机器学习——使用pipeline简化预处理，构建模型过程

深碍√TFBOYSˉ_ 2024-04-18 08:49 44阅读 0赞

一：使用pipeline进行数据预处理，模型构建

from sklearn.pipeline import Pipeline
    from sklearn.svm import SVC
    from sklearn.datasets import load_breast_cancer
    from sklearn.model_selection import train_test_split
    from sklearn.preprocessing import MinMaxScaler
    
    # load and split the data
    cancer = load_breast_cancer()
    X_train, X_test, y_train, y_test = train_test_split(cancer.data, cancer.target, random_state=0)
    
    pipe = Pipeline([("scaler", MinMaxScaler()), ("svm", SVC())])#有两个步骤
    
    pipe.fit(X_train, y_train) #自动对数据进行scaler，再用scale之后的数据输入SVC构建模型
    print("Test score: {:.2f}".format(pipe.score(X_test, y_test)))

![在这里插入图片描述][20190904105637167.png]  
二：将pipeline应用到GridSearchCV

#接着上面的代码
    param_grid = {'svm__C': [0.001, 0.01, 0.1, 1, 10, 100],
    'svm__gamma': [0.001, 0.01, 0.1, 1, 10, 100]}
    #注意这里参数svm__C：前半部分svm指定pipeline里的第几个步骤，中间两个下划线，最后是参数名称
    
    grid = GridSearchCV(pipe, param_grid=param_grid, cv=5)
    grid.fit(X_train, y_train)
    print("Best cross-validation accuracy: {:.2f}".format(grid.best_score_))
    print("Test set score: {:.2f}".format(grid.score(X_test, y_test)))
    print("Best parameters: {}".format(grid.best_params_))

![在这里插入图片描述][20190904110343482.png]  
三：make\_pipeline简化构建过程

from sklearn.pipeline import make_pipeline
    # standard syntax
    pipe_long = Pipeline([("scaler", MinMaxScaler()), ("svm", SVC(C=100))])#原来的方式
    # abbreviated syntax
    pipe_short = make_pipeline(MinMaxScaler(), SVC(C=100)) #简化版
    
    print("Pipeline steps:\n{}".format(pipe_short.steps))#steps参数获取pipeline里的各项参数

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3p6bGRt_size_16_color_FFFFFF_t_70]  
四：获取pipeline里的参数

from sklearn.preprocessing import StandardScaler
    from sklearn.decomposition import PCA
    pipe = make_pipeline(StandardScaler(), PCA(n_components=2), StandardScaler())
    
    # fit the pipeline defined before to the cancer dataset
    pipe.fit(cancer.data)
    # extract the first two principal components from the "pca" step
    components = pipe.named_steps["pca"].components_ #获取PCA里的参数
    print("components.shape: {}".format(components.shape))

![在这里插入图片描述][20190904210657413.png]  
五：获取Grid-Searched Pipeline里的参数

from sklearn.linear_model import LogisticRegression
    pipe = make_pipeline(StandardScaler(), LogisticRegression())
    
    param_grid = {'logisticregression__C': [0.01, 0.1, 1, 10, 100]}
    
    X_train, X_test, y_train, y_test = train_test_split(
    cancer.data, cancer.target, random_state=4)
    grid = GridSearchCV(pipe, param_grid, cv=5)
    grid.fit(X_train, y_train)
    
    print("Best estimator:\n{}".format(grid.best_estimator_))

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3p6bGRt_size_16_color_FFFFFF_t_70 1]

print("Logistic regression step:\n{}".format(
    grid.best_estimator_.named_steps["logisticregression"]))

![在这里插入图片描述][20190904210906890.png]  
六：pipeline结合Grid-Searching去选择最佳模型

from sklearn.ensemble import RandomForestClassifier
    
    pipe = Pipeline([('preprocessing', StandardScaler()), ('classifier', SVC())])
    
    param_grid = [
    {'classifier': [SVC()], 'preprocessing': [StandardScaler(), None],
    'classifier__gamma': [0.001, 0.01, 0.1, 1, 10, 100],
    'classifier__C': [0.001, 0.01, 0.1, 1, 10, 100]},
    {'classifier': [RandomForestClassifier(n_estimators=100)],
    'preprocessing': [None], 'classifier__max_features': [1, 2, 3]}]
    
    X_train, X_test, y_train, y_test = train_test_split(cancer.data, cancer.target, random_state=0)
    grid = GridSearchCV(pipe, param_grid, cv=5)
    grid.fit(X_train, y_train)
    print("Best params:\n{}\n".format(grid.best_params_))
    print("Best cross-validation score: {:.2f}".format(grid.best_score_))
    print("Test-set score: {:.2f}".format(grid.score(X_test, y_test)))

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3p6bGRt_size_16_color_FFFFFF_t_70 2]  
七：pipeline结合cross validation

xgbr = xgb.XGBRegressor(max_depth=7, n_estimators=300, learning_rate=0.07, n_jobs=60, reg_lambda=0.7, booster='dart')
    select = RFE(RandomForestClassifier(n_estimators=50, random_state=42, n_jobs=60), n_features_to_select=375)
    
    pipe = Pipeline([('select', select), ('xgbr', xgbr)])
    score = cross_val_score(pipe, X=train_x, y=train_y, scoring='r2', cv=3, n_jobs=40)
    print(score.mean(), score.std())
    print(score)

[20190904105637167.png]: https://image.dandelioncloud.cn/pgy_files/images/2024/04/17/6d9eb62f158d49be9926cd27d5dbcf60.png
[20190904110343482.png]: https://image.dandelioncloud.cn/pgy_files/images/2024/04/17/26c7cce00925401daa4394900dd807d7.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3p6bGRt_size_16_color_FFFFFF_t_70]: https://image.dandelioncloud.cn/pgy_files/images/2024/04/17/bed93ba552624e3f87d191fe0a5a05ec.png
[20190904210657413.png]: https://image.dandelioncloud.cn/pgy_files/images/2024/04/17/49fe395124dc4293a6b6bc5e3f406fcb.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3p6bGRt_size_16_color_FFFFFF_t_70 1]: https://image.dandelioncloud.cn/pgy_files/images/2024/04/17/2224e6b48aae45ed9190607c66ad3a1c.png
[20190904210906890.png]: https://image.dandelioncloud.cn/pgy_files/images/2024/04/17/d3be7dc3b90c4a78b91d0ef54481953f.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3p6bGRt_size_16_color_FFFFFF_t_70 2]: https://image.dandelioncloud.cn/pgy_files/images/2024/04/17/3dbbb341976f43ed80a3b761af353754.png