如何使用朴素贝叶斯将数据分为多个类别？

Question

我试图将句子分类为各种情感（其中有八个），但是在运行代码时出现此错误。抱歉，我真的是Python的新手，所以我不确定在这里发生了什么。

ValueError                                
Traceback (most recent call last)
<ipython-input-66-40fb2c79238c> in <module>
      18 test_data = data[4800:]
      19 
--->  20 classfier= nltk.NaiveBayesClassifier.train(train_data)
      21 print(nltk.classify.accuracy(classifier, test_data)) 


  ~/anaconda3/lib/python3.7/site-packages/nltk/classify/naivebayes.py in train(cls, labeled_featuresets, estimator)
204         # Count up how many times each feature value occurred, given
205         # the label and featurename.
--> 206         for featureset, label in labeled_featuresets:
207             label_freqdist[label] += 1
208             for fname, fval in featureset.items():

ValueError: too many values to unpack (expected 2)

---

这是我的原始代码：

import nltk
import pandas as pd
import csv
import numpy as np
from sklearn.model_selection import train_test_split

import pandas as pd
import numpy as np

import random

with open("/Users/mac/Documents/Transcribed.rtf", "rb") as f:
data = f.read().split()

random.shuffle(data)

train_data = data[:1200]
test_data = data[4800:]

classfier= nltk.NaiveBayesClassifier.train(train_data)
print(nltk.classify.accuracy(classifier, test_data))

Answer 1

从我看到的问题出在第206行：

  ~/anaconda3/lib/python3.7/site-packages/nltk/classify/naivebayes.py in train(cls, labeled_featuresets, estimator)
204         # Count up how many times each feature value occurred, given
205         # the label and featurename.
--> 206         for featureset, label in labeled_featuresets:
207             label_freqdist[label] += 1
208             for fname, fval in featureset.items():

ValueError: too many values to unpack (expected 2)

该错误表明您在labeled_featuresets中所期望的for featureset, label in labeled_featuresets。因此，您要做的是打印labeled_featureset的内容，并查看它的尺寸。