《统计学习方法：李航》笔记 从原理到实现（基于python）-- 第5章 决策树（代码python实践）

第5章 决策树—python 实践

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inlinefrom sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from collections import Counter
import math
from math import log
import pprint

书上题目5.1

def create_data():datasets = [['青年', '否', '否', '一般', '否'],['青年', '否', '否', '好', '否'],['青年', '是', '否', '好', '是'],['青年', '是', '是', '一般', '是'],['青年', '否', '否', '一般', '否'],['中年', '否', '否', '一般', '否'],['中年', '否', '否', '好', '否'],['中年', '是', '是', '好', '是'],['中年', '否', '是', '非常好', '是'],['中年', '否', '是', '非常好', '是'],['老年', '否', '是', '非常好', '是'],['老年', '否', '是', '好', '是'],['老年', '是', '否', '好', '是'],['老年', '是', '否', '非常好', '是'],['老年', '否', '否', '一般', '否'],]labels = [u'年龄', u'有工作', u'有自己的房子', u'信贷情况', u'类别']# 返回数据集和每个维度的名称return datasets, labels

datasets, labels = create_data()
train_data = pd.DataFrame(datasets, columns=labels)

	# 熵
def calc_ent(datasets):data_length = len(datasets)label_count = {}for i in range(data_length):label = datasets[i][-1]if label not in label_count:label_count[label] = 0label_count[label] += 1ent = -sum([(p / data_length) * log(p / data_length, 2)for p in label_count.values()])return ent# 经验条件熵
def cond_ent(datasets, axis=0):data_length = len(datasets)feature_sets = {}for i in range(data_length):feature = datasets[i][axis]if feature not in feature_sets:feature_sets[feature] = []feature_sets[feature].append(datasets[i])cond_ent = sum([(len(p) / data_length) * calc_ent(p) for p in feature_sets.values()])return cond_ent# 信息增益：熵-经验条件熵
def info_gain(ent, cond_ent):return ent - cond_entdef info_gain_train(datasets):count = len(datasets[0]) - 1ent = calc_ent(datasets)best_feature = []for c in range(count):c_info_gain = info_gain(ent, cond_ent(datasets, axis=c))best_feature.append((c, c_info_gain))print('特征({}) - info_gain - {:.3f}'.format(labels[c], c_info_gain))# 比较大小best_ = max(best_feature, key=lambda x: x[-1])return '特征({})的信息增益最大，选择为根节点特征'.format(labels[best_[0]])

info_gain_train(np.array(datasets))
===================================
特征(年龄) - info_gain - 0.083
特征(有工作) - info_gain - 0.324
特征(有自己的房子) - info_gain - 0.420
特征(信贷情况) - info_gain - 0.363
'特征(有自己的房子)的信息增益最大，选择为根节点特征'

