Python中文网 - 问答频道, 解决您学习工作中的Python难题和Bug
Python常见问题
我有一个带有情感标签的推特数据集。我已经对数据进行了预处理，并完成了词性标记（都是通过python中的NLTK）。预处理后，数据如下所示：
预处理后，使用以下代码准备训练数据：
full_text = list(train['content'].values) + list(test['content'].values)
tokenizer = Tokenizer(num_words=20000,lower = True, filters = '')
tokenizer.fit_on_texts(full_text)
train_tokenized = tokenizer.texts_to_sequences(train['content'])
test_tokenized = tokenizer.texts_to_sequences(test['content'])
max_len = 50
X_train = pad_sequences(train_tokenized, maxlen = max_len)
X_test = pad_sequences(test_tokenized, maxlen = max_len)
embed_size = 300
max_features = 20000
def get_coefs(word,*arr):
return word, np.asarray(arr, dtype='float32')
def get_embed_mat(embedding_path):
embedding_index = dict(get_coefs(*o.strip().split(" ")) for o in open(embedding_path,encoding="utf8"))
word_index = tokenizer.word_index
nb_words = min(max_features, len(word_index))
print(nb_words)
embedding_matrix = np.zeros((nb_words + 1, embed_size))
for word, i in word_index.items():
if i >= max_features:
continue
embedding_vector = embedding_index.get(word)
if embedding_vector is not None:
embedding_matrix[i] = embedding_vector
return embedding_matrix建立了一个以单词嵌入为层的深度学习模型。模型建造规范如下所示：
def build_model1(lr = 0.0, lr_d = 0.0, units = 0, dr = 0.0):
inp = Input(shape = (max_len,))
x = Embedding(20001, embed_size, weights = [embedding_matrix], trainable = False)(inp)
x1 = SpatialDropout1D(dr)(x)
x_lstm = Bidirectional(LSTM(units, return_sequences = True))(x1)
x1 = Conv1D(32, kernel_size=2, padding='valid', kernel_initializer='he_uniform')(x_lstm)
avg_pool1_lstm1 = GlobalAveragePooling1D()(x1)
max_pool1_lstm1 = GlobalMaxPooling1D()(x1)
x_lstm = Bidirectional(LSTM(units, return_sequences = True))(x1)
x1 = Conv1D(32, kernel_size=2, padding='valid', kernel_initializer='he_uniform')(x_lstm)
avg_pool1_lstm = GlobalAveragePooling1D()(x1)
max_pool1_lstm = GlobalMaxPooling1D()(x1)
x = concatenate([avg_pool1_lstm1, max_pool1_lstm1,
avg_pool1_lstm, max_pool1_lstm])
#x = BatchNormalization()(x)
x = Dropout(0.1)(Dense(128,activation='relu') (x))
x = BatchNormalization()(x)
x = Dropout(0.1)(Dense(64,activation='relu') (x))
x = Dense(8, activation = "sigmoid")(x)
model = Model(inputs = inp, outputs = x)
model.compile(loss = "binary_crossentropy", optimizer = Adam(lr = lr, decay = lr_d), metrics = ["accuracy"])
history = model.fit(X_train, y_one_hot, batch_size = 128, epochs = 20, validation_split=0.1,
verbose = 1, callbacks = [check_point, early_stop])
model = load_model(file_path)
return model我想用石灰来解释这个模型的预测（如下图所示）。但它不起作用。
Tags： testsizeindexmodellenreturntrainembedding
目前没有回答
相关问题 更多 >
编程相关推荐