import keras
from sklearn.model_selection import train_test_split
import tensorflow as tf
from keras.callbacks import ModelCheckpoint,Callback
# import keras.backend as K
from keras.layers import *
from keras.models import Model
from keras.optimizers import SGD, RMSprop, Adagrad,Adam
from keras.models import *
from keras.metrics import *
from keras import backend as K
from keras.regularizers import *
from keras.metrics import categorical_accuracy
# from keras.regularizers import activity_l1 #通過L1正則項(xiàng)，使得輸出更加稀疏
from keras_contrib.layers import CRF

from visual_callbacks import AccLossPlotter
plotter = AccLossPlotter(graphs=['acc', 'loss'], save_graph=True, save_graph_path=sys.path[0])

# from crf import CRFLayer,create_custom_objects

class LossHistory(Callback):
  def on_train_begin(self, logs={}):
    self.losses = []

  def on_batch_end(self, batch, logs={}):
    self.losses.append(logs.get('loss'))
# def on_epoch_end(self, epoch, logs=None):

word_input = Input(shape=(max_len,), dtype='int32', name='word_input')
word_emb = Embedding(len(char_value_dict)+2, output_dim=64, input_length=max_len, dropout=0.2, name='word_emb')(word_input)
bilstm = Bidirectional(LSTM(32, dropout_W=0.1, dropout_U=0.1, return_sequences=True))(word_emb)
bilstm_d = Dropout(0.1)(bilstm)
half_window_size = 2
paddinglayer = ZeroPadding1D(padding=half_window_size)(word_emb)
conv = Conv1D(nb_filter=50, filter_length=(2 * half_window_size + 1), border_mode='valid')(paddinglayer)
conv_d = Dropout(0.1)(conv)
dense_conv = TimeDistributed(Dense(50))(conv_d)
rnn_cnn_merge = merge([bilstm_d, dense_conv], mode='concat', concat_axis=2)
dense = TimeDistributed(Dense(class_label_count))(rnn_cnn_merge)
crf = CRF(class_label_count, sparse_target=False)
crf_output = crf(dense)
model = Model(input=[word_input], output=[crf_output])
model.compile(loss=crf.loss_function, optimizer='adam', metrics=[crf.accuracy])
model.summary()

# serialize model to JSON
model_json = model.to_json()
with open("model.json", "w") as json_file:
  json_file.write(model_json)

#編譯模型
# model.compile(loss='categorical_crossentropy', optimizer=adam, metrics=['acc',])

# 用于保存驗(yàn)證集誤差最小的參數(shù)，當(dāng)驗(yàn)證集誤差減少時(shí)，立馬保存下來
checkpointer = ModelCheckpoint(filepath="bilstm_1102_k205_tf130.w", verbose=0, save_best_only=True, save_weights_only=True) #save_weights_only=True
history = LossHistory()

history = model.fit(x_train, y_train,
          batch_size=32, epochs=500,#validation_data = ([x_test, seq_lens_test], y_test),
          callbacks=[checkpointer, history, plotter],
          verbose=1,
          validation_split=0.1,
          )