英文识别双11活动

import tensorflow as tf
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences

# 假设我们有一组英文文本数据和对应的标签（0表示非双11活动，1表示双11活动）
texts = ["This is a sample text about Double 11 event.", "Another unrelated text."]
labels = [1, 0]

# 文本预处理
tokenizer = Tokenizer()
tokenizer.fit_on_texts(texts)
sequences = tokenizer.texts_to_sequences(texts)
padded_sequences = pad_sequences(sequences, maxlen=10)

# 构建简单的神经网络模型
model = tf.keras.Sequential([
    tf.keras.layers.Embedding(input_dim=len(tokenizer.word_index) + 1, output_dim=16, input_length=10),
    tf.keras.layers.GlobalAveragePooling1D(),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
model.fit(padded_sequences, labels, epochs=10)

# 使用模型进行预测
new_texts = ["Exciting Double 11 sales are coming!", "A normal day."]
new_sequences = tokenizer.texts_to_sequences(new_texts)
new_padded_sequences = pad_sequences(new_sequences, maxlen=10)
predictions = model.predict(new_padded_sequences)
print(predictions)  # 输出预测的概率值