决策树算法+sklearn库的实现

直接上代码，和我之前的SVM差不多，都是使用了sklearn库

from sklearn import tree
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction import DictVectorizer
import numpy as np
import graphviz


def load_data(filename):
    data = np.genfromtxt(filename, delimiter='\t')
    x = data[:, 1:]
    y = data[:, 0].astype(int)
    scaler = StandardScaler()  # 标准化函数
    x_std = scaler.fit_transform(x)  # 标准化
    # 将数据划分为训练集和测试集，test_size=.5表示50%的测试集
    x_train, x_test, y_train, y_test = train_test_split(x_std, y, test_size=.5)
    print(len(x_train), len(x_test), len(y_train), len(y_test))
    return x_train, x_test, y_train, y_test


def dec_tree(x_train, x_test, y_train, y_test):
    clf = tree.DecisionTreeClassifier()
    clf = clf.fit(x_train, y_train)

    # answer = clf.predict(x_test) 预测
    print(clf.score(x_test, y_test))

    dot_data = tree.export_graphviz(clf, out_file=None)
    graph = graphviz.Source(dot_data)
    graph.render(r"tree.dot")


if __name__ == '__main__':
    dec_tree(*load_data('txt/10/frame505/all.txt'))

import graphviz，我导入了graphviz，最后会生成一个dot文件，所以大家如果想要图形化查看dot文件，需要下载graphviz。

下载好之后，进入到终端，win+R，输入cmd，进入dot所在文件夹，使用

graphviz -Tpdf ***.dot -o ***.pdf

输入上面命令运行可以在当前文件夹生成pdf。

好了，这就是决策树的sklearn库实现，不调用库的实现方法后续给出