data_util = DataUtil() train_data, test_data = data_util.load_train_test_data(config) label_to_index, index_to_label = data_util.get_label_index() train_x = train_data['SENTENCE'].as_matrix() train_y = train_data['LABEL_INDEX'].as_matrix() test_x = test_data['SENTENCE'].as_matrix() test_y = test_data['LABEL_INDEX'].as_matrix() from deep_learning.cnn.wordEmbedding_cnn.example.one_conv_layer_wordEmbedding_cnn import WordEmbeddingCNNWithOneConv input_length = 14 word_embedding_dim = 50 WordEmbeddingCNNWithOneConv.cross_validation( train_data=(train_x, train_y), test_data=(test_x, test_y), need_validation=True, include_train_data=True, vocabulary_including_test_set=False, cv=3, feature_type = 'word', num_labels=24, input_length=input_length, # num_filter_list=[8], num_filter_list=[10,30,50, 80, 100, 110, 150, 200, 300,500,1000], verbose=0, embedding_weight_trainable=False, word2vec_model_file_path = data_util.transform_word2vec_model_name('%dd_weibo_100w' % word_embedding_dim) )
config = { 'verbose': 1, } from version_2.data_processing.data_util import DataUtil data_util = DataUtil() train_data, test_data = data_util.load_train_test_data(config) label_to_index, index_to_label = data_util.get_label_index() train_x = train_data['TEXT'].as_matrix() train_y = train_data['STANCE_INDEX'].as_matrix() test_x = test_data['TEXT'].as_matrix() test_y = test_data['STANCE_INDEX'].as_matrix() from deep_learning.cnn.wordEmbedding_cnn.example.one_conv_layer_wordEmbedding_cnn import WordEmbeddingCNNWithOneConv input_length = 120 word_embedding_dim = 50 WordEmbeddingCNNWithOneConv.cross_validation( train_data=(train_x, train_y), test_data=(test_x, test_y), feature_type='word', input_length=input_length, num_filter_list=[10], # num_filter_list=[10,30,50, 80, 100, 110, 150, 200, 300,500,1000], verbose=1, # word2vec_model_file_path = data_util.transform_word2vec_model_name('%dd_weibo_100w' % word_embedding_dim), word2vec_model_file_path= '/home/jdwang/PycharmProjects/corprocessor/word2vec/vector/50dim/vector1000000_50dim.gem' )
from deep_learning.cnn.wordEmbedding_cnn.example.one_conv_layer_wordEmbedding_cnn import WordEmbeddingCNNWithOneConv input_length = 14 word_embedding_dim = 50 WordEmbeddingCNNWithOneConv.cross_validation( train_data=(train_X, train_y), test_data=(test_X, test_y), need_validation=True, include_train_data=True, vocabulary_including_test_set=True, cv=3, feature_type=feature_type, num_labels=24, input_length=input_length, # batch_size = 50, # num_filter_list=[8], num_filter_list=num_filter_list, verbose=config['verbose'], embedding_weight_trainable=False, # 获取中间层输出 get_cnn_middle_layer_output=True, # 保存到以下地址 middle_layer_output_file = 'result/conv_middle_output_%dfilters.pkl'%num_filter_list[0], word2vec_model_file_path=data_util.transform_word2vec_model_name('%dd_weibo_100w' % word_embedding_dim) ) if config['verbose'] > 0: print('-' * 20) # endregion -------------- cross validation ---------------
print('-' * 20) print('cross validation') input_length = 14 word_embedding_dim = 50 WordEmbeddingCNNWithOneConv.cross_validation( train_data=(train_X, train_y), test_data=(test_X, test_y), need_validation=True, include_train_data=True, vocabulary_including_test_set=True, cv=3, feature_type=feature_type, num_labels=24, input_length=input_length, # batch_size = 50, # num_filter_list=[8], num_filter_list=num_filter_list, verbose=config['verbose'], embedding_weight_trainable=False, # 获取中间层输出 get_cnn_middle_layer_output=True, # 保存到以下地址 middle_layer_output_file='result/conv_middle_output_%dfilters.pkl' % num_filter_list[0], word2vec_model_file_path=data_util.transform_word2vec_model_name( '%dd_weibo_100w' % word_embedding_dim)) if config['verbose'] > 0: print('-' * 20) # endregion -------------- cross validation ---------------
'verbose':1, } from version_2.data_processing.data_util import DataUtil data_util = DataUtil() train_data, test_data = data_util.load_train_test_data(config) label_to_index, index_to_label = data_util.get_label_index() train_x = train_data['TEXT'].as_matrix() train_y = train_data['STANCE_INDEX'].as_matrix() test_x = test_data['TEXT'].as_matrix() test_y = test_data['STANCE_INDEX'].as_matrix() from deep_learning.cnn.wordEmbedding_cnn.example.one_conv_layer_wordEmbedding_cnn import WordEmbeddingCNNWithOneConv input_length = 120 word_embedding_dim = 50 WordEmbeddingCNNWithOneConv.cross_validation( train_data=(train_x, train_y), test_data=(test_x, test_y), feature_type = 'word', input_length=input_length, num_filter_list=[10], # num_filter_list=[10,30,50, 80, 100, 110, 150, 200, 300,500,1000], verbose=1, # word2vec_model_file_path = data_util.transform_word2vec_model_name('%dd_weibo_100w' % word_embedding_dim), word2vec_model_file_path = '/home/jdwang/PycharmProjects/corprocessor/word2vec/vector/50dim/vector1000000_50dim.gem' )