每日总结51

from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split



# 加载 iris 数据集

iris = load_iris()

X, y = iris.data, iris.target



# 使用 train_test_split 函数留出 1/3 的样本作为测试集

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=1/3, random_state=42, stratify=y)



from sklearn.cluster import KMeans



# 创建 KMeans 模型，设置类别数为 3

kmeans = KMeans(n_clusters=3, random_state=42)



# 使用训练集训练模型

kmeans.fit(X_train, y_train)



from sklearn.model_selection import cross_val_score

from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score



# 定义一个函数来评估模型性能

def evaluate_model(X, y):

    kmeans = KMeans(n_clusters=3, random_state=42)

    scores = cross_val_score(kmeans, X, y, cv=5, scoring='f1_macro')

    return scores.mean()



# 评估模型性能

f1_macro_score = evaluate_model(X_train, y_train)

print(f"F1 Macro Score: {f1_macro_score}")



# 使用训练好的模型对测试集进行预测

y_pred = kmeans.predict(X_test)



# 计算准确度、精度、召回率和 F1 值

accuracy = accuracy_score(y_test, y_pred)

precision = precision_score(y_test, y_pred, average='macro')

recall = recall_score(y_test, y_pred, average='macro')

f1 = f1_score(y_test, y_pred, average='macro')



print(f"Accuracy: {accuracy}")

print(f"Precision: {precision}")

print(f"Recall: {recall}")

print(f"F1 Score: {f1}")