Python文本處理：AttributeError：'list'對象沒有屬性'lower'

Question

我是Python和Stackoverflow的新手（請溫柔），我正在努力學習如何進行情緒分析。 我正在使用我在教程中找到的代碼組合，這里： Python - AttributeError：'list'對象沒有屬性但是，我一直在

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'`

這是我的代碼：

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)

任何幫助都將受到大力贊賞。

Answer 1

csv閱讀器的結果是一個列表， lower只適用於字符串。 據推測它是一個字符串列表，所以有兩個選項。 您可以在每個元素上調用lower ，或者將列表轉換為字符串，然后在其上調用lower 。

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

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

但更合理（沒有更多信息很難說）你實際上只想要一個項目列表。 有點像：

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

另外，猜測你沒有像你認為的那樣使用csv閱讀器，因為現在你每次都在一個單獨的例子上訓練一個朴素的貝葉斯分類器，然后讓它預測它被訓練的一個例子。 也許解釋你想要做什么？