non-letter characters
def normalizeString(s):
s = unicodeToAscii(s.lower().strip())
s = re.sub(r"([.!?])", r" ", s)
s = re.sub(r"[^a-zA-Z.!?]+", r" ", s)
s = re.sub(r"\s+", r" ", s).strip()
return s
# Read query/response pairs and return a voc object
def readVocs(datafile, corpus_name):
print("Reading lines...")
# Read the file and split into lines
lines = open(datafile, encoding='utf-8').\
read().strip().split('\n')
# Split every line into pairs and normalize
pairs = [[normalizeString(s) for s in l.split('\t')] for l in lines]
voc = Voc(corpus_name)
return voc, pairs
# Returns True iff both sentences in a pair 'p' are under the MAX_LENGTH threshold
def filterPair(p):
# Input sequences need to preserve the last word for EOS token
return len(p[0].split(' ')) < MAX_LENGTH and len(p[1].split(' ')) < MAX_LENGTH
# Filter pairs using filterPair condition
def filterPairs(pairs):
return [pair for pair in pairs if filterPair(pair)]
# Using the functions defined above, return a populated voc object and pairs list
def loadPrepareData(corpus, corpus_name, datafile, save_dir):
print("Start preparing training data ...")
voc, pairs = readVocs(datafile, corpus_name)
print("Read {!s} sentence pairs".format(len(pairs)))
pairs = filterPairs(pairs)
print("Trimmed to {!s} sentence pairs".format(len(pairs)))
print("Counting words...")
for pair in pairs:
voc.addSentence(pair[0])
voc.addSentence(pair[1])
print("Counted words:", voc.num_words)
return voc, pairs
# Load/Assemble voc and pairs
save_dir = os.path.join("data", "save")
voc, pairs = loadPrepareData(corpus, corpus_name, datafile, save_dir)
# Print some pairs to validate
print("\npairs:")
for pair in pairs[:10]:
print(pair)
MIN_COUNT = 3 # Minimum word count threshold for trimming
我真的希望有人能帮我解决这个问题并帮助我理解为什么会这样。
最后我改了
return len(p[0].split(' ')) < MAX_LENGTH and len(p[1].split(' ')) < MAX_LENGTH
至
try:
return len(p[0].split(' ')) < MAX_LENGTH and len(p[1].split(' ')) < MAX_LENGTH
except:
return False
现在代码似乎可以正常工作了。
我正在尝试学习如何使用 pytorch 制作深度学习聊天机器人的教程。然而，这段代码对我来说相当复杂，它已经停止并出现“IndexError：列表索引超出范围”。我查看了错误并了解了它通常意味着什么的要点，但是看到这段代码对我来说非常复杂，我不知道如何解决错误。
这是源码教程：[https://colab.research.google.com/github/pytorch/tutorials/blob/gh-pages/_downloads/chatbot_tutorial.ipynb#scrollTo=LTzdbPF-OBL9][1]
第 198 行似乎是导致错误的原因
return len(p[0].split(' ')) < MAX_LENGTH and len(p[1].split(' ')) < MAX_LENGTH
这是错误日志
Start preparing training data ...
Reading lines...
Traceback (most recent call last):
File "D:\Documents\Python\python pycharm files\pythonProject4.9 Chatbot.py", line 221, in <module>
voc, pairs = loadPrepareData(corpus, corpus_name, datafile, save_dir)
File "D:\Documents\Python\python pycharm files\pythonProject4.9 Chatbot.py", line 209, in loadPrepareData
pairs = filterPairs(pairs)
File "D:\Documents\Python\python pycharm files\pythonProject4.9 Chatbot.py", line 202, in filterPairs
return [pair for pair in pairs if filterPair(pair)]
File "D:\Documents\Python\python pycharm files\pythonProject4.9 Chatbot.py", line 202, in <listcomp>
return [pair for pair in pairs if filterPair(pair)]
File "D:\Documents\Python\python pycharm files\pythonProject4.9 Chatbot.py", line 198, in filterPair
return len(p[0].split(' ')) < MAX_LENGTH and len(p[1].split(' ')) < MAX_LENGTH
IndexError: list index out of range
Read 442563 sentence pairs
Process finished with exit code 1
这是我从 pycharm 复制到错误块的代码。鉴于它是一个巨大的代码，我无法复制整个代码。其余代码可以在上面的 github 来源 link 中找到。
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("D:\Documents\Python\intents", 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"))
# Splits each line of the file into a dictionary of fields
def loadLines(fileName, fields):
lines = {}
with open(fileName, 'r', encoding='iso-8859-1') as f:
for line in f:
values = line.split(" +++$+++ ")
# Extract fields
lineObj = {}
for i, field in enumerate(fields):
lineObj[field] = values[i]
lines[lineObj['lineID']] = lineObj
return lines
# Groups fields of lines from `loadLines` into conversations based on *movie_conversations.txt*
def loadConversations(fileName, lines, fields):
conversations = []
with open(fileName, 'r', encoding='iso-8859-1') as f:
for line in f:
values = line.split(" +++$+++ ")
# Extract fields
convObj = {}
for i, field in enumerate(fields):
convObj[field] = values[i]
