Keras深度学习实战——使用GloVe模型构建单词向量

好的，以下是使用Keras构建情感分析模型的代码示例： 首先，需要导入需要的库： ```python import pandas as pd import numpy as np from keras.preprocessing.text import Tokenizer from keras.preprocessing.sequence import pad_sequences from keras.models import Sequential from keras.layers import Embedding, Conv1D, GlobalMaxPooling1D, Dense ``` 接着，读取数据集并进行预处理： ```python # 读取数据集 data = pd.read_csv('sentiment_analysis.csv') # 将文本转换为小写 texts = data['text'].apply(lambda x: x.lower()) # 将标签转换为数字：0表示负面情感，1表示正面情感 labels = np.array([0 if label == 'negative' else 1 for label in data['label']]) ``` 然后，进行单词向量化： ```python # 将文本转换为单词序列 tokenizer = Tokenizer(num_words=5000) tokenizer.fit_on_texts(texts) sequences = tokenizer.texts_to_sequences(texts) # 对单词序列进行填充，使其长度相同 padded_sequences = pad_sequences(sequences, maxlen=100) ``` 接下来，构建模型： ```python model = Sequential() # 添加嵌入层 model.add(Embedding(input_dim=5000, output_dim=100, input_length=100)) # 添加1D卷积层 model.add(Conv1D(filters=32, kernel_size=3, padding='same', activation='relu')) # 添加全局最大池化层 model.add(GlobalMaxPooling1D()) # 添加全连接层 model.add(Dense(units=64, activation='relu')) # 添加输出层 model.add(Dense(units=1, activation='sigmoid')) # 编译模型 model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy']) ``` 最后，训练模型并进行评估： ```python # 划分训练集和测试集 indices = np.arange(padded_sequences.shape[0]) np.random.shuffle(indices) padded_sequences = padded_sequences[indices] labels = labels[indices] train_size = int(0.8 * padded_sequences.shape[0]) train_X, test_X = padded_sequences[:train_size], padded_sequences[train_size:] train_y, test_y = labels[:train_size], labels[train_size:] # 训练模型 model.fit(train_X, train_y, epochs=10, batch_size=64) # 评估模型 loss, accuracy = model.evaluate(test_X, test_y) print('Test accuracy:', accuracy) ``` 完整的代码示例如下： ```python import pandas as pd import numpy as np from keras.preprocessing.text import Tokenizer from keras.preprocessing.sequence import pad_sequences from keras.models import Sequential from keras.layers import Embedding, Conv1D, GlobalMaxPooling1D, Dense # 读取数据集 data = pd.read_csv('sentiment_analysis.csv') # 将文本转换为小写 texts = data['text'].apply(lambda x: x.lower()) # 将标签转换为数字：0表示负面情感，1表示正面情感 labels = np.array([0 if label == 'negative' else 1 for label in data['label']]) # 将文本转换为单词序列 tokenizer = Tokenizer(num_words=5000) tokenizer.fit_on_texts(texts) sequences = tokenizer.texts_to_sequences(texts) # 对单词序列进行填充，使其长度相同 padded_sequences = pad_sequences(sequences, maxlen=100) # 构建模型 model = Sequential() # 添加嵌入层 model.add(Embedding(input_dim=5000, output_dim=100, input_length=100)) # 添加1D卷积层 model.add(Conv1D(filters=32, kernel_size=3, padding='same', activation='relu')) # 添加全局最大池化层 model.add(GlobalMaxPooling1D()) # 添加全连接层 model.add(Dense(units=64, activation='relu')) # 添加输出层 model.add(Dense(units=1, activation='sigmoid')) # 编译模型 model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy']) # 划分训练集和测试集 indices = np.arange(padded_sequences.shape[0]) np.random.shuffle(indices) padded_sequences = padded_sequences[indices] labels = labels[indices] train_size = int(0.8 * padded_sequences.shape[0]) train_X, test_X = padded_sequences[:train_size], padded_sequences[train_size:] train_y, test_y = labels[:train_size], labels[train_size:] # 训练模型 model.fit(train_X, train_y, epochs=10, batch_size=64) # 评估模型 loss, accuracy = model.evaluate(test_X, test_y) print('Test accuracy:', accuracy) ```