Python文本处理：AttributeError：'list'对象没有'lower'属性

Question

我刚接触Python，也刚开始在Stackoverflow上发帖（请多多包涵），现在我想学习如何进行情感分析。我使用的是在一个教程和这里找到的一些代码：Python - AttributeError: 'list' object has no attribute 但是，我总是遇到问题。

Traceback (most recent call last):
    File "C:/Python27/training", line 111, in <module>
    processedTestTweet = processTweet(row)
  File "C:/Python27/training", line 19, in processTweet
    tweet = tweet.lower()
AttributeError: 'list' object has no attribute 'lower'`

这是我的代码：

import csv
#import regex
import re
import pprint
import nltk.classify


#start replaceTwoOrMore
def replaceTwoOrMore(s):
    #look for 2 or more repetitions of character
    pattern = re.compile(r"(.)\1{1,}", re.DOTALL)
    return pattern.sub(r"\1\1", s)

# process the tweets
def processTweet(tweet):
    #Convert to lower case
    tweet = tweet.lower()
    #Convert www.* or https?://* to URL
    tweet = re.sub('((www\.[\s]+)|(https?://[^\s]+))','URL',tweet)
    #Convert @username to AT_USER
    tweet = re.sub('@[^\s]+','AT_USER',tweet)
    #Remove additional white spaces
    tweet = re.sub('[\s]+', ' ', tweet)
    #Replace #word with word
    tweet = re.sub(r'#([^\s]+)', r'\1', tweet)
    #trim
    tweet = tweet.strip('\'"')
    return tweet

#start getStopWordList
def getStopWordList(stopWordListFileName):
    #read the stopwords file and build a list
    stopWords = []
    stopWords.append('AT_USER')
    stopWords.append('URL')

    fp = open(stopWordListFileName, 'r')
    line = fp.readline()
    while line:
        word = line.strip()
        stopWords.append(word)
        line = fp.readline()
    fp.close()
    return stopWords

def getFeatureVector(tweet, stopWords):
    featureVector = []
    words = tweet.split()
    for w in words:
        #replace two or more with two occurrences
        w = replaceTwoOrMore(w)
        #strip punctuation
        w = w.strip('\'"?,.')
        #check if it consists of only words
        val = re.search(r"^[a-zA-Z][a-zA-Z0-9]*[a-zA-Z]+[a-zA-Z0-9]*$", w)
        #ignore if it is a stopWord
        if(w in stopWords or val is None):
            continue
        else:
            featureVector.append(w.lower())
     return featureVector

def extract_features(tweet):
    tweet_words = set(tweet)
    features = {}
    for word in featureList:
        features['contains(%s)' % word] = (word in tweet_words)
    return features


#Read the tweets one by one and process it
inpTweets = csv.reader(open('C:/GsTraining.csv', 'rb'),
                       delimiter=',',
                       quotechar='|')
stopWords = getStopWordList('C:/stop.txt')
count = 0;
featureList = []
tweets = []

for row in inpTweets:
    sentiment = row[0]
    tweet = row[1]
    processedTweet = processTweet(tweet)
    featureVector = getFeatureVector(processedTweet, stopWords)
    featureList.extend(featureVector)
    tweets.append((featureVector, sentiment))

# Remove featureList duplicates
featureList = list(set(featureList))

# Generate the training set
training_set = nltk.classify.util.apply_features(extract_features, tweets)

# Train the Naive Bayes classifier
NBClassifier = nltk.NaiveBayesClassifier.train(training_set)

# Test the classifier
with open('C:/CleanedNewGSMain.txt', 'r') as csvinput:
    with open('GSnewmain.csv', 'w') as csvoutput:
    writer = csv.writer(csvoutput, lineterminator='\n')
    reader = csv.reader(csvinput)

    all=[]
    row = next(reader)

    for row in reader:
        processedTestTweet = processTweet(row)
        sentiment = NBClassifier.classify(
            extract_features(getFeatureVector(processedTestTweet, stopWords)))
        row.append(sentiment)
        processTweet(row[1])

    writer.writerows(all)

任何帮助都会非常感谢。

Answer 1

从csv读取的数据结果是一个列表，而lower这个函数只能作用于字符串。假设这个列表里的确是字符串类型，那么你有两个选择。要么对列表中的每个元素都调用一次lower，要么把整个列表变成一个字符串，然后再调用lower。

# the first approach
[item.lower() for item in tweet]

# the second approach
' '.join(tweet).lower()

不过更合理的推测是（没有更多信息很难判断）你其实只想从列表中取出一个元素。大概可以这样做：

for row in reader:
    processedTestTweet = processTweet(row[0]) # Again, can't know if this is actually correct without seeing the file

另外，我猜测你可能没有像你想的那样使用csv读取器，因为现在你每次都是在用一个例子来训练朴素贝叶斯分类器，然后让它预测这个它刚训练过的例子。也许你可以解释一下你想要做什么？