# Convert string to list (convObj["utteranceIDs"] == "['L598485', 'L598486', ...]")
lineIds = eval(convObj["utteranceIDs"])
# Reassemble lines
convObj["lines"] = []
for lineId in lineIds:
convObj["lines"].append(lines[lineId])
conversations.append(convObj)
return conversations
# Extracts pairs of sentences from conversations
def extractSentencePairs(conversations):
qa_pairs = []
for conversation in conversations:
# Iterate over all the lines of the conversation
for i in range(len(conversation["lines"]) - 1): # We ignore the last line (no answer for it)
inputLine = conversation["lines"][i]["text"].strip()
targetLine = conversation["lines"][i+1]["text"].strip()
# Filter wrong samples (if one of the lists is empty)
if inputLine and targetLine:
qa_pairs.append([inputLine, targetLine])
return qa_pairs
# Define path to new file
datafile = os.path.join(corpus, "formatted_movie_lines.txt")
delimiter = '\t'
# Unescape the delimiter
delimiter = str(codecs.decode(delimiter, "unicode_escape"))
# Initialize lines dict, conversations list, and field ids
lines = {}
conversations = []
MOVIE_LINES_FIELDS = ["lineID", "characterID", "movieID", "character", "text"]
MOVIE_CONVERSATIONS_FIELDS = ["character1ID", "character2ID", "movieID", "utteranceIDs"]
# Load lines and process conversations
print("\nProcessing corpus...")
lines = loadLines(os.path.join(corpus, "movie_lines.txt"), MOVIE_LINES_FIELDS)
print("\nLoading conversations...")
conversations = loadConversations(os.path.join(corpus, "movie_conversations.txt"),
lines, MOVIE_CONVERSATIONS_FIELDS)
# Write new csv file
print("\nWriting newly formatted file...")
with open(datafile, 'w', encoding='utf-8') as outputfile:
writer = csv.writer(outputfile, delimiter=delimiter)
for pair in extractSentencePairs(conversations):
writer.writerow(pair)
# Print a sample of lines
print("\nSample lines from file:")
printLines(datafile)
# Default word tokens
PAD_token = 0 # Used for padding short sentences
SOS_token = 1 # Start-of-sentence token
EOS_token = 2 # End-of-sentence token
class Voc:
def __init__(self, name):
self.name = name
self.trimmed = False
self.word2index = {}
self.word2count = {}
self.index2word = {PAD_token: "PAD", SOS_token: "SOS", EOS_token: "EOS"}
self.num_words = 3 # Count SOS, EOS, PAD
def addSentence(self, sentence):
for word in sentence.split(' '):
self.addWord(word)
def addWord(self, word):
if word not in self.word2index:
self.word2index[word] = self.num_words
self.word2count[word] = 1
self.index2word[self.num_words] = word
self.num_words += 1
else:
self.word2count[word] += 1
# Remove words below a certain count threshold
def trim(self, min_count):
if self.trimmed:
return
self.trimmed = True
keep_words = []
for k, v in self.word2count.items():
if v >= min_count:
keep_words.append(k)
print('keep_words {} / {} = {:.4f}'.format(
len(keep_words), len(self.word2index), len(keep_words) / len(self.word2index)
))
# Reinitialize dictionaries
self.word2index = {}
self.word2count = {}
self.index2word = {PAD_token: "PAD", SOS_token: "SOS", EOS_token: "EOS"}
self.num_words = 3 # Count default tokens
for word in keep_words:
self.addWord(word)
MAX_LENGTH = 10 # Maximum sentence length to consider
# Turn a Unicode string to plain ASCII, thanks to
#
def unicodeToAscii(s):
return ''.join(
c for c in unicodedata.normalize('NFD', s)
if unicodedata.category(c) != 'Mn'
)
# Lowercase, trim, and remove non-letter characters
def normalizeString(s):
s = unicodeToAscii(s.lower().strip())
s = re.sub(r"([.!?])", r" ", s)
s = re.sub(r"[^a-zA-Z.!?]+", r" ", s)
s = re.sub(r"\s+", r" ", s).strip()
return s
# Read query/response pairs and return a voc object
def readVocs(datafile, corpus_name):
print("Reading lines...")
# Read the file and split into lines
lines = open(datafile, encoding='utf-8').\
read().strip().split('\n')
# Split every line into pairs and normalize
pairs = [[normalizeString(s) for s in l.split('\t')] for l in lines]
voc = Voc(corpus_name)
return voc, pairs
# Returns True iff both sentences in a pair 'p' are under the MAX_LENGTH threshold
def filterPair(p):
# Input sequences need to preserve the last word for EOS token
return len(p[0].split(' ')) < MAX_LENGTH and len(p[1].split(' ')) < MAX_LENGTH
# Filter pairs using filterPair condition
def filterPairs(pairs):
return [pair for pair in pairs if filterPair(pair)]
# Using the functions defined above, return a populated voc object and pairs list
def loadPrepareData(corpus, corpus_name, datafile, save_dir):
print("Start preparing training data ...")
voc, pairs = readVocs(datafile, corpus_name)
print("Read {!s} sentence pairs".format(len(pairs)))
pairs = filterPairs(pairs)
print("Trimmed to {!s} sentence pairs".format(len(pairs)))
print("Counting words...")
for pair in pairs:
voc.addSentence(pair[0])
voc.addSentence(pair[1])
print("Counted words:", voc.num_words)
return voc, pairs
# Load/Assemble voc and pairs
save_dir = os.path.join("data", "save")
voc, pairs = loadPrepareData(corpus, corpus_name, datafile, save_dir)
# Print some pairs to validate
print("\npairs:")
for pair in pairs[:10]:
print(pair)
MIN_COUNT = 3 # Minimum word count threshold for trimming
我真的希望有人能帮我解决这个问题并帮助我理解为什么会这样。
最后我改了
return len(p[0].split(' ')) < MAX_LENGTH and len(p[1].split(' ')) < MAX_LENGTH
至
try:
return len(p[0].split(' ')) < MAX_LENGTH and len(p[1].split(' ')) < MAX_LENGTH
except:
return False
现在代码似乎可以正常工作了。