数据挖掘（六）：模型融合

数据挖掘（六）：模型融合

# 导入包 import numpy as np import pandas as pd import matplotlib.pyplot as plt from sklearn.model_selection import train_test_split from sklearn.model_selection import KFold from vecstack import stacking from sklearn.model_selection import GridSearchCV,ParameterGrid from sklearn.svm import SVC from sklearn.linear_model import LogisticRegression from sklearn.tree import DecisionTreeClassifier from sklearn.ensemble import RandomForestClassifier from xgboost import XGBClassifier from sklearn.ensemble import GradientBoostingClassifier from sklearn import metrics import warnings plt.rcParams['font.sans-serif']=['SimHei'] plt.rcParams['axes.unicode_minus']=False warnings.filterwarnings('ignore') # 导入数据 org_data = pd.read_csv("org_data.csv", encoding = 'gbk') print(org_data.shape)

变量处理及单模型的构建见本系列前一篇，此处略处

# 模型融合 model_list = [Lr_cv, svc_cv, dt_cv, rf_cv, xgb_cv] S_train, S_test = stacking(model_list, x_train, y_train, x_test, regression=False, n_folds=5) # # Initialize 2-nd level model model = GradientBoostingClassifier(learning_rate = 0.1, n_estimators = 100, max_depth = 3) # # Fit 2-nd level model model_s = model.fit(S_train, y_train) # # Predict y_pred = model_s.predict(S_test) # Final prediction score # print('Final prediction score: [%.8f]' % metrics.accuracy_score(y_test, y_pred)) acc_score_test = metrics.accuracy_score(y_pred, y_test) precision_score_test = metrics.precision_score(y_pred, y_test) recall_score_test = metrics.recall_score(y_pred, y_test) f1_score_test = metrics.f1_score(y_pred, y_test) roc_auc_score_test = metrics.roc_auc_score(y_pred, y_test) print('Final 测试集准确率：{}\n'.format(acc_score_test)) print('Final 测试集精确率：{}\n'.format(precision_score_test)) print('Final 测试集召回率：{}\n'.format(recall_score_test)) print('Final 测试集f1评分：{}\n'.format(f1_score_test)) print('Final 测试集AUC值：{}\n'.format(roc_auc_score_test)) # model_est(model_dict_s, x_train, x_test, y_train, y_test) Final 测试集准确率：0.7701471618780659 Final 测试集精确率：0.24512534818941503 Final 测试集召回率：0.6068965517241379 Final 测试集f1评分：0.3492063492063492 Final 测试集AUC值：0.6977540480929582 # from mlxtend.classifier import StackingClassifier sclf = StackingClassifier(classifiers=[Lr_cv, dt_cv, rf_cv, xgb_cv, svc_cv], meta_classifier=xgb_cv) model_dict_mlxtend = {'融合模型':sclf} model_est(model_dict_mlxtend, x_train, x_test, y_train, y_test) 融合模型 训练集准确率：0.8935978358881875 融合模型 测试集准确率：0.7764540995094604 融合模型 训练集精确率：0.6390887290167866 融合模型 测试集精确率：0.3342618384401114 融合模型 训练集召回率：0.909556313993174 融合模型 测试集召回率：0.6 融合模型 训练集f1评分：0.7507042253521128 融合模型 测试集f1评分：0.42933810375670844 融合模型 训练集AUC值：0.8998711887368278 融合模型 测试集AUC值：0.7026079869600651