word2vec_file_path = (config['word2vec_file_path'])%config['word_embedding_dim']
print model_file_path
print result_file_path
print train_cnn_feature_file_path
print test_cnn_feature_file_path
print word2vec_file_path
rand_embedding_cnn = WordEmbeddingCNN(
rand_seed=seed,
verbose=verbose,
input_dim=feature_encoder.vocabulary_size + 1,
word_embedding_dim=config['word_embedding_dim'],
embedding_init_weight=feature_encoder.to_embedding_weight(word2vec_file_path),
input_length=config['sentence_padding_length'],
num_labels=len(label_to_index),
conv_filter_type=config['conv_filter_type'],
k=config['kmax_k'],
embedding_dropout_rate=config['embedding_dropout_rate'],
output_dropout_rate=config['output_dropout_rate'],
nb_epoch=int(config['cnn_nb_epoch']),
earlyStoping_patience=config['earlyStoping_patience'],
)
rand_embedding_cnn.print_model_descibe()
if config['refresh_all_model'] or not os.path.exists(model_file_path):
# 训练模型
rand_embedding_cnn.fit((feature_encoder.train_padding_index, train_y),
(map(feature_encoder.transform_sentence, test_X), test_y))
# 保存模型
rand_embedding_cnn.save_model(model_file_path)
def __init__(self, feature_encoder, num_filter, num_labels, n_estimators,
word2vec_model_file_path, **kwargs):
if kwargs.get('rand_weight', False):
# CNN(rand)模式
weight = None
elif kwargs['dataset_flag'] == 0:
if RFAndWordEmbeddingCnnMerge.train_data_weight is None:
# 训练集
RFAndWordEmbeddingCnnMerge.train_data_weight = feature_encoder.to_embedding_weight(
word2vec_model_file_path)
weight = RFAndWordEmbeddingCnnMerge.train_data_weight
else:
# kwargs['dataset_flag']>0
if RFAndWordEmbeddingCnnMerge.val_data_weight is None:
RFAndWordEmbeddingCnnMerge.val_data_weight = feature_encoder.to_embedding_weight(
word2vec_model_file_path)
weight = RFAndWordEmbeddingCnnMerge.val_data_weight
# print(weight)
self.static_w2v_cnn = WordEmbeddingCNN(
rand_seed=1377,
verbose=kwargs.get('verbose', 0),
feature_encoder=feature_encoder,
# optimizers='adadelta',
optimizers='sgd',
# 当使用CNN (rand) 模式的时候使用到了
word_embedding_dim=50,
# 设置embedding使用训练好的w2v模型初始化
embedding_init_weight=weight,
# 默认设置为训练时embedding层权重不变
embedding_weight_trainable=kwargs.get('embedding_weight_trainable',
False),
num_labels=num_labels,
l1_conv_filter_type=[
[num_filter, 3, -1, 'valid', (-1, 1), 0.5, 'relu', 'none'],
[num_filter, 4, -1, 'valid', (-1, 1), 0., 'relu', 'none'],
[num_filter, 5, -1, 'valid', (-1, 1), 0., 'relu', 'none'],
],
l2_conv_filter_type=[],
full_connected_layer_units=[],
embedding_dropout_rate=0.,
nb_epoch=kwargs.get('nb_epoch', 25),
batch_size=kwargs.get('batch_size', 32),
earlyStoping_patience=30,
lr=kwargs.get('lr', 1e-2),
show_validate_accuracy=True
if kwargs.get('verbose', 0) > 0 else False,
# output_regularizer=('l2', 0.5),
output_constraints=('maxnorm', 3),
# 必须设为True，才能取中间结果做特征
save_middle_output=True,
)
self.bow_randomforest = BowRandomForest(
rand_seed=1377,
verbose=kwargs.get('verbose', 0),
feature_encoder=feature_encoder,
# optimizers='adadelta',
n_estimators=n_estimators,
min_samples_leaf=1,
)
def get_model(feature_encoder, num_filter, num_labels,
word2vec_model_file_path, **kwargs):
# print(WordEmbeddingCNNWithOneConv.weight)
"""获取 CNN(w2v)模型
Parameters
----------
feature_encoder : FeatureEncoder
特征编码器
num_filter : int
num_labels : int
word2vec_model_file_path : str
kwargs : dict
- dataset_flag
- rand_weight : (default,False)设置为 True 时，为 CNN(rand) 模型
- verbose
- embedding_weight_trainable
Returns
-------
"""
if kwargs.get('rand_weight', False):
# CNN(rand)模式
weight = None
elif kwargs['dataset_flag'] == 0:
if WordEmbeddingCNNWithOneConv.train_data_weight is None:
# 训练集
WordEmbeddingCNNWithOneConv.train_data_weight = feature_encoder.to_embedding_weight(
word2vec_model_file_path)
weight = WordEmbeddingCNNWithOneConv.train_data_weight
else:
# kwargs['dataset_flag']>0
if WordEmbeddingCNNWithOneConv.val_data_weight is None:
WordEmbeddingCNNWithOneConv.val_data_weight = feature_encoder.to_embedding_weight(
word2vec_model_file_path)
weight = WordEmbeddingCNNWithOneConv.val_data_weight
# print(weight)
static_w2v_cnn = WordEmbeddingCNN(
rand_seed=1377,
verbose=kwargs.get('verbose', 0),
feature_encoder=feature_encoder,
# optimizers='adadelta',
optimizers='sgd',
# 当使用CNN (rand) 模式的时候使用到了
word_embedding_dim=300,
# 设置embedding使用训练好的w2v模型初始化
embedding_init_weight=weight,
# 默认设置为训练时embedding层权重不变
embedding_weight_trainable=kwargs.get('embedding_weight_trainable',
False),
num_labels=num_labels,
l1_conv_filter_type=[
[num_filter, 3, -1, 'valid', (-1, 1), 0.5, 'relu', 'none'],
[num_filter, 4, -1, 'valid', (-1, 1), 0., 'relu', 'none'],
[num_filter, 5, -1, 'valid', (-1, 1), 0., 'relu', 'none'],
],
l2_conv_filter_type=[],
full_connected_layer_units=[],
embedding_dropout_rate=0.,
nb_epoch=kwargs.get('nb_epoch', 25),
batch_size=kwargs.get('batch_size', 32),
earlyStoping_patience=30,
lr=kwargs.get('lr', 1e-2),
show_validate_accuracy=True
if kwargs.get('verbose', 0) > 0 else False,
# output_regularizer=('l2', 0.5),
output_constraints=('maxnorm', 3),
save_middle_output=kwargs.get('get_cnn_middle_layer_output',
False),
)
# static_w2v_cnn.print_model_descibe()
# quit()
return static_w2v_cnn
