def run(kf, data, model, label='flag_y'):
"""
Train model, predict on test set and get model performance.
:param kf:
:param data:
:param model:
:param label:
:return:
"""
defaults, gini_trains, gini_tests, auc_trains, auc_tests, ks_trains, ks_tests, psis, models = [], [], [], [], [], \
[], [], [], []
# 交叉验证
kf_list = list(kf.split(data))
for i, index in enumerate(kf_list):
# 训练
X = data.drop(columns=label)
y = data[label]
train_index, test_index = index[0], index[1]
X_train, y_train = X.iloc[train_index], y.iloc[train_index]
X_test, y_test = X.iloc[test_index], y.iloc[test_index]
model.fit(X_train, y_train)
y_pred = model.predict_proba(X_train)[:, 1]
y_test_pred = model.predict_proba(X_test)[:, 1]
# 计算指标
ks_train, ks_test = calc_ks(y_pred, y_train), calc_ks(y_test_pred, y_test)
auc_train, auc_test = calc_auc(y_pred, y_train), calc_auc(y_test_pred, y_test)
gini_train, gini_test = calc_gini(y_pred, y_train), calc_gini(y_test_pred, y_test)
psi = calc_psi(y_pred, y_test_pred)
default = 1.8 * ks_test - 0.8 * abs(ks_train - ks_test)
defaults.append(default)
gini_trains.append(gini_train)
gini_tests.append(gini_test)
auc_trains.append(auc_train)
auc_tests.append(auc_test)
ks_trains.append(ks_train)
ks_tests.append(ks_test)
psis.append(psi)
models.append(model)
# 整合结果
metrics = {
'gini_train': float(np.mean(gini_trains)),
'gini_test': float(np.mean(gini_tests)),
'auc_train': float(np.mean(auc_trains)),
'auc_test': float(np.mean(auc_tests)),
'ks_train': float(np.mean(ks_trains)),
'ks_test': float(np.mean(ks_tests)),
'psi': float(np.mean(psis)),
'default': float(np.mean(defaults))
}
# 输出每套超参数最优模型
best_model_idx = np.argmax(defaults)
dump_pkl(models[best_model_idx])
# 生成训练集测试集
train = data.iloc[kf_list[best_model_idx][0]]
write_data(train, 'train.fea')
test = data.iloc[kf_list[best_model_idx][1]]
write_data(test, 'test.fea')
LOG.debug(metrics)
nni.report_final_result(metrics)
def run(X_train, X_test, y_train, y_test, model):
"""
Train model, predict on test set and get model performance.
:param X_train: train data
:param X_test:
:param y_train: train label
:param y_test: test label
:param model: specific model
:return: report final result to nni
"""
# 训练
model.fit(X_train, y_train)
y_pred = model.predict_proba(X_train)[:, 1]
y_test_pred = model.predict_proba(X_test)[:, 1]
# 计算指标
ks_train, ks_test = calc_ks(y_pred, y_train), calc_ks(y_test_pred, y_test)
auc_train, auc_test = calc_auc(y_pred, y_train), calc_auc(y_test_pred, y_test)
gini_train, gini_test = calc_gini(y_pred, y_train), calc_gini(y_test_pred, y_test)
psi = calc_psi(y_pred, y_test_pred)
# 整合结果
metrics = {
'gini_train': gini_train,
'gini_test': gini_test,
'auc_train': auc_train,
'auc_test': auc_test,
'ks_train': ks_train,
'ks_test': ks_test,
'psi': psi,
'default': 1.8 * ks_test - 0.8 * abs(ks_train - ks_test)
}
dump_pkl(model)
LOG.debug(metrics)
nni.report_final_result(metrics)
