使用Python实现ID3算法
时间: 2023-05-29 09:02:28 浏览: 40
ID3算法是一种决策树学习算法,用于分类问题。它通过计算信息增益来选择最佳特征作为分裂节点。
以下是使用Python实现ID3算法的示例代码:
```
import numpy as np
import pandas as pd
from collections import Counter
def entropy(target_col):
elements,counts = np.unique(target_col,return_counts = True)
entropy = np.sum([(-counts[i]/np.sum(counts))*np.log2(counts[i]/np.sum(counts)) for i in range(len(elements))])
return entropy
def InfoGain(data,split_attribute_name,target_name="class"):
total_entropy = entropy(data[target_name])
vals,counts= np.unique(data[split_attribute_name],return_counts=True)
Weighted_Entropy = np.sum([(counts[i]/np.sum(counts))*entropy(data.where(data[split_attribute_name]==vals[i]).dropna()[target_name]) for i in range(len(vals))])
Information_Gain = total_entropy - Weighted_Entropy
return Information_Gain
def ID3(data,originaldata,features,target_attribute_name="class",parent_node_class = None):
if len(np.unique(data[target_attribute_name])) <= 1:
return np.unique(data[target_attribute_name])[0]
elif len(data)==0:
return np.unique(originaldata[target_attribute_name])[np.argmax(np.unique(originaldata[target_attribute_name],return_counts=True)[1])]
elif len(features) ==0:
return parent_node_class
else:
parent_node_class = np.unique(data[target_attribute_name])[np.argmax(np.unique(data[target_attribute_name],return_counts=True)[1])]
item_values = [InfoGain(data,feature,target_attribute_name) for feature in features]
best_feature_index = np.argmax(item_values)
best_feature = features[best_feature_index]
tree = {best_feature:{}}
features = [i for i in features if i != best_feature]
for value in np.unique(data[best_feature]):
value = value
sub_data = data.where(data[best_feature] == value).dropna()
subtree = ID3(sub_data,data,features,target_attribute_name,parent_node_class)
tree[best_feature][value] = subtree
return(tree)