full_connected_layer_units=[[hidden1,0.5],[hidden2,0.5]],
embedding_dropout_rate=0.,
nb_epoch=30,
earlyStoping_patience=config['earlyStoping_patience'],
lr = config['lr'],
batch_size = batch_size,
embedding_weight_trainable = True,
embedding_init_weight=init_weight,
)
print (w2v_embedding_cnn.embedding_layer_output.get_weights()[0][1])
w2v_embedding_cnn.print_model_descibe()
print('+'*80)
# 训练模型
train_loss, train_accuracy, val_loss, val_accuracy = w2v_embedding_cnn.fit((train_X_feature, train_y),
(test_X_feature, test_y))
print (w2v_embedding_cnn.embedding_layer_output.get_weights()[0][1])
print('dev:%f,%f' % (train_loss, train_accuracy))
print('val:%f,%f' % (val_loss, val_accuracy))
quit()
# train
# w2v_embedding_cnn.accuracy((train_X_feature, train_y))
end_time = timeit.default_timer()
print('end! Running time:%ds!' % (end_time - start_time))
logging.debug('=' * 20)
logging.debug('end! Running time:%ds!' % (end_time - start_time))
logging.debug('=' * 20)
input_dim=feature_encoder.vocabulary_size + 1,
word_embedding_dim=config['word_embedding_dim'],
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((train_X_feature, train_y),
(test_X_feature, test_y))
# 保存模型
rand_embedding_cnn.save_model(model_file_path)
else:
# 从保存的pickle中加载模型
rand_embedding_cnn.model_from_pickle(model_file_path)
# -------------- code start : 结束 -------------
if verbose > 2:
logging.debug('-' * 20)
print '-' * 20
# -------------- region end : 3. 初始化CNN模型并训练 ---------------
# -------------- region start : 4. 预测 -------------
if verbose > 1:
logging.debug('-' * 20)
class RFAndWordEmbeddingCnnMerge(object):
# 如果使用全体数据作为字典，则使用这个变量来存放权重，避免重复加载权重，因为每次加载的权重都是一样的。
train_data_weight = None
# 验证数据是一份权重，不包含测试集了
val_data_weight = None
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 fit(self, train_data=None, validation_data=None):
train_X, train_y = train_data
validation_X, validation_y = validation_data
self.static_w2v_cnn.fit(train_data, validation_data)
train_x_features = self.static_w2v_cnn.get_layer_output(train_X)[4]
validation_x_features = self.static_w2v_cnn.get_layer_output(
validation_X)[4]
return self.bow_randomforest.fit((train_x_features, train_y),
(validation_x_features, validation_y))
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'],
feature_encoder=feature_encoder.vocabulary_size+1,
optimizers='sgd',
lr= 1e-1,
batch_size = 128,
)
w2v_embedding_cnn.print_model_descibe()
if config['refresh_all_model'] or not os.path.exists(model_file_path):
# 训练模型
w2v_embedding_cnn.fit((train_w2v_features, train_y),
(test_w2v_features, test_y))
# 保存模型
w2v_embedding_cnn.save_model(model_file_path)
else:
# 从保存的pickle中加载模型
w2v_embedding_cnn.model_from_pickle(model_file_path)
# -------------- code start : 结束 -------------
if verbose > 2:
logging.debug('-' * 20)
print '-' * 20
# -------------- region end : 3. 初始化CNN模型并训练 ---------------
print index_to_label[w2v_embedding_cnn.predict(feature_encoder.transform_sentence('你好吗'))]
nb_epoch=int(config["cnn_nb_epoch"]),
earlyStoping_patience=config["earlyStoping_patience"],
lr=config["lr"],
batch_size=config["batch_size"],
embedding_weight_trainable=True,
)
rand_embedding_cnn.print_model_descibe()
if config["refresh_all_model"] or not os.path.exists(model_file_path):
print ("+" * 80)
# 训练模型
print (rand_embedding_cnn.embedding_layer_output.get_weights()[0][1])
train_loss, train_accuracy, val_loss, val_accuracy = rand_embedding_cnn.fit(
(train_X_feature, train_y), (test_all_X_feature, test_all_y)
)
print (rand_embedding_cnn.embedding_layer_output.get_weights()[0][1])
# y_pred, is_correct, accu, f1 = rand_embedding_cnn.accuracy((test_all_X_feature, test_all_y))
#
# print 'F1(macro)为：%f' % (np.average(f1))
#
# # train
# rand_embedding_cnn.accuracy((train_X_feature, train_y))
print ("dev:%f,%f" % (train_loss, train_accuracy))
print ("val:%f,%f" % (val_loss, val_accuracy))
quit()
# 五折
print ("五折")
counter = 0
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)
else:
# 从保存的pickle中加载模型
rand_embedding_cnn.model_from_pickle(model_file_path)
# -------------- code start : 结束 -------------
if verbose > 2:
logging.debug('-' * 20)
print '-' * 20
# -------------- region end : 3. 初始化CNN模型并训练 ---------------
# -------------- region start : 4. 预测 -------------
if verbose > 1:
logging.debug('-' * 20)
input_dim=feature_encoder.vocabulary_size + 1,
word_embedding_dim=config['word_embedding_dim'],
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((train_X_feature, train_y),
(test_X_feature, test_y))
# 保存模型
rand_embedding_cnn.save_model(model_file_path)
else:
# 从保存的pickle中加载模型
rand_embedding_cnn.model_from_pickle(model_file_path)
# -------------- code start : 结束 -------------
if verbose > 2:
logging.debug('-' * 20)
print '-' * 20
# -------------- region end : 3. 初始化CNN模型并训练 ---------------
# -------------- region start : 4. 预测 -------------
if verbose > 1:
logging.debug('-' * 20)
class RFAndWordEmbeddingCnnMerge(CnnBaseClass):
__version__ = '1.4'
# 如果使用全体数据作为字典，则使用这个变量来存放权重，避免重复加载权重，因为每次加载的权重都是一样的。
train_data_weight = None
# 验证数据是一份权重，不包含测试集了
val_data_weight = None
def __init__(self, feature_encoder, num_filter, num_labels, n_estimators,
word2vec_model_file_path, **kwargs):
self.static_w2v_cnn = None
self.bow_randomforest = None
self.feature_encoder = feature_encoder
if not kwargs.get('init_model', True):
# 不初始化模型，一般在恢复模型时候用
return
if kwargs.get('rand_weight', False):
# CNN(rand)模式
weight = None
elif kwargs['dataset_flag'] == 0:
# 训练集
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 fit(self, train_data=None, validation_data=None):
train_X, train_y = train_data
validation_X, validation_y = validation_data
self.static_w2v_cnn.fit(train_data, validation_data)
train_x_features = self.static_w2v_cnn.get_layer_output(train_X)[4]
validation_x_features = self.static_w2v_cnn.get_layer_output(
validation_X)[4]
return self.bow_randomforest.fit((train_x_features, train_y),
(validation_x_features, validation_y))
def save_model(self, path):
"""
保存模型,保存成pickle形式
:param path: 模型保存的路径
:type path: 模型保存的路径
:return:
"""
model_file = open(path, 'wb')
pickle.dump(self.feature_encoder, model_file)
pickle.dump(self.static_w2v_cnn, model_file)
pickle.dump(self.bow_randomforest, model_file)
def model_from_pickle(self, path):
'''
从模型文件中直接加载模型
:param path:
:return: RandEmbeddingCNN object
'''
model_file = file(path, 'rb')
self.feature_encoder = pickle.load(model_file)
self.static_w2v_cnn = pickle.load(model_file)
self.bow_randomforest = pickle.load(model_file)
@staticmethod
def get_feature_encoder(**kwargs):
"""
获取该分类器的特征编码器
:param kwargs: 可设置参数 [ input_length(*), full_mode(#,False), feature_type(#,word),verbose(#,0)],加*表示必须提供，加#表示可选，不写则默认。
:return:
"""
assert kwargs.has_key('input_length'), '请提供 input_length 的属性值'
from data_processing_util.feature_encoder.onehot_feature_encoder import FeatureEncoder
feature_encoder = FeatureEncoder(
need_segmented=kwargs.get('need_segmented', True),
sentence_padding_length=kwargs['input_length'],
verbose=kwargs.get('verbose', 0),
full_mode=kwargs.get('full_mode', False),
remove_stopword=True,
replace_number=True,
lowercase=True,
zhs2zht=True,
remove_url=True,
padding_mode='center',
add_unkown_word=True,
feature_type=kwargs.get('feature_type', 'word'),
vocabulary_including_test_set=kwargs.get(
'vocabulary_including_test_set', True),
update_dictionary=kwargs.get('update_dictionary', True))
return feature_encoder
def batch_predict_bestn(self, sentences, transform_input=False, bestn=1):
"""
批量预测句子的类别,对输入的句子进行预测
:param sentences: 测试句子,
:type sentences: array-like
:param transform_input: 是否转换句子，如果为True,输入原始字符串句子即可，内部已实现转换成字典索引的形式。
:type transform_input: bool
:param bestn: 预测，并取出bestn个结果。
:type bestn: int
:return: y_pred_result, y_pred_score
"""
if transform_input:
sentences = self.static_w2v_cnn.transform(sentences)
# sentences = np.asarray(sentences)
# assert len(sentences.shape) == 2, 'shape必须是2维的！'
train_x_features = self.static_w2v_cnn.get_layer_output(sentences)[4]
# print(train_x_features)
# print(train_x_features.shape)
return self.bow_randomforest.batch_predict_bestn(train_x_features,
transform_input=False,
bestn=bestn)
class RFAndWordEmbeddingCnnMerge(CnnBaseClass):
__version__ = '1.4'
# 如果使用全体数据作为字典，则使用这个变量来存放权重，避免重复加载权重，因为每次加载的权重都是一样的。
train_data_weight = None
# 验证数据是一份权重，不包含测试集了
val_data_weight = None
def __init__(self,
feature_encoder,
num_filter,
num_labels,
n_estimators,
word2vec_model_file_path,
**kwargs
):
self.static_w2v_cnn = None
self.bow_randomforest = None
self.feature_encoder = feature_encoder
if not kwargs.get('init_model', True):
# 不初始化模型，一般在恢复模型时候用
return
if kwargs.get('rand_weight', False):
# CNN(rand)模式
weight = None
elif kwargs['dataset_flag'] == 0:
# 训练集
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 fit(self, train_data=None, validation_data=None):
train_X, train_y = train_data
validation_X, validation_y = validation_data
self.static_w2v_cnn.fit(train_data, validation_data)
train_x_features = self.static_w2v_cnn.get_layer_output(train_X)[4]
validation_x_features = self.static_w2v_cnn.get_layer_output(validation_X)[4]
return self.bow_randomforest.fit((train_x_features, train_y), (validation_x_features, validation_y))
def save_model(self, path):
"""
保存模型,保存成pickle形式
:param path: 模型保存的路径
:type path: 模型保存的路径
:return:
"""
model_file = open(path, 'wb')
pickle.dump(self.feature_encoder, model_file)
pickle.dump(self.static_w2v_cnn, model_file)
pickle.dump(self.bow_randomforest, model_file)
def model_from_pickle(self, path):
'''
从模型文件中直接加载模型
:param path:
:return: RandEmbeddingCNN object
'''
model_file = file(path, 'rb')
self.feature_encoder = pickle.load(model_file)
self.static_w2v_cnn = pickle.load(model_file)
self.bow_randomforest = pickle.load(model_file)
@staticmethod
def get_feature_encoder(**kwargs):
"""
获取该分类器的特征编码器
:param kwargs: 可设置参数 [ input_length(*), full_mode(#,False), feature_type(#,word),verbose(#,0)],加*表示必须提供，加#表示可选，不写则默认。
:return:
"""
assert kwargs.has_key('input_length'), '请提供 input_length 的属性值'
from data_processing_util.feature_encoder.onehot_feature_encoder import FeatureEncoder
feature_encoder = FeatureEncoder(
need_segmented=kwargs.get('need_segmented', True),
sentence_padding_length=kwargs['input_length'],
verbose=kwargs.get('verbose', 0),
full_mode=kwargs.get('full_mode', False),
remove_stopword=True,
replace_number=True,
lowercase=True,
zhs2zht=True,
remove_url=True,
padding_mode='center',
add_unkown_word=True,
feature_type=kwargs.get('feature_type', 'word'),
vocabulary_including_test_set=kwargs.get('vocabulary_including_test_set', True),
update_dictionary=kwargs.get('update_dictionary', True)
)
return feature_encoder
def batch_predict_bestn(self, sentences, transform_input=False, bestn=1):
"""
批量预测句子的类别,对输入的句子进行预测
:param sentences: 测试句子,
:type sentences: array-like
:param transform_input: 是否转换句子，如果为True,输入原始字符串句子即可，内部已实现转换成字典索引的形式。
:type transform_input: bool
:param bestn: 预测，并取出bestn个结果。
:type bestn: int
:return: y_pred_result, y_pred_score
"""
if transform_input:
sentences = self.static_w2v_cnn.transform(sentences)
# sentences = np.asarray(sentences)
# assert len(sentences.shape) == 2, 'shape必须是2维的！'
train_x_features = self.static_w2v_cnn.get_layer_output(sentences)[4]
# print(train_x_features)
# print(train_x_features.shape)
return self.bow_randomforest.batch_predict_bestn(train_x_features, transform_input=False, bestn=bestn)
full_connected_layer_units=config['full_connected_layer_units'],
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'],
lr = config['lr'],
batch_size = config['batch_size'],
)
rand_embedding_cnn.print_model_descibe()
if config['refresh_all_model'] or not os.path.exists(model_file_path):
print('+'*80)
# 训练模型
rand_embedding_cnn.fit((train_X_feature, train_y),
(test_all_X_feature, test_all_y))
y_pred, is_correct, accu, f1 = rand_embedding_cnn.accuracy((test_all_X_feature, test_all_y))
print 'F1(macro)为：%f' % (np.average(f1))
# train
rand_embedding_cnn.accuracy((train_X_feature, train_y))
# 五折
print('五折')
counter = 0
for dev_X,dev_y,val_X,val_y in data_util.get_k_fold_data(k=5, data=(train_X_feature, train_y)):
counter += 1
# quit()
