# encoding:utf-8
import numpy as np
import pandas as pd
from math import log
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']
return datasets, 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] = 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，选择为根结点特征'.format(labels[best[0]])
"""生成数据集以及每列元素名称"""
datasets, labels = create_data()
"""设定数据集的格式"""
train_data = pd.DataFrame(datasets, columns=labels)
# list = np.array(datasets)
# for i in range(len(list)):
# print(list[i])
info_gain_train(np.array(datasets))
# encoding:utf-8
from sklearn.tree import DecisionTreeClassifier
from sklearn.tree import export_graphviz
import graphviz
import numpy as np
import pandas as pd
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
"""数据"""
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)
clf = DecisionTreeClassifier()
clf.fit(x_train, y_train)
clf.score(x_test, y_test)
tree_pic = export_graphviz(clf, out_file="mytree.pdf")
with open("mytree.pdf") as f:
dot_graph = f.read()
graphviz.Source(dot_graph)
# encoding:utf-8
import numpy as np
import pandas as pd
from math import log
"""定义结点类 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
"""
_, 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为单结点树，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为单结点树，将D中实例数最大的类Ck作为该结点的类标记，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为单结点树，并将D中实例数最大的类Ck作为该结点的类标记，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)
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)
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()
data_df = pd.DataFrame(datasets, columns=labels)
dt = DTree()
tree = dt.fit(data_df)
print(dt.predict(['老年', '否', '否', '一般']))