组合不同类型的特征（文本分类）

Question

我正在做文本分类任务，我遇到了一个问题。 我已经使用词袋方法选择了 1000 个最佳特征集合。现在我想使用基于词性、平均词长等的其他功能。在我想将这些功能组合在一起之后。我怎样才能实现它 我正在使用 Python、NLTK、Scikit 包。这是我的第一个 python 项目，所以代码可能不是很好。

提前致谢，

    import nltk
    from nltk.corpus.reader import CategorizedPlaintextCorpusReader
    from sklearn.feature_extraction.text import TfidfVectorizer
    import os
    import numpy as np
    import random
    import pickle
    from time import time
    from sklearn import metrics

    from nltk.classify.scikitlearn import SklearnClassifier
    from sklearn.naive_bayes import MultinomialNB,BernoulliNB
    from sklearn.linear_model import LogisticRegression,SGDClassifier
    from sklearn.svm import SVC, LinearSVC, NuSVC

    import matplotlib.pyplot as plt

    def intersect(a, b, c, d):
        return list(set(a) & set(b)& set(c)& set(d))

    def find_features(document, feauture_list):
        words = set(document)
        features = {}
        for w in feauture_list:
            features[w] = (w in words)
        return features


    def benchmark(clf, name, training_set, testing_set):

        print('_' * 80)
        print("Training: ")
        print(clf)
        t0 = time()
        clf.train(training_set)
        train_time = time() - t0
        print("train time: %0.3fs" % train_time)

        t0 = time()
        score = nltk.classify.accuracy(clf, testing_set)*100
        #pred = clf.predict(testing_set)
        test_time = time() - t0

        print("test time:  %0.3fs" % test_time)

        print("accuracy:   %0.3f" % score)
        clf_descr = name
        return clf_descr, score, train_time, test_time

        #print((find_features(corpus.words('fantasy/1077-0_fantasy.txt'),feature_list)))
    path = 'c:/data/books-Copy'
    os.chdir(path)
         #need this if you want to save tfidf_matrix
    corpus = CategorizedPlaintextCorpusReader(path, r'.*\.txt', 
                                                  cat_pattern=r'(\w+)/*')
    save_featuresets = open(path +"/features_500.pickle","rb")
    featuresets = []
    featuresets = pickle.load(save_featuresets)
    save_featuresets.close()

    documents = [(list(corpus.words(fileid)), category)
                 for category in corpus.categories()
                 for fileid in corpus.fileids(category)]

    random.shuffle(documents)

    tf = TfidfVectorizer(analyzer='word', min_df = 1, 
                         stop_words = 'english', sublinear_tf=True)
    #documents_tfidf = []
    top_features = []
    tf = TfidfVectorizer(input= 'filename', analyzer='word',
                         min_df = 1, stop_words = 'english', sublinear_tf=True)

    for category in corpus.categories():
        files = corpus.fileids(category)
        tf.fit_transform( files )
        feature_names = tf.get_feature_names()
        #documents_tfidf.append(feature_names)
        indices = np.argsort(tf.idf_)[::-1]
        top_features.append([feature_names[i] for i in indices[:10000]])
        #print(top_features_detective)

    feature_list = list( set(top_features[0][:500]) | set(top_features[1][:500]) | 
                         set(top_features[2][:500])  | set(top_features[3][:500]) | 
                         set(intersect(top_features[0], top_features[1], top_features[2], top_features[3])))


    featuresets = [(find_features(rev, feature_list), category) for (rev, category) in documents]  
training_set = featuresets[:50]
testing_set =  featuresets[20:]
results = []
for clf, name in (
                          (SklearnClassifier(MultinomialNB()), "MultinomialNB"),
                          (SklearnClassifier(BernoulliNB()),   "BernoulliNB"),
                          (SklearnClassifier(LogisticRegression()), "LogisticRegression"),
                          (SklearnClassifier(SVC()),   "SVC"),
                          (SklearnClassifier(LinearSVC()),   "Linear SVC "),
                          (SklearnClassifier(SGDClassifier()),   "SGD ")):
    print(name)
    results.append(benchmark(clf, name, training_set, testing_set))

indices = np.arange(len(results))
results = [[x[i] for x in results] for i in range(4)]

clf_names, score, training_time, test_time = results
training_time = np.array(training_time) / np.max(training_time)
test_time = np.array(test_time) / np.max(test_time)



plt.figure(figsize=(12, 8))
plt.title("Score")
plt.barh(indices, score, .2, label="score", color='navy')
plt.barh(indices + .3, training_time, .2, label="training time",
                 color='c')
plt.barh(indices + .6, test_time, .2, label="test time", color='darkorange')
plt.yticks(())
plt.legend(loc='best')
plt.subplots_adjust(left=.25)
plt.subplots_adjust(top=.95)
plt.subplots_adjust(bottom=.05)

for i, c in zip(indices, clf_names):
    plt.text(-15.6, i, c)
    plt.show() 

Answer 1

将不同类型的特征组合起来并没有错（事实上，这通常是分类任务的好主意）。 NLTK 的 API 期望特征出现在字典中，因此您只需将特征集合合并到一个字典中即可。

这是您所提问题的答案。如果您的代码有问题需要帮助但没有询问，您可能应该开始一个新问题。