from nltk.corpus import PlaintextCorpusReader \u00a0# \u5bfc\u5165PlaintextCorpusReader \u7528\u4e8e\u8bfb\u53d6\u6587\u672c\u8bed\u6599\u5e93<\/span><\/code><\/p>\n

import nltk \u00a0# \u5bfc\u5165 Natural Language Toolkit\uff08nltk\uff09\u5e93\uff0c\u7528\u4e8e\u81ea\u7136\u8bed\u8a00\u5904\u7406\u4efb\u52a1<\/span><\/code><\/p>\n

<\/code><\/code><\/p>\n

# \u6307\u5b9a\u8bed\u6599\u5e93\u7684\u6839\u76ee\u5f55\uff0c\u5373\u5305\u542b\u6587\u672c\u6587\u4ef6\u7684\u6587\u4ef6\u5939\u8def\u5f84<\/span><\/code><\/p>\n

corpus_root = r\"D:\u5b66\u4e60\u8bed\u6599\u5e93\u4e2d\u56fd\u653f\u6cbb\u6587\u672c\u8bed\u6599\u5e93\"<\/span><\/code><\/p>\n

<\/code><\/p>\n

<\/code># \u521b\u5efa PlaintextCorpusReader \u5bf9\u8c61\uff0c\u6307\u5b9a\u8bed\u6599\u5e93\u7684\u6839\u76ee\u5f55\u548c\u8981\u8bfb\u53d6\u7684\u6587\u4ef6\u5217\u8868<\/span><\/code><\/p>\n

corpora = PlaintextCorpusReader(corpus_root, ['jiang selected 1.txt'])<\/span><\/code><\/p>\n

<\/code><\/p>\n

<\/code># \u83b7\u53d6\u8bed\u6599\u5e93\u4e2d\u7684\u6587\u4ef6\u6807\u8bc6\u7b26\uff08\u6587\u4ef6\u540d\uff09\uff0c\u8fd9\u91cc\u53ea\u6709\u4e00\u4e2a\u6587\u4ef6 'jiang selected 1.txt'<\/span><\/code><\/p>\n

corpora.fileids()<\/span><\/code><\/p>\n

<\/code><\/p>\n

<\/code># \u521b\u5efa\u4e00\u4e2a\u7a7a\u5217\u8868 'pairs'\uff0c\u7528\u4e8e\u5b58\u50a8\u6761\u4ef6-\u4e8b\u4ef6\u5bf9<\/span><\/code><\/p>\n

pairs = [(field, word)<\/span><\/code><\/p>\n

\u00a0 \u00a0 \u00a0 \u00a0 for field in corpora.fileids() \u00a0# \u904d\u5386\u8bed\u6599\u5e93\u4e2d\u7684\u6587\u4ef6\u6807\u8bc6\u7b26<\/span><\/code><\/p>\n

\u00a0 \u00a0 \u00a0 \u00a0 for word in [word.lower() for word in corpora.words(field)]] \u00a0# \u904d\u5386\u6587\u4ef6\u4e2d\u7684\u6bcf\u4e2a\u5355\u8bcd\uff0c\u5c06\u5355\u8bcd\u8f6c\u6362\u4e3a\u5c0f\u5199<\/span><\/code><\/p>\n

<\/code><\/p>\n

<\/code># \u4f7f\u7528 nltk \u5e93\u4e2d\u7684 ConditionalFreqDist \u521b\u5efa\u6761\u4ef6\u9891\u7387\u5206\u5e03\u5bf9\u8c61 '<\/span><\/code>cfd'<\/span><\/code><\/p>\n

cfd = nltk.ConditionalFreqDist(pairs)<\/span><\/code><\/p>\n

<\/code><\/p>\n

<\/code># \u5b9a\u4e49\u8981\u5206\u6790\u7684\u6587\u672c\u6587\u4ef6\u540d<\/span><\/code><\/p>\n

corpus_text = ['jiang selected 1.txt']<\/span><\/code><\/p>\n

<\/code><\/p>\n

<\/code># \u5b9a\u4e49\u8981\u7edf\u8ba1\u7684\u60c5\u6001\u52a8\u8bcd\u5217\u8868<\/span><\/code><\/p>\n

count_word = ['can', 'could', 'may', 'might', 'must', 'will', 'shall', 'should']<\/span><\/code><\/p>\n

<\/code><\/p>\n

<\/code># \u4f7f\u7528 cfd.plot() \u65b9\u6cd5\u7ed8\u5236\u6761\u4ef6\u9891\u7387\u5206\u5e03\u56fe<\/span><\/code><\/p>\n

# conditions \u53c2\u6570\u6307\u5b9a\u8981\u7ed8\u5236\u7684\u6761\u4ef6\uff08\u6587\u672c\u6587\u4ef6\u540d\uff09\uff0csamples \u53c2\u6570\u6307\u5b9a\u8981\u7edf\u8ba1\u7684\u4e8b\u4ef6\uff08\u60c5\u6001\u52a8\u8bcd\uff09<\/span><\/code><\/p>\n

cfd.plot(conditions=corpus_text, samples=count_word)<\/span><\/code><\/p>\n<\/section>\n

\n

\u8fd0\u884c\u7ed3\u679c\u5982\u4e0b\uff1a<\/span><\/p>\n

<\/span><\/p>\n

\u6bcf\u65e5\u5543\u4e00\u6bb5\u4ee3\u7801\uff0c\u65e5\u79ef\u6708\u7d2f\uff0c\u6211\u4eec\u53ef\u4ee5\u8de8\u8d8a\u8fd9\u6761\u9e3f\u6c9f\uff0c\u82e5\u662f\u8fd8\u672a\u5165\u95e8Python,\u53ef\u52a0\u5165\u6211\u4eec\u7684\u5fae\u4fe1\u516c\u4f17\u53f7\u201c\u7ffb\u8bd1\u5708\u201d\u7c89\u4e1d\u7fa4\u514d\u8d39\u83b7\u53d6\u300a\u7b2c\u4e00\u672c\u4e66Python\u300b,\u5feb\u901f\u5165\u95e8\uff01<\/span><\/p>\n

\u5f80\u671f\u4ee3\u7801\u5408\u96c6\u53ef\u5728\u516c\u4f17\u53f7\u540e\u53f0\u56de\u590d\u4ee3\u7801\u5206\u4eab<\/strong>\u6216\u8005\u52a0\u5165\u7c89\u4e1d\u7fa4\u83b7\u53d6\uff0c\u7c89\u4e1d\u7fa4\u8fd8\u6709\u5176\u5b83\u8d44\u6e90\u54e6\uff01<\/span><\/p>\n

<\/p>\n

\u53c2\u8003\u4e66\u85c9\uff1aPython\u8bed\u8a00\u6570\u636e\u5206\u6790 \u7ba1\u65b0\u6f6e \u8457<\/span><\/p>\n