数据挖掘 —— 半监督学习（标签传播算法）

标签传播算法

参数解释

标签传播算法要求为标注数据标签为1

LablePropagation(kernel,gamma,n_neighbors)

• kernel:{“knn”,“rbf”}
• gamma:rbf中的r
• n_neighbors:knn中的参数

代码

from sklearn.datasets import load_iris
from sklearn.semi_supervised import LabelPropagation
import numpy as np
import pandas as pd
from sklearn.metrics import accuracy_score,recall_score,f1_score
iris = load_iris()
labels = np.copy(iris.target)
labels[np.random.rand(len(labels)) < 0.3] = -1
label_prop_model = LabelPropagation()
label_prop_model.fit(iris.data,labels)
label_predict = label_prop_model.predict(iris.data)
print("acc_score:",accuracy_score(iris.target,label_predict))
print("acc_score:",recall_score(iris.target,label_predict,average="macro"))
print("acc_score:",f1_score(iris.target,label_predict,average="macro"))

结果

acc_score: 0.98
acc_score: 0.98
acc_score: 0.9799819837854069

by CyrusMay 2022 04 05