在Python中使用决策树进行模型压缩的实现方法

from sklearn.tree import DecisionTreeClassifier, export_graphviz
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
import graphviz 

digits = load_digits() #加载手写数字数据集
X_train, X_test, y_train, y_test = train_test_split(digits.data, digits.target, random_state=42) #切分数据集

clf = DecisionTreeClassifier(random_state=42) #初始化决策树分类器
clf.fit(X_train, y_train) #训练模型
y_pred = clf.predict(X_test) #预测测试数据
acc = accuracy_score(y_test, y_pred) #计算准确率
print("Accuracy before pruning: {:.2f}%".format(acc*100))

dot_data = export_graphviz(clf, out_file=None, filled=True, rounded=True, special_characters=True)
graph = graphviz.Source(dot_data) 
graph.view() #打开决策树可视化界面

from sklearn.tree import DecisionTreeRegressor
from sklearn.model_selection import GridSearchCV

#定义一个函数来计算模型中非叶子节点的数量
def count_nodes(tree):
    cnt = 0
    if tree.get_n_leaves() != 1:
        cnt += 1
    for c in tree.children_:
        if c is not None:
            cnt += count_nodes(c)
    return cnt

#使用决策树回归器对决策树分类器进行压缩
clf = DecisionTreeRegressor(criterion='mse', splitter='best', max_depth=10, min_samples_split=2, min_samples_leaf=1, max_features=None, random_state=42)
param_grid = {
    'max_depth': [2, 3, 4, 5],
    'min_samples_split': [2, 3, 4],
    'min_samples_leaf': [1, 2, 3],
}
search = GridSearchCV(clf, param_grid, cv=10)
search.fit(X_train, y_train)

clf = search.best_estimator_
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
acc = accuracy_score(y_test, y_pred.round())
print("Accuracy after pruning: {:.2f}%".format(acc*100))
print("Number of nodes before pruning: {}".format(count_nodes(clf.tree_)))

dot_data = export_graphviz(clf, out_file=None, filled=True, rounded=True, special_characters=True)
graph = graphviz.Source(dot_data) 
graph.view() #打开决策树可视化界面