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))
y = np.random.RandomState(seed).permutation(y) # print(dev_y) dev_X_feature = feature_encoder.fit_transform(x) test_X_feature = feature_encoder.transform(test_data[u'SENTENCE'].as_matrix()) bow_rf = BowRandomForest( # rand_seed=rand_seed, verbose=0, n_estimators=estimators, min_samples_leaf=1, feature_encoder=None, ) bow_rf.fit(train_data=(dev_X_feature, y), validation_data=(test_X_feature, test_y)) _, _, dev_accuracy, _ = bow_rf.accuracy((dev_X_feature, y), False) _, _, val_accuracy, _ = bow_rf.accuracy((test_X_feature, test_y), False) train_accu.append(dev_accuracy) test_accu.append(val_accuracy) print('-' * 80) print('#***#训练准确率:%s'%(train_accu)) print('#***#测试准确率:%s'%(test_accu)) ave_acc.append(test_accu) counter += 1 print(np.asarray(ave_acc))
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)
for n_estimators in [10,100,200,300,400,500,800,1000,2000,5000]: bow_rf = BowRandomForest( rand_seed=seed, verbose=config['verbose'], n_estimators=n_estimators, min_samples_leaf=1, feature_encoder=feature_encoder, ) model_file_path = ''.join([str(item) for item in config['model_file_path']]) result_file_path = ''.join([str(item) for item in config['result_file_path']]) result_file_path = result_file_path%seed print model_file_path print result_file_path # quit() if config['refresh_all_model']: bow_rf.fit(train_data=(train_X_feature, train_data['LABEL_INDEX']), validation_data=(test_X_feature, test_data['LABEL_INDEX'])) bow_rf.save_model(model_file_path) else: bow_rf.model_from_pickle(model_file_path) bow_rf.print_model_descibe() print(index_to_label[bow_rf.predict('啥', transform_input=True)]) print(index_to_label[bow_rf.predict('哪台好', transform_input=True)]) bow_rf.accuracy((train_X_feature, train_data['LABEL_INDEX'].as_matrix()), False) y_pred, is_correct, accu, f1 = bow_rf.accuracy((test_X_feature,test_data['LABEL_INDEX'].as_matrix()),False) test_data['PREDICT'] = [index_to_label[item] for item in y_pred] test_data['IS_CORRECT'] = is_correct
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)