机器学习步骤分享（2023.3.19）.zip

# 昵 称:XieXu # 时 间: 2023/3/18/0018 10:06 # 导入乳腺癌数据集 from sklearn.datasets import load_breast_cancer data = load_breast_cancer() # 记得需要自己主动加()，否则下边无法正常调用！ # 特征值和标签的赋值 X = data.data y = data.target # print("X.shape:", X.shape) # X.shape: (569, 30) # print("y.shape:", y.shape) # y.shape: (569,) # print(X) X = X[:, :10] # print("\n", "*" * 66, "\n") # print(X) # 方法的实现 # 使用逻辑回归算法 from sklearn.linear_model import LogisticRegression model = LogisticRegression() # 这种都要记得后面的小括号()需要自己主动添加 model.fit(X, y) y_pred = model.predict(X) # print("y_pred:", y_pred) # 评估方法 from sklearn.metrics import accuracy_score print("accuracy_score(y,y_pred):", accuracy_score(y, y_pred)) # accuracy_score(y,y_pred): 0.9121265377855887 ''' from sklearn.datasets import load_breast_cancer from sklearn.model_selection import train_test_split data = load_breast_cancer() cancers = load_breast_cancer() X = cancers.data # 获取特征值 Y = cancers.target # 获取标签 print(X.shape) # 查看特征形状 (569, 30) print(Y.shape) # 查看标签形状 (569,) print(X) print(Y) print(data.DESCR) # 查看数据集描述 Breast cancer wisconsin (diagnostic) dataset print('特征名称') print(data.feature_names) # 特征名 print('分类名称') print(data.target_names) # 标签类别名 # 注意返回值： 训练集train，x_train，y_train，测试集test，x_test，y_test # x_train为训练集的特征值，y_train为训练集的目标值，x_test为测试集的特征值，y_test为测试集的目标值 # 注意，接收参数的顺序固定 # 训练集占80%，测试集占20% x_train, x_test, y_train, y_test = train_test_split(X, Y, test_size=0.2) print('训练集的特征值和目标值：', x_train, y_train) print('测试集的特征值和目标值：', x_test, y_test) # dict_keys(['data', 'target', 'target_names', 'DESCR', 'feature_names', 'filename']) print(cancers.keys()) '''