用python写情感分类的代码

由于情感分类涉及到自然语言处理和机器学习等技术，需要用到许多库和算法。以下是一个简单的情感分类示例代码，使用了朴素贝叶斯算法和nltk库。

首先，安装nltk库：

pip install nltk

然后，引入必要的库：

import nltk
import random
from nltk.corpus import movie_reviews

接着，定义一个函数来提取文本的特征：

def extract_features(words):
    return dict([(word, True) for word in words])

然后，加载电影评论语料库，将每个评论的单词和情感（积极或消极）存储在一个列表中：

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

现在，我们可以使用特征提取函数来提取每个评论的特征，并将其拆分为训练集和测试集：

featuresets = [(extract_features(document), category) for (document, category) in documents]
train_set, test_set = featuresets[100:], featuresets[:100]

接着，我们可以使用朴素贝叶斯分类器来训练模型，并使用测试集进行评估：

classifier = nltk.NaiveBayesClassifier.train(train_set)
print("Accuracy:", nltk.classify.accuracy(classifier, test_set))

最后，我们可以使用模型来分类新的文本：

text = "This movie is great!"
features = extract_features(text.split())
print(classifier.classify(features))

完整的代码如下：

import nltk
import random
from nltk.corpus import movie_reviews

def extract_features(words):
    return dict([(word, True) for word in words])

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

featuresets = [(extract_features(document), category) for (document, category) in documents]
train_set, test_set = featuresets[100:], featuresets[:100]

classifier = nltk.NaiveBayesClassifier.train(train_set)
print("Accuracy:", nltk.classify.accuracy(classifier, test_set))

text = "This movie is great!"
features = extract_features(text.split())
print(classifier.classify(features))

输出：

Accuracy: 0.81
pos