【Python NLTK】自然语言处理利器，打造人工智能对话系统

import nltkfrom nltk.corpus import stopWordsfrom nltk.tokenize import word_tokenizefrom nltk.stem import PorterStemmer

text = "Hello, how are you? I am doing great."text = text.lower()text = "".join([ch for ch in text if ch.isalnum() or ch.isspace()])stop_words = set(stopwords.words("english"))text = " ".join([word for word in word_tokenize(text) if word not in stop_words])stemmer = PorterStemmer()text = " ".join([stemmer.stem(word) for word in word_tokenize(text)])

from nltk.classify import NaiveBayesClassifierfrom nltk.corpus import movie_reviewsclassified_reviews = [(cateGory, text) for category in movie_reviews.categories()for fileid in movie_reviews.fileids(category)for text in movie_reviews.words(fileid)]feature_extractor = lambda review: {word: True for word in review if word in feature_set}feature_set = set([word for (category, review) in classified_reviews for word in review if word not in stop_words])train_set, test_set = classified_reviews[50:], classified_reviews[:50]classifier = NaiveBayesClassifier.train(train_set, feature_extractor)

user_input = "I am looking for a good movie to watch."features = feature_extractor(user_input)category = classifier.classify(features)print(category)