写一个用决策树进行文本分类的代码
时间: 2024-01-27 15:06:13 浏览: 41
好的,以下是一个简单的用决策树进行文本分类的Python代码:
```python
from sklearn.tree import DecisionTreeClassifier
from sklearn.feature_extraction.text import CountVectorizer
# 训练集和测试集数据
train_data = ['This is good', 'That is bad', 'This is bad', 'That is good']
train_labels = ['positive', 'negative', 'negative', 'positive']
test_data = ['This is good', 'That is good']
test_labels = ['positive', 'positive']
# 特征提取
count_vect = CountVectorizer()
X_train_counts = count_vect.fit_transform(train_data)
# 训练决策树模型
clf = DecisionTreeClassifier()
clf.fit(X_train_counts, train_labels)
# 预测测试集
X_test_counts = count_vect.transform(test_data)
predicted = clf.predict(X_test_counts)
# 输出预测结果
print(predicted)
```
在这个例子中,我们使用了sklearn库中的`DecisionTreeClassifier`和`CountVectorizer`来构建决策树模型和提取文本特征。我们首先定义了训练集和测试集数据,然后使用`CountVectorizer`来将文本数据转换为向量表示。接着,我们使用`DecisionTreeClassifier`来训练决策树模型,并使用测试集数据进行预测。最后,我们输出了预测结果。