sklearn的乳腺癌预测2024/4/25

from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import StandardScaler

# 加载乳腺癌数据集
data = load_breast_cancer()
X = data.data
y = data.target
print(X)
print(y)
# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(data.data, data.target,  test_size=0.1, random_state=22)

#数据标准化
transfer = StandardScaler()
X_train = transfer.fit_transform(X_train)
X_test = transfer.fit_transform(X_test)
print(X_train)
print(X_test)

# 使用随机森林分类器进行训练
clf = RandomForestClassifier()
clf.fit(X_train, y_train)

# 预测测试集
y_result = clf.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_result)
print("准确率：", accuracy)