纠正代码：trainsets = pd.read_csv('/Users/zhangxinyu/Desktop/trainsets82.csv') testsets = pd.read_csv('/Users/zhangxinyu/Desktop/testsets82.csv') y_train_forced_turnover_nolimited = trainsets['m3_forced_turnover_nolimited'] X_train = trainsets.drop(['m3_P_perf_ind_all_1','m3_P_perf_ind_all_2','m3_P_perf_ind_all_3','m3_P_perf_ind_allind_1',\ 'm3_P_perf_ind_allind_2','m3_P_perf_ind_allind_3','m3_P_perf_ind_year_1','m3_P_perf_ind_year_2',\ 'm3_P_perf_ind_year_3','m3_forced_turnover_nolimited','m3_forced_turnover_3mon',\ 'm3_forced_turnover_6mon','m3_forced_turnover_1year','m3_forced_turnover_3year',\ 'm3_forced_turnover_5year','m3_forced_turnover_10year',\ 'CEOid','CEO_turnover_N','year','Firmid','appo_year'],axis=1) y_test_forced_turnover_nolimited = testsets['m3_forced_turnover_nolimited'] X_test = testsets.drop(['m3_P_perf_ind_all_1','m3_P_perf_ind_all_2','m3_P_perf_ind_all_3','m3_P_perf_ind_allind_1',\ 'm3_P_perf_ind_allind_2','m3_P_perf_ind_allind_3','m3_P_perf_ind_year_1','m3_P_perf_ind_year_2',\ 'm3_P_perf_ind_year_3','m3_forced_turnover_nolimited','m3_forced_turnover_3mon',\ 'm3_forced_turnover_6mon','m3_forced_turnover_1year','m3_forced_turnover_3year',\ 'm3_forced_turnover_5year','m3_forced_turnover_10year',\ 'CEOid','CEO_turnover_N','year','Firmid','appo_year'],axis=1) # 定义模型参数 input_dim = X.shape[1] epochs = 100 batch_size = 32 lr = 0.001 dropout_rate = 0.5 # 定义模型结构 def create_model(): model = Sequential() model.add(Dense(64, input_dim=input_dim, activation='relu')) model.add(Dropout(dropout_rate)) model.add(Dense(32, activation='relu')) model.add(Dropout(dropout_rate)) model.add(Dense(1, activation='sigmoid')) optimizer = Adam(lr=lr) model.compile(loss='binary_crossentropy', optimizer=optimizer, metrics=['accuracy']) return model # 5折交叉验证 kf = KFold(n_splits=5, shuffle=True, random_state=42) cv_scores = [] for train_index, test_index in kf.split(X): # 划分训练集和验证集 X_train, X_val = X[train_index], X[test_index] y_train, y_val = y[train_index], y[test_index] # 创建模型 model = create_model() # 定义早停策略 early_stopping = EarlyStopping(monitor='val_loss', patience=10, verbose=1) # 训练模型 model.fit(X_train, y_train, validation_data=(X_val, y_val), epochs=epochs, batch_size=batch_size, callbacks=[early_stopping], verbose=1) # 预测验证集 y_pred = model.predict(X_val) # 计算AUC指标 auc = roc_auc_score(y_val, y_pred) cv_scores.append(auc) # 输出交叉验证结果 print('CV AUC:', np.mean(cv_scores)) # 在全量数据上重新训练模型 model = create_model() model.fit(X, y, epochs=epochs, batch_size=batch_size, verbose=1)
扫一扫
1311
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
