实验四 决策树算法及应用
| 这个作业属于哪个课程 | https://edu.cnblogs.com/campus/ahgc/machinelearning |
|---|---|
| 这个作业要求在哪里 | https://edu.cnblogs.com/campus/ahgc/machinelearning/homework/12086 |
| 这个作业的目标 | <理解和实现决策树算法> |
| 学号 | <3180701330> |
实验四 决策树算法及应用
【实验目的】
理解决策树算法原理，掌握决策树算法框架；
理解决策树学习算法的特征选择、树的生成和树的剪枝；
能根据不同的数据类型，选择不同的决策树算法；
针对特定应用场景及数据，能应用决策树算法解决实际问题。
【实验内容】
设计算法实现熵、经验条件熵、信息增益等方法。
实现ID3算法。
熟悉sklearn库中的决策树算法；
针对iris数据集，应用sklearn的决策树算法进行类别预测。
针对iris数据集，利用自编决策树算法进行类别预测。
【实验报告要求】
对照实验内容，撰写实验过程、算法及测试结果；
代码规范化：命名规则、注释；
分析核心算法的复杂度；
查阅文献，讨论ID3、5算法的应用场景；
查询文献，分析决策树剪枝策略。
【实验过程及步骤】
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
from 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
datasets, labels = create_data()
train_data = pd.DataFrame(datasets, columns=labels)
train_data
# 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] = 0
label_count[label] += 1
ent = -sum([(p / data_length) * log(p / data_length, 2)
for p in label_count.values()])
return ent
# def entropy(y):
# """
# Entropy of a label sequence
# """
# hist = np.bincount(y)
# ps = hist / np.sum(hist)
# return -np.sum([p * np.log2(p) for p in ps if p > 0])
# 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
def info_gain(ent, cond_ent):
return ent - cond_ent
def info_gain_train(datasets):
count = len(datasets[0]) - 1
ent = calc_ent(datasets)
# ent = entropy(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))
# 定义节点类 二叉树
class Node:
def __init__(self, root=True, label=None, feature_name=None, feature=None):
self.root = root
self.label = label
self.feature_name = feature_name
self.feature = feature
self.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] = node
def predict(self, features):
if self.root is True:
return self.label
return self.tree[features[self.feature]].predict(features)
class DTree:
def __init__(self, epsilon=0.1):
self.epsilon = epsilon
self._tree = {}
# 熵
@staticmethod
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] = 0
label_count[label] += 1
ent = -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
@staticmethod
def info_gain(ent, cond_ent):
return ent - cond_ent
def info_gain_train(self, datasets):
count = len(datasets[0]) - 1
ent = 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eta
output: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T
if 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T
if 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
if 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().index
for 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_tree
def fit(self, train_data):
self._tree = self.train(train_data)
return self._tree
def predict(self, X_test):
return self._tree.predict(X_test)
【实验小结】
决策树算法非常容易过拟合，导致泛化能力不强。可以通过设置节点最少样本数量和限制决策树深度来改进。
决策树会因为样本发生一点点的改动（特别是在节点的末梢），导致树结构的剧烈改变。可以通过集成学习之类的方法解决。
