问题描述
我对Python和机器学习非常陌生，以下是我在python 3中的代码，并且我在jupyter nottebook中编写了python代码。
import random
def splitDataset(dataset, splitRatio):
trainSize = int(len(dataset) * splitRatio)
trainSet = []
copy = list(dataset)
while len(trainSet) < trainSize:
index = random.randrange(len(copy))
trainSet.append(copy.pop(index))
return [trainSet, testSet]
import csv
import sys
from langdetect import detect
import random
import math
def loadCsv(filename):
lines = csv.reader(open(filename, "r",encoding='latin1'))
x=0
myList=[]
for line in lines:
t=line[14]
try:
b = detect(t)
if b=="en":
myList.insert(x,t)
x=x+1
except Exception :
y=0
return myList
import nltk.classify.util
from nltk.classify import NaiveBayesClassifier
filename = 'F:\\Study\\Text Mining (GIT)\\sources\\Data.csv'
splitRatio = 0.8
loadCsv(filename)
trainingSet, testSet = splitDataset(myList, splitRatio)
classifier = nltk.NaiveBayesClassifier.train(trainingSet)
print (nltk.classify.util.accuracy(classifier, testSet))
classifier.show_most_informative_features()
运行abve代码后，出现以下错误
ValueError Traceback (most recent call last)
<ipython-input-206-75c0ffc409d5> in <module>()
10 print(len(testSet))
11
---> 12 classifier = nltk.NaiveBayesClassifier.train(trainingSet)
13 print (nltk.classify.util.accuracy(classifier, testSet))
14
f:\python\lib\site-packages\nltk\classify\naivebayes.py in train(cls,
labeled_featuresets, estimator)
195 # Count up how many times each feature value occurred, given
196 # the label and featurename.
--> 197 for featureset, label in labeled_featuresets:
198 label_freqdist[label] += 1
199 for fname, fval in featureset.items():
ValueError: too many values to unpack (expected 2)
trainingSet=[ "Pleasant 10 min walk along the sea front to the Water Bus. restaurants etc. Hotel was comfortable breakfast was good - quite a variety. Room aircon didn't work very well. Take mosquito repelant!", "Really lovely hotel. Stayed on the very top floor and were surprised by a Jacuzzi bath we didn't know we were getting! Staff were friendly and helpful and the included breakfast was great! Great location and great value for money. Didn't want to leave!", 'We stayed here for four nights in October. The hotel staff were welcoming, friendly and helpful. Assisted in booking tickets for the opera. The rooms were clean and comfortable- good shower, light and airy rooms with windows you could open wide. Beds were comfortable. Plenty of choice for breakfast.Spa at hotel nearby which we used while we were there.', 'We stayed here for four nights in October. The hotel staff were welcoming, friendly and helpful. Assisted in booking tickets for the opera. The rooms were clean and comfortable- good shower, light and airy rooms with windows you could open wide. Beds were comfortable. Plenty of choice for breakfast.Spa at hotel nearby which we used while we were there.',.....]
我已经看过以下网站的解决方案，但找不到任何解决方案：
1楼
您对train（）的输入是错误的。 它期望输入元组列表，其中元组的第一个元素应该是字典。
def train(cls, labeled_featuresets, estimator=ELEProbDist): """ :param labeled_featuresets: A list of classified featuresets, ie, a list of tuples ``(featureset, label)``. """
label_features = []
dic = {}
dic['chipotle']='mexican'
dic['burger']='american'
label_features.append((dic,'food'))
NaiveBayesClassifier.train(label_features)
>><nltk.classify.naivebayes.NaiveBayesClassifier object at 0x000001704916BDD8>
您可以参考示例并打印出功能集值以了解格式。