机器学习-KNN小实战---乳腺癌预测

一、数据集导入

本项目采用sklearn中的 breast_cancer 的数据集，数据集源介绍sklearn.datasets.load_breast_cancer — scikit-learn 1.4.2 documentation

from sklearn.datasets import load_breast_cancer
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.neighbors import KNeighborsClassifier
from sklearn.preprocessing import StandardScaler

#导入 数据集
mydata = load_breast_cancer()

二、数据集预处理

# 划分数据集
x_train, x_test, y_train, y_test = train_test_split(mydata.data, mydata.target, test_size=0.3, random_state=32)

# 数据集标准化预处理
transformer = StandardScaler()
x_train = transformer.fit_transform(x_train)
x_test = transformer.fit_transform(x_test)

三、模型训练

model = KNeighborsClassifier()
# 交叉验证
param_grid = {'n_neighbors': [1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21]}
model = GridSearchCV(estimator=model, param_grid=param_grid, cv=5)
# 模型训练
model.fit(x_train, y_train)

四、模型评估

# 模型评估
y_predict = model.predict(x_test)
myresult = accuracy_score(y_test, y_predict)
print('myresult-->', myresult)

五、总结

这个乳腺癌的检测实战基于之前的鸢尾花预测，都是一些简单的分类问题，而这个是二分类，比较简单，总体来说，把项目分为三类就可以公式化学习：数据集导入，预处理、模型训练、模型评估。