1

我正在试验 python NLTK 文本分类。这是我正在练习的代码示例：http ://www.laurentluce.com/posts/twitter-sentiment-analysis-using-python-and-nltk/

这是代码：

from nltk import bigrams
from nltk.probability import ELEProbDist, FreqDist
from nltk import NaiveBayesClassifier
from collections import defaultdict

train_samples = {}

with file ('data/positive.txt', 'rt') as f:
   for line in f.readlines():
       train_samples[line] = 'pos'

with file ('data/negative.txt', 'rt') as d:
   for line in d.readlines():
       train_samples[line] = 'neg'

f = open("data/test.txt", "r")
test_samples = f.readlines()

# Error in this code
# def bigramReturner(text):
#    tweetString = text.lower()
#    bigramFeatureVector = {}
#    for item in bigrams(tweetString.split()):
#        bigramFeatureVector.append(' '.join(item))
#    return bigramFeatureVector

# Updated the code from the stack overflow comment 
def bigramReturner (tweetString):
    tweetString = tweetString.lower()
    #comment the line since the function is not defined
    #tweetString = removePunctuation (tweetString)
    bigramFeatureVector = []
    for item in nltk.unigrams(tweetString.split()):
        bigramFeatureVector.append(' '.join(item))
    return bigramFeatureVector

def get_labeled_features(samples):
    word_freqs = {}
    for text, label in train_samples.items():
        tokens = text.split()
        for token in tokens:
            if token not in word_freqs:
                word_freqs[token] = {'pos': 0, 'neg': 0}
            word_freqs[token][label] += 1
    return word_freqs


def get_label_probdist(labeled_features):
    label_fd = FreqDist()
    for item, counts in labeled_features.items():
        for label in ['neg', 'pos']:
            if counts[label] > 0:
                label_fd.inc(label)
    label_probdist = ELEProbDist(label_fd)
    return label_probdist


def get_feature_probdist(labeled_features):
    feature_freqdist = defaultdict(FreqDist)
    feature_values = defaultdict(set)
    num_samples = len(train_samples) / 2
    for token, counts in labeled_features.items():
        for label in ['neg', 'pos']:
            feature_freqdist[label, token].inc(True, count=counts[label])
            feature_freqdist[label, token].inc(None, num_samples - counts[label])
            feature_values[token].add(None)
            feature_values[token].add(True)
    for item in feature_freqdist.items():
        print item[0], item[1]
    feature_probdist = {}
    for ((label, fname), freqdist) in feature_freqdist.items():
        probdist = ELEProbDist(freqdist, bins=len(feature_values[fname]))
        feature_probdist[label, fname] = probdist
    return feature_probdist



labeled_features = get_labeled_features(train_samples)

label_probdist = get_label_probdist(labeled_features)

feature_probdist = get_feature_probdist(labeled_features)

classifier = NaiveBayesClassifier(label_probdist, feature_probdist)


for sample in test_samples:
    print "%s | %s" % (sample, classifier.classify(bigramReturner(sample)))

但是当我运行代码时，出现以下错误：

Traceback (most recent call last):
  File "naive_bigram_1.py", line 87, in <module>
    print "%s | %s" % (sample, classifier.classify(bigramReturner(sample)))
  File "naive_bigram_1.py", line 30, in bigramReturner
    tweetString = removePunctuation (tweetString)
NameError: global name 'removePunctuation' is not defined

我看到了类似的问题和其他错误，在这里我也用朴素贝叶斯分类器更新了 n-grams

4

1 回答 1

-1

您正在调用removePunctuation以前未定义的函数：

def bigramReturner (tweetString):
    tweetString = tweetString.lower()
    tweetString = removePunctuation (tweetString)
    ....

我还注意到您在函数名称和参数列表之间放置了空格。避免这种情况，因为它不是真正地道的 Python，甚至可能导致一些问题（比如你的函数被评估为对象而不是被调用）。

于 2013-10-06T14:38:27.147 回答