利用ID3算法生成决策树，例5.3

# 定义节点类 二叉树
class Node:def __init__(self, root=True, label=None, feature_name=None, feature=None):self.root = rootself.label = labelself.feature_name = feature_nameself.feature = featureself.tree = {}self.result = {'label:': self.label,'feature': self.feature,'tree': self.tree}def __repr__(self):return '{}'.format(self.result)def add_node(self, val, node):self.tree[val] = nodedef predict(self, features):if self.root is True:return self.labelreturn self.tree[features[self.feature]].predict(features)class DTree:def __init__(self, epsilon=0.1):self.epsilon = epsilonself._tree = {}# 熵@staticmethoddef calc_ent(datasets):data_length = len(datasets)label_count = {}for i in range(data_length):label = datasets[i][-1]if label not in label_count:label_count[label] = 0label_count[label] += 1ent = -sum([(p / data_length) * log(p / data_length, 2)for p in label_count.values()])return ent# 经验条件熵def cond_ent(self, datasets, axis=0):data_length = len(datasets)feature_sets = {}for i in range(data_length):feature = datasets[i][axis]if feature not in feature_sets:feature_sets[feature] = []feature_sets[feature].append(datasets[i])cond_ent = sum([(len(p) / data_length) * self.calc_ent(p)for p in feature_sets.values()])return cond_ent# 信息增益@staticmethoddef info_gain(ent, cond_ent):return ent - cond_entdef info_gain_train(self, datasets):count = len(datasets[0]) - 1ent = self.calc_ent(datasets)best_feature = []for c in range(count):c_info_gain = self.info_gain(ent, self.cond_ent(datasets, axis=c))best_feature.append((c, c_info_gain))# 比较大小best_ = max(best_feature, key=lambda x: x[-1])return best_def train(self, train_data):"""input:数据集D(DataFrame格式)，特征集A，阈值etaoutput:决策树T"""_, y_train, features = train_data.iloc[:, :-1], train_data.iloc[:,-1], train_data.columns[:-1]# 1,若D中实例属于同一类Ck，则T为单节点树，并将类Ck作为结点的类标记，返回Tif len(y_train.value_counts()) == 1:return Node(root=True, label=y_train.iloc[0])# 2, 若A为空，则T为单节点树，将D中实例树最大的类Ck作为该节点的类标记，返回Tif len(features) == 0:return Node(root=True,label=y_train.value_counts().sort_values(ascending=False).index[0])# 3,计算最大信息增益 同5.1,Ag为信息增益最大的特征max_feature, max_info_gain = self.info_gain_train(np.array(train_data))max_feature_name = features[max_feature]# 4,Ag的信息增益小于阈值eta,则置T为单节点树，并将D中是实例数最大的类Ck作为该节点的类标记，返回Tif max_info_gain < self.epsilon:return Node(root=True,label=y_train.value_counts().sort_values(ascending=False).index[0])# 5,构建Ag子集node_tree = Node(root=False, feature_name=max_feature_name, feature=max_feature)feature_list = train_data[max_feature_name].value_counts().indexfor f in feature_list:sub_train_df = train_data.loc[train_data[max_feature_name] ==f].drop([max_feature_name], axis=1)# 6, 递归生成树sub_tree = self.train(sub_train_df)node_tree.add_node(f, sub_tree)# pprint.pprint(node_tree.tree)return node_treedef fit(self, train_data):self._tree = self.train(train_data)return self._treedef predict(self, X_test):return self._tree.predict(X_test)

datasets, labels = create_data()
data_df = pd.DataFrame(datasets, columns=labels)
dt = DTree()
tree = dt.fit(data_df)

tree
=============================
{'label:': None, 'feature': 2, 'tree': {'否': {'label:': None, 'feature': 1, 'tree': {'否': {'label:': '否', 'feature': None, 'tree': {}}, '是': {'label:': '是', 'feature': None, 'tree': {}}}}, '是': {'label:': '是', 'feature': None, 'tree': {}}}}

dt.predict(['老年', '否', '否', '一般'])
================================
'否'

scikit-learn实例

# data
def create_data():iris = load_iris()df = pd.DataFrame(iris.data, columns=iris.feature_names)df['label'] = iris.targetdf.columns = ['sepal length', 'sepal width', 'petal length', 'petal width', 'label']data = np.array(df.iloc[:100, [0, 1, -1]])# print(data)return data[:, :2], data[:, -1]X, y = create_data()
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)

from sklearn.tree import DecisionTreeClassifier
from sklearn.tree import export_graphviz
import graphviz

clf = DecisionTreeClassifier()
clf.fit(X_train, y_train,)
===================================
DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,max_features=None, max_leaf_nodes=None,min_impurity_decrease=0.0, min_impurity_split=None,min_samples_leaf=1, min_samples_split=2,min_weight_fraction_leaf=0.0, presort=False, random_state=None,splitter='best')

clf.score(X_test, y_test)
==============================
0.9666666666666667

tree_pic = export_graphviz(clf, out_file="mytree.pdf")
with open('mytree.pdf') as f:dot_graph = f.read()==============================
graphviz.Source(dot_graph)
<graphviz.files.Source at 0x1f159bc2780>