IMDB数据集下载和探索——影评文本分类 | TensorFlow

参考TensorFlow官方教程

import tensorflow as tf
from tensorflow import keras
import numpy as np
print(tf.__version__)

imdb = keras.datasets.imdb

(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)
print("Training entries: {}, labels: {}".format(len(train_data), len(train_labels)))
#将整数转换回字词
# A dictionary mapping words to an integer index
word_index = imdb.get_word_index()

# The first indices are reserved
word_index = {k:(v+3) for k,v in word_index.items()}
word_index[""] = 0
word_index[""] = 1
word_index[""] = 2  # unknown
word_index[""] = 3
reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])
def decode_review(text):
    return ' '.join([reverse_word_index.get(i, '?') for i in text])
#准备数据
train_data = keras.preprocessing.sequence.pad_sequences(train_data,
                                                        value=word_index[""],
                                                        padding='post',
                                                        maxlen=256)

test_data = keras.preprocessing.sequence.pad_sequences(test_data,
                                                       value=word_index[""],
                                                       padding='post',
                                                       maxlen=256)
#构建模型
# input shape is the vocabulary count used for the movie reviews (10,000 words)
vocab_size = 10000
model = keras.Sequential()
model.add(keras.layers.Embedding(vocab_size, 16))
model.add(keras.layers.GlobalAveragePooling1D())
model.add(keras.layers.Dense(16, activation=tf.nn.relu))
model.add(keras.layers.Dense(1, activation=tf.nn.sigmoid))
model.summary()
#配置模型以使用优化器和损失函数：
model.compile(optimizer=tf.train.AdamOptimizer(),
              loss='binary_crossentropy',
              metrics=['accuracy'])
#创建验证集
x_val = train_data[:10000]
partial_x_train = train_data[10000:]

y_val = train_labels[:10000]
partial_y_train = train_labels[10000:]        
#训练模型
history = model.fit(partial_x_train,
                    partial_y_train,
                    epochs=40,
                    batch_size=512,
                    validation_data=(x_val, y_val),
                    verbose=1) 
#评估模型
results = model.evaluate(test_data, test_labels)
print(results)  
              

结果如下：
使用这种相当简单的方法可实现约 87% 的准确率。如果采用更高级的方法，模型的准确率应该会接近 95%。

小白手敲强行学习过程。。。。