def model_all_own(clf, X_train, y_train, X_test, y_test):
print('*******************************************')
print(clf.__class__.__name__, '开始fit...')
start_time = time()
clf.fit(X_train, y_train.values.ravel())
y_pred = clf.predict(X_test)
y_perd_prob = clf.predict_proba(X_test)
end_time = time()
result = {}
roc_pr = {}
recall_, accuracy_, precision_, f1_, f5_, auc_, g_mean_, fpr_, tpr_ = \
DataTools.compute_score(y_test, y_pred, y_perd_prob)
result['recall'] = recall_
result['acc'] = accuracy_
result['precision'] = precision_
result['f1'] = f1_
result['f5'] = f5_
result['auc'] = auc_
result['gmean'] = g_mean_
result['time'] = end_time - start_time
roc_pr['fpr'] = fpr_
roc_pr['tpr'] = tpr_
print("{} 训练结束，耗时： {:.4f} ".format(clf.__class__.__name__,
(end_time - start_time)))
return result, roc_pr
def LR_EE_smote(data):
# 子集数目
num_subsets = 10
X, y = DataPreprocessing.read_X_y(data)
print('原始数据：')
DataTools.print_data_ratio(y)
X_train, X_test, y_train, y_test = DataTools.data_split(X, y)
print('分割后的测试集：')
DataTools.print_data_ratio(y_test)
print('分割后的训练集：')
DataTools.print_data_ratio(y_train)
result = {}
result_recall = []
result_acc = []
result_precision = []
result_f1 = []
result_auc = []
result_gmean = []
result_fpr_temps = []
result_tpr_temps = []
start_time = time.clock()
for i in (range(num_subsets)):
print(
'******************************************************************************'
)
print('第 ', i + 1, ' 个分类器开始：')
# EE&smote后的数据
X_ee_smote, y_ee_smote = SmoteEE.smoteEE_own(X_train, y_train)
DataTools.print_data_ratio(y_ee_smote)
# 训练参数
# print('训练集子集%d：' % (i + 1))
# ClassifierLR.lr_grid_search_cv(X_ee_smote, y_ee_smote)
pd.concat([X_ee_smote, y_ee_smote],
axis=1).to_csv('data/subsets/lr_subset%d.csv' % (i + 1))
print('第%d个 子集导出成功！' % (i + 1))
print('训练集子集%d：' % (i + 1))
DataTools.print_data_ratio(y_ee_smote)
y_predict = ClassifierLR.fit_model_LR(X_ee_smote, y_ee_smote,
X_test, 0.1)
y_predict_prob = ClassifierLR.lr_predict_proba(
X_ee_smote, y_ee_smote, X_test, 0.1)
recall_, accuracy_, precision_, f1_, auc_, g_mean_, fpr_, tpr_ = \
DataTools.compute_score(y_test, y_predict, y_predict_prob)
result_recall.append(recall_)
result_acc.append(accuracy_)
result_precision.append(precision_)
result_f1.append(f1_)
result_auc.append(auc_)
result_gmean.append(g_mean_)
result_fpr_temps.append(fpr_)
result_tpr_temps.append(tpr_)
end_time = time.clock()
result['time'] = end_time - start_time
result['recall'] = np.mean(result_recall)
result['acc'] = np.mean(result_acc)
result['precision'] = np.mean(result_precision)
result['f1'] = np.mean(result_f1)
result['auc'] = np.mean(result_auc)
result['gmean'] = np.mean(result_gmean)
result['fpr'] = pd.DataFrame(result_fpr_temps).mean()
result['tpr'] = pd.DataFrame(result_tpr_temps).mean()
pd.DataFrame(result).to_csv('data/score/lr_ee_tuned.csv')
print('结果已保存至score文件夹下 ^_^')
def XGB_EE(data):
# 子集数目
num_subsets = 5
X, y = DataPreprocessing.read_X_y(data)
X_train_tmp, X_test, y_train_tmp, y_test = DataTools.data_split(X, y)
X_train, X_validate, y_train, y_validate = DataTools.data_split(
X_train_tmp, y_train_tmp)
result = {}
result_recall = []
result_acc = []
result_precision = []
result_f1 = []
result_f5 = []
result_auc = []
result_gmean = []
result_fpr_temps = []
result_tpr_temps = []
start_time = time.clock()
for i in (range(num_subsets)):
print(
'******************************************************************************'
)
print('第 ', i + 1, ' 个分类器开始：')
# EE&smote后的数据
X_ee, y_ee = EE.ee_own(X_train, y_train)
pd.concat([X_ee, y_ee],
axis=1).to_csv('data/subsets/subset_ee%d.csv' % (i + 1))
print('第%d个 子集导出成功！' % (i + 1))
print('训练集子集%d：' % (i + 1))
DataTools.print_data_ratio(y_ee)
# 训练参数
# ModelXGB.xgb_cv_param(X_ee, y_ee)
# ModelXGB.xgb_gridSearchCV(X_ee, y_ee)
# return
y_predict = ModelXGB.xgb_predict(X_ee, y_ee, X_test)
y_predict_prob = ModelXGB.xgb_predict_prob(X_ee, y_ee, X_test)
recall_, accuracy_, precision_, f1_, f5_, auc_, g_mean_, fpr_, tpr_ = \
DataTools.compute_score(y_test, y_predict, y_predict_prob)
result_recall.append(recall_)
result_acc.append(accuracy_)
result_precision.append(precision_)
result_f1.append(f1_)
result_f5.append(f5_)
result_auc.append(auc_)
result_gmean.append(g_mean_)
result_fpr_temps.append(fpr_)
result_tpr_temps.append(tpr_)
end_time = time.clock()
result['time'] = end_time - start_time
result['recall'] = np.mean(result_recall)
result['acc'] = np.mean(result_acc)
result['precision'] = np.mean(result_precision)
result['f1'] = np.mean(result_f1)
result['f5'] = np.mean(result_f5)
result['auc'] = np.mean(result_auc)
result['gmean'] = np.mean(result_gmean)
result['fpr'] = pd.DataFrame(result_fpr_temps).mean()
result['tpr'] = pd.DataFrame(result_tpr_temps).mean()
pd.DataFrame(result).to_csv('data/score2/xgb_ee3.csv')
print('结果已保存至score文件夹下 ^_^')
# # 计算混淆矩阵
cnf_matrix = DataTools.compute_confusion_matrix(y_test, y_predict)
# # 绘制混淆矩阵图
PlotTools.plot_confusion_matrix(cnf_matrix, title='Confusion matrix')
PlotTools.plot_roc_curve(y_test, y_predict_prob[:, 1])