1.导入包
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
2.实现熵、经验条件熵、信息增益
# 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
# 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)
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))
3.房贷数据集实现和根节点特征
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)
train_data
4.定义二叉树
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，返回T
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)
5.决策树并测试
datasets, labels = create_data()
data_df = pd.DataFrame(datasets, columns=labels)
dt = DTree()
tree = dt.fit(data_df)
tree
dt.predict(['老年', '否', '否', '一般'])
6.用iris数据集应用sklearn决策树算法进行类别预测
##sklearn.tree.DecisionTreeClassifier
# data
def create_data():
iris = load_iris()
df = pd.DataFrame(iris.data, columns=iris.feature_names)
df['label'] = iris.target
df.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,)
clf.score(X_test, y_test)
7.用graphviz画图
tree_pic = export_graphviz(clf, out_file="mytree.pdf")
with open('mytree.pdf') as f:
dot_graph = f.read()
graphviz.Source(dot_graph)
8.问题描述：当中会没有graphgiz这个包，去官网下载配置环境并用pip install 安装就行了
9.小结
ID3算法应用场景：
它的基础理论清晰，算法比较简单，学习能力较强，适于处理大规模的学习问题，是数据挖掘和知识发现领域中的一个很好的范例，为后来各学者提出优化算法奠定了理论基础。ID3算法特别在机器学习、知识发现和数据挖掘等领域得到了极大发展。
C4.5算法具有条理清晰，能处理连续型属性，防止过拟合，准确率较高和适用范围广等优点，是一个很有实用价值的决策树算法，可以用来分类，也可以用来回归。C4.5算法在机器学习、知识发现、金融分析、遥感影像分类、生产制造、分子生物学和数据挖掘等领域得到广泛应用。
剪枝的目的在于：缓解决策树的"过拟合"，降低模型复杂度，提高模型整体的学习效率
预剪枝：是指在决策树生成过程中，对每一个结点在划分前进行估计，若当前结点的划分不能带来决策树泛化性能提升，则停止划分并将当前结点标记为叶子结点。
优点：降低了过拟合地风险，并显著减少了决策树地训练时间开销和测试时间开销。
缺点：有些分支地当前划分虽不能提升泛化性能、甚至可能导致泛化性能下降，但是在其基础上进行地后续划分却可能导致性能显著提高；
后剪枝：先从训练集生成一棵完整的决策树，然后自底向上地对非叶子结点进行考察，若将该结点对应地子树替换为叶结点能带来决策树泛化性能提升，则将该子树替换为叶结点。
优点：一般情况下后剪枝决策树的欠拟合风险很小，泛化性能往往优于预剪枝决策树。
缺点：自底向上的注意考察，时间开销较高。
标签：datasets,self,feature,算法,train,实验,ent,data,决策树 From： https://www.cnblogs.com/1759945451qq/p/16838608.html