机器学习day4

代码展示

import matplotlib.pyplot as plt
from sklearn.datasets import load_breast_cancer
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import cross_val_score
from sklearn.metrics import accuracy_score
# 获取数据集
breast_cancer = load_breast_cancer()
# print(breast_cancer)
 
# 数据基本处理-划分数据集
x_train, x_test, y_train, y_test = train_test_split(breast_cancer.data, breast_cancer.target, test_size=0.2, random_state=22)
 
# 数据预处理-数据标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.fit_transform(x_test)
# print(x_train)
 
# 模型训练
# estimator = KNeighborsClassifier(n_neighbors=5)
# estimator.fit(x_train, y_train)
# # 模型评估
# myscore = estimator.score(x_test, y_test)
# print(myscore)
 
# 设定K值的范围
k_range = range(1, 10)
k_scores = []
 
# 交叉验证
for k in k_range:
    estimator = KNeighborsClassifier(n_neighbors=k)
    scores = cross_val_score(estimator, x_train, y_train, cv=5, scoring='accuracy')
    k_scores.append(scores.mean())
 
# 绘制K值与准确率的关系图
plt.plot(k_range, k_scores)
plt.xlabel('Value of K for KNN')
plt.ylabel('Cross-Validated Accuracy')
plt.title('Accuracy scores for Values of K')
plt.show()
 
# 找到最优的K值
optimal_k = k_scores.index(max(k_scores)) + 1
print(optimal_k)
 
# 使用最优的K值重新训练模型
estimator_optimal = KNeighborsClassifier(n_neighbors=optimal_k)
estimator_optimal.fit(x_train, y_train)
 
# 使用最优模型进行预测
y_pred_optimal = estimator_optimal.predict(x_test)
 
 
# 计算最优模型的准确率
accuracy_optimal = accuracy_score(y_test, y_pred_optimal)
print(accuracy_optimal)
 

效果图