Question

我有以下功能：

def sample_handling(sample, lexicon, classification):
    featureset = []

    with open(sample, 'r') as f:
        contents = f.readlines()
        for l in contents[:hm_lines]:
            current_words = word_tokenize(l.lower())
            current_words = [lemmatizer.lemmatize(i) for i in current_words]
            features = np.zeros(len(lexicon))
            for word in current_words():
                if word.lower() in lexicon:
                    index_value = lexicon.index(word.lower())
                    features[index_value] += 1
            features = list(features)
            featureset.append([features, classification])

    return featureset

当我运行代码时，它会给我以下错误：

TypeError：＆＃39; list＆＃39;对象不可调用

这里有没有黯然失色？我在SO上跟踪了很多线程处理这个错误，但无法解决我的问题。

这是我的完整代码：

import nltk
from nltk.tokenize import word_tokenize
from nltk.stem import WordNetLemmatizer
import numpy as np
import random
import pickle
from collections import Counter

lemmatizer = WordNetLemmatizer()
hm_lines = 10000000

def create_lexicon(pos, neg):
    lexicon = []
    for fi in  [pos, neg]:
        with open(fi, 'r') as f:
            contents = f.readlines()
            for l in contents[:hm_lines]:
                all_words = word_tokenize(l.lower())
                lexicon += list(all_words)
    lexicon = [lemmatizer.lemmatize(i) for i in lexicon]
    w_counts = Counter(lexicon)
    #w_counts = {'the': 52521, 'and': 25242}

    l2 = []
    for w in w_counts:
        if 1000 > w_counts[w] > 50:
            l2.append(w)

    print(l2)
    return l2

def sample_handling(sample, lexicon, classification):
    featureset = []

    with open(sample, 'r') as f:
        contents = f.readlines()
        for l in contents[:hm_lines]:
            current_words = word_tokenize(l.lower())
            current_words = [lemmatizer.lemmatize(i) for i in current_words]
            features = np.zeros(len(lexicon))
            for word in current_words():
                if word.lower() in lexicon:
                    index_value = lexicon.index(word.lower())
                    features[index_value] += 1
            features = list(features)
            featureset.append([features, classification])

    return featureset

def create_feature_sets_and_lables(pos, neg, test_size = 0.1):
    lexicon = create_lexicon(pos, neg)
    features = []
    features += sample_handling('pos.txt', lexicon,[1,0])
    features += sample_handling('neg.txt', lexicon,[0,1])
    random.shuffle(features)

    features = np.array(features)

    testing_size = int(test_size * len(features))

    train_x = list(features[:,0][:-testing_size])
    train_y = list(features[:,1][:-testing_size])

    test_x = list(features[:,0][-testing_size:])
    test_y = list(features[:,1][-testing_size:])

    return train_x, train_y, test_x, test_y

if __name__ == '__main__':
    train_x, train_y, test_x, test_y = create_feature_sets_and_lables('pos.txt', 'neg.txt')
    with open('sentiment_set.pickle', 'wb') as f:
        pickle.dump([train_x, train_y, test_x, test_y], f)

Answer 1

好吧，要开始调试，我会使用

运行程序

python -m pdb whatever_your_file_is.py

这将启动一个pdb调试控制台。在那里，按＆＃39; c ＆＃39;运行程序。一段时间后，假设程序崩溃，您将在发生错误的确切位置停止。

从那里，您可以参考this或this（只是Google python pdb ）来确定代码中发生了什么。< / p> 祝你好运！

Answer 2

如果打印完整的堆栈跟踪会更有帮助。由于这是一个相对简单的错误，因此在这种情况下很容易识别问题。这就是这条线，

for word in current_words():

在循环播放列表时，您无需调用列表。这样就可以了，

for word in current_words:

TypeError：list对象不可调用

2 个答案: