sentence_padding_length=sentence_padding_length,
verbose=1,
need_segmented=True,
full_mode=full_mode,
remove_stopword=True,
replace_number=True,
lowercase=True,
zhs2zht=True,
remove_url=True,
padding_mode='center',
add_unkown_word=True,
feature_type=feature_type,
)
train_X_feature = feature_encoder.fit_transform(train_data=train_data['SENTENCE'].as_matrix())
feature_encoder.print_model_descibe()
feature_encoder.print_sentence_length_detail()
# train_y = train_data['LABEL_INDEX'].as_matrix()
test_all_X_feature = feature_encoder.transform(test_data['SENTENCE'].as_matrix())
test_all_y = test_data['LABEL_INDEX'].as_matrix()
print(train_X_feature.shape)
print(test_all_X_feature.shape)
logging.debug('=' * 20)
# ****************************************************************
# ------------- region end : 2. 转换数据的格式并特征编码 -------------
# ****************************************************************
feature_encoder = FeatureEncoder(
sentence_padding_length=config['sentence_padding_length'],
verbose=0,
need_segmented=config['need_segmented'],
full_mode=True,
replace_number=True,
remove_stopword=True,
lowercase=True,
padding_mode='center',
add_unkown_word=True,
mask_zero=True,
zhs2zht=True,
remove_url=True,
)
train_X_feature = feature_encoder.fit_transform(train_data=train_X)
test_X_feature = map(feature_encoder.transform_sentence, test_X)
feature_encoder.print_sentence_length_detail
print feature_encoder.vocabulary_size
# print ','.join(sorted(feature_encoder.vocabulary))
# quit()
feature_encoder.print_model_descibe()
# -------------- code start : 结束 -------------
if verbose > 2:
logging.debug('-' * 20)
print '-' * 20
# -------------- region end : 2. 转换数据格式，以可以进行分类 ---------------
for seed in config['rand_seed']:
def test_onehot_bow_cnn():
# 使用样例
train_X = ['你好', '无聊', '测试句子', '今天天气不错', '我要买手机']
trian_y = [1, 3, 2, 2, 3]
test_X = ['句子', '你好', '你妹']
test_y = [2, 3, 0]
sentence_padding_length = 8
from data_processing_util.feature_encoder.onehot_feature_encoder import FeatureEncoder
word_feature_encoder = FeatureEncoder(
sentence_padding_length=sentence_padding_length,
verbose=0,
need_segmented=True,
full_mode=True,
replace_number=True,
remove_stopword=True,
lowercase=True,
padding_mode='left',
add_unkown_word=True,
feature_type='word',
zhs2zht=True,
remove_url=True,
# 设置为True，输出 onehot array
to_onehot_array=True,
)
train_X_word_feature = word_feature_encoder.fit_transform(train_X)
test_X_word_feature = word_feature_encoder.transform(test_X)
print(','.join(word_feature_encoder.vocabulary))
print train_X_word_feature.shape
print train_X_word_feature
seg_feature_encoder = FeatureEncoder(
sentence_padding_length=sentence_padding_length,
verbose=0,
need_segmented=True,
full_mode=True,
replace_number=True,
remove_stopword=True,
lowercase=True,
padding_mode='left',
add_unkown_word=True,
feature_type='seg',
zhs2zht=True,
remove_url=True,
# 设置为True，输出 onehot array
to_onehot_array=True,
)
train_X_seg_feature = seg_feature_encoder.fit_transform(train_X)
test_X_seg_feature = seg_feature_encoder.transform(test_X)
print(','.join(seg_feature_encoder.vocabulary))
print train_X_seg_feature.shape
print train_X_seg_feature
# quit()
onehot_cnn = MultiChannelOnehotBowCNN(
rand_seed=1377,
verbose=1,
feature_encoder=(word_feature_encoder,seg_feature_encoder),
# optimizers='adadelta',
optimizers='sgd',
word_input_length=sentence_padding_length,
seg_input_length=sentence_padding_length,
word_input_dim=word_feature_encoder.vocabulary_size,
seg_input_dim=seg_feature_encoder.vocabulary_size,
num_labels=5,
l1_conv_filter_type=[
[1, 2, -1, 'valid', (0, 1), 0., 'relu', 'none'],
[1, 3, -1, 'valid', (0, 1), 0., 'relu', 'none'],
[1, -1, -1, 'bow', (0, 1), 0., 'relu', 'none'],
],
l2_conv_filter_type=[
# [16, 2, -1, 'valid',(2,1),0.5, 'relu', 'none']
],
full_connected_layer_units=[
(50, 0.5, 'relu', 'none'),
],
embedding_dropout_rate=0.,
nb_epoch=30,
nb_batch=5,
earlyStoping_patience=20,
lr=1e-2,
)
onehot_cnn.print_model_descibe()
# 训练模型
# 从保存的pickle中加载模型
# onehot_cnn.model_from_pickle('model/modelA.pkl')
print(onehot_cnn.fit(([train_X_word_feature,train_X_seg_feature], trian_y),
([test_X_word_feature,test_X_seg_feature], test_y)))
print(trian_y)
# loss, train_accuracy = onehot_cnn.model.evaluate(train_X_feature, trian_y)
# onehot_cnn.accuracy((train_X_word_feature, trian_y), transform_input=False)
print(onehot_cnn.batch_predict([test_X_word_feature,test_X_seg_feature], transform_input=False))
print(onehot_cnn.batch_predict_bestn([test_X_word_feature,test_X_seg_feature], transform_input=False, bestn=2))
quit()
print onehot_cnn.batch_predict(test_X, transform_input=True)
print onehot_cnn.predict(test_X[0], transform_input=True)
onehot_cnn.accuracy((test_X, test_y), transform_input=True)
# 保存模型
# onehot_cnn.save_model('model/modelA.pkl')
print onehot_cnn.predict('你好吗', transform_input=True)
test_y = [3, 1, 1]
sentence_padding_length = 10
feature_encoder = FeatureEncoder(
sentence_padding_length=sentence_padding_length,
verbose=0,
need_segmented=True,
full_mode=True,
remove_stopword=True,
replace_number=True,
lowercase=True,
zhs2zht=True,
remove_url=True,
padding_mode='center',
add_unkown_word=True,
mask_zero=True)
train_X_features = feature_encoder.fit_transform(train_data=train_X)
print(train_X_features)
dcnn = DynamicCNN(
rand_seed=1337,
verbose=2,
batch_size=1,
vocab_size=feature_encoder.vocabulary_size,
word_embedding_dim=48,
# input_length=None,
input_length=sentence_padding_length,
num_labels=4,
conv_filter_type=[
[100, 2, 'full'],
[100, 4, 'full'],
# [100,6,5,'valid'],
],
