本文共 5207 字，大约阅读时间需要 17 分钟。

使用 sklearn 的 pipeline 搭建机器学习的流程

1. 导入工具包

import numpy as npimport pandas as pd%matplotlib inlineimport matplotlib.pyplot as pltfrom sklearn.model_selection import train_test_splitfrom sklearn.model_selection import StratifiedShuffleSplitfrom sklearn.impute import SimpleImputerfrom sklearn.preprocessing import LabelEncoderfrom sklearn.preprocessing import OneHotEncoderfrom sklearn.preprocessing import LabelBinarizerfrom sklearn.base import BaseEstimator, TransformerMixinfrom sklearn.pipeline import Pipelinefrom sklearn.preprocessing import StandardScalerfrom sklearn.pipeline import FeatureUnionfrom sklearn.model_selection import GridSearchCVfrom sklearn.model_selection import cross_val_score

2. 读取数据

data = pd.read_csv("../competition/Employee_Satisfaction/train.csv")test = pd.read_csv("../competition/Employee_Satisfaction/test.csv")data.columns

Index(['id', 'last_evaluation', 'number_project', 'average_monthly_hours',       'time_spend_company', 'Work_accident', 'package',       'promotion_last_5years', 'division', 'salary', 'satisfaction_level'],      dtype='object')

• 训练数据，标签分离

y = data['satisfaction_level']X = data.drop(['satisfaction_level'], axis=1)

3. 数字特征、文字特征分离

def num_cat_splitor(X):    s = (X.dtypes == 'object')    object_cols = list(s[s].index)    # object_cols # ['package', 'division', 'salary']    num_cols = list(set(X.columns) - set(object_cols))    # num_cols    # ['Work_accident', 'time_spend_company', 'promotion_last_5years', 'id',    #  'average_monthly_hours',  'last_evaluation',  'number_project']    return num_cols, object_colsnum_cols, object_cols = num_cat_splitor(X)# print(num_cols)# print(object_cols)# X[object_cols].values

• 特征数值筛选器

class DataFrameSelector(BaseEstimator, TransformerMixin):    def __init__(self, attribute_names):        self.attribute_names = attribute_names    def fit(self, X, y=None):        return self    def transform(self, X):        return X[self.attribute_names].values

4. 数据处理Pipeline

• 数字特征

num_pipeline = Pipeline([        ('selector', DataFrameSelector(num_cols)),        ('imputer', SimpleImputer(strategy="median")),        ('std_scaler', StandardScaler()),    ])

• 文字特征

cat_pipeline = Pipeline([        ('selector', DataFrameSelector(object_cols)),        ('cat_encoder', OneHotEncoder(sparse=False)),    ])

• 组合数字和文字特征

full_pipeline = FeatureUnion(transformer_list=[        ("num_pipeline", num_pipeline),        ("cat_pipeline", cat_pipeline),    ])X_prepared = full_pipeline.fit_transform(X)

5. 尝试不同的模型

from sklearn.ensemble import RandomForestRegressorforest_reg = RandomForestRegressor()forest_scores = cross_val_score(forest_reg,X_prepared,y,                               scoring='neg_mean_squared_error',cv=3)forest_rmse_scores = np.sqrt(-forest_scores)print(forest_rmse_scores)print(forest_rmse_scores.mean())print(forest_rmse_scores.std())

还可以尝试别的模型

6. 参数搜索

param_grid = [    {
   'n_estimators' : [3,10,30,50,80],'max_features':[2,4,6,8]},    {
   'bootstrap':[False], 'n_estimators' : [3,10],'max_features':[2,3,4]},]forest_reg = RandomForestRegressor()grid_search = GridSearchCV(forest_reg, param_grid, cv=5,                          scoring='neg_mean_squared_error')grid_search.fit(X_prepared,y)

• 最佳参数

grid_search.best_params_

• 最优模型

grid_search.best_estimator_

• 搜索结果

cv_result = grid_search.cv_results_for mean_score, params in zip(cv_result['mean_test_score'], cv_result['params']):    print(np.sqrt(-mean_score), params)

0.2129252723367584 {
   'max_features': 2, 'n_estimators': 3}0.19276874697889504 {
   'max_features': 2, 'n_estimators': 10}0.1865548358477794 {
   'max_features': 2, 'n_estimators': 30}.......

7. 特征重要性筛选

feature_importances = grid_search.best_estimator_.feature_importances_

• 选择前 k 个最重要的特征

k = 3def indices_of_top_k(arr, k):    return np.sort(np.argpartition(np.array(arr), -k)[-k:])class TopFeatureSelector(BaseEstimator, TransformerMixin):    def __init__(self, feature_importances, k):        self.feature_importances = feature_importances        self.k = k    def fit(self, X, y=None):        self.feature_indices_ = indices_of_top_k(self.feature_importances, self.k)        return self    def transform(self, X):        return X[:, self.feature_indices_]

8. 最终完整Pipeline

prepare_select_and_predict_pipeline = Pipeline([    ('preparation', full_pipeline),    ('feature_selection', TopFeatureSelector(feature_importances, k)),    ('forst_reg', RandomForestRegressor())])

• 参数搜索

param_grid = [{
       'preparation__num_pipeline__imputer__strategy': ['mean', 'median', 'most_frequent'],    'feature_selection__k': list(range(5, len(feature_importances) + 1)),    'forst_reg__n_estimators' : [200,250,300,310,330],    'forst_reg__max_features':[2,4,6,8]}]grid_search_prep = GridSearchCV(prepare_select_and_predict_pipeline, param_grid, cv=10,                                scoring='neg_mean_squared_error', verbose=2, n_jobs=-1)

• 训练

grid_search_prep.fit(X,y)grid_search_prep.best_params_final_model = grid_search_prep.best_estimator_

• 预测

y_pred_test = final_model.predict(test)result = pd.DataFrame()result['id'] = test['id']result['satisfaction_level'] = y_pred_testresult.to_csv('rf_ML_pipeline.csv',index=False)

以上只是粗略的大体框架，还有很多细节，大家多指教！

我的CSDN

长按或扫码关注我的公众号（Michael阿明），一起加油、一起学习进步！

转载地址：https://michael.blog.csdn.net/article/details/107675895 如侵犯您的版权，请留言回复原文章的地址，我们会给您删除此文章，给您带来不便请您谅解！