由于不清楚具体想要的是哪种数据挖掘方法的代码，以下为几种常见数据挖掘方法的代码示例： ### 决策树 ```python from sklearn.datasets import load_iris from sklearn.model_selection import train_test_split from sklearn.tree import DecisionTreeClassifier from sklearn.metrics import accuracy_score # 加载鸢尾花数据集 iris = load_iris() X = iris.data y = iris.target # 划分训练集和测试集 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42) # 创建决策树分类器 clf = DecisionTreeClassifier() # 训练模型 clf.fit(X_train, y_train) # 预测 y_pred = clf.predict(X_test) # 计算准确率 accuracy = accuracy_score(y_test, y_pred) print(f"Accuracy: {accuracy}") ``` ### 关联规则挖掘（Apriori算法） ```python from mlxtend.preprocessing import TransactionEncoder from mlxtend.frequent_patterns import apriori, association_rules import pandas as pd # 示例数据 dataset = [['Milk', 'Onion', 'Nutmeg', 'Kidney Beans', 'Eggs', 'Yogurt'], ['Dill', 'Onion', 'Nutmeg', 'Kidney Beans', 'Eggs', 'Yogurt'], ['Milk', 'Apple', 'Kidney Beans', 'Eggs'], ['Milk', 'Unicorn', 'Corn', 'Kidney Beans', 'Yogurt'], ['Corn', 'Onion', 'Onion', 'Kidney Beans', 'Ice cream', 'Eggs']] # 数据编码 te = TransactionEncoder() te_ary = te.fit(dataset).transform(dataset) df = pd.DataFrame(te_ary, columns=te.columns_) # 挖掘频繁项集 frequent_itemsets = apriori(df, min_support=0.6, use_colnames=True) # 生成关联规则 rules = association_rules(frequent_itemsets, metric="confidence", min_threshold=0.7) print(rules) ``` ### K-Means聚类 ```python from sklearn.datasets import make_blobs from sklearn.cluster import KMeans import matplotlib.pyplot as plt # 生成样本数据 X, y = make_blobs(n_samples=300, centers=4, cluster_std=0.60, random_state=0) # 创建K-Means模型 kmeans = KMeans(n_clusters=4, random_state=0) kmeans.fit(X) # 获取聚类标签 labels = kmeans.labels_ # 可视化聚类结果 plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis') plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s=300, c='red') plt.show() ```