train_model_input = {name: train_X[name].values for name in get_feature_names(feature_columns)}
print("########################################")
# histroy输入必须是二维数组
from tqdm import tqdm
for fea in ['hist_merchant_id', 'hist_action_type']:
list = []
for i in tqdm(train_model_input[fea]):
list.append(i)
train_model_input[fea] = np.array(list)
history = model.fit(train_model_input, train_y.values, verbose=True, epochs=10, validation_split=0.2, batch_size=512)
# 转换test__model_input
test_data['action_type'] = 3
test_model_input = {name: test_data[name].values for name in feature_names}
from tqdm import tqdm
for fea in ['hist_merchant_id', 'hist_action_type']:
list = []
for i in tqdm(test_model_input[fea]):
list.append(i)
test_model_input[fea] = np.array(list)
# 得到预测结果
prob = model.predict(test_model_input)
submission['prob'] = prob
submission.drop(['origin'], axis=1, inplace=True)
submission.to_csv('prediction.csv', index=False)
att_activation='dice',
att_weight_normalization=False,
hist_len_max=sess_len_max,
dnn_hidden_units=(200, 80),
att_hidden_size=(
64,
16,
),
l2_reg_embedding=REG,
seed=2019)
model.compile('adagrad',
'binary_crossentropy',
metrics=[
'binary_crossentropy',
])
hist_ = model.fit(
train_input[:],
train_label,
batch_size=BATCH_SIZE,
epochs=1,
initial_epoch=0,
verbose=1,
)
pred_ans = model.predict(test_input, TEST_BATCH_SIZE)
print()
print("test LogLoss", round(log_loss(test_label, pred_ans), 4), "test AUC",
round(roc_auc_score(test_label, pred_ans), 4))
