#!/usr/bin/env python
# Copyright (c) 2016 Baidu, Inc. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from paddle.trainer_config_helpers import *

######################## data source ################################
dict_path = 'gserver/tests/Sequence/tour_dict_phrase.dict'
dict_file = dict()
for line_count, line in enumerate(open(dict_path, "r")):
    dict_file[line.strip()] = line_count

define_py_data_sources2(train_list='gserver/tests/Sequence/train.list',
                        test_list=None,
                        module='sequenceGen',
                        obj='process',
                        args={"dict_file":dict_file})

settings(batch_size=5)
######################## network configure ################################
dict_dim = len(open(dict_path,'r').readlines())
word_dim = 128
hidden_dim = 256
label_dim = 3

data = data_layer(name="word", size=dict_dim)

emb = embedding_layer(input=data, size=word_dim)

# (lstm_input + lstm) is equal to lstmemory 
with mixed_layer(size=hidden_dim*4) as lstm_input:
    lstm_input += full_matrix_projection(input=emb)

lstm = lstmemory_group(input=lstm_input,
                       size=hidden_dim,
                       act=TanhActivation(),
                       gate_act=SigmoidActivation(),
                       state_act=TanhActivation(),
                       lstm_layer_attr=ExtraLayerAttribute(error_clipping_threshold=50))

lstm_last = last_seq(input=lstm)

with mixed_layer(size=label_dim, 
                 act=SoftmaxActivation(), 
                 bias_attr=True) as output:
    output += full_matrix_projection(input=lstm_last)

outputs(classification_cost(input=output, label=data_layer(name="label", size=1)))