情感分析实例：IMDB影评情感分析-基于keras的python学习笔记（十二）

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/weixin_44474718/article/details/86651958
分析某部电影是好电影还是不好的电影。数据集由IMDB（http://www.imdb.com/interfaces/）提供。

一、导入数据

数据通过keras的imdb.load_data()函数导入，为了便于在训练中使用数据集，keras提供的数据集将单词转化成整数，这个整数代表单词在整个数据集中的流行程度。
导入数据后，将训练数据和评估数据集合并，并查看相关统计信息，如中值和标准差，结构通过箱线图和直方图展示，代码如下：

from keras.datasets import imdb
import numpy as np
from matplotlib import pyplot as plt

(x_train, y_train), (x_validation, y_validation) = imdb.load_data()

# 合并训练集和评估数据集
x = np.concatenate((x_train, x_validation), axis=0)
y = np.concatenate((y_train, y_validation), axis=0)

print('x shape is %s, y shape is %s' % (x.shape, y.shape))
print('Classes: %s' % np.unique(y))

print('Total words: %s' % len(np.unique(np.hstack(x))))

result = [len(word) for word in x]
print('Mean: %.2f words (STD: %.2f)' %(np.mean(result), np.std(result)))

# 图表展示
plt.subplot(121)
plt.boxplot(result)
plt.subplot(122)
plt.hist(result)
plt.show()

执行代码，可以看到数据的离散状态和分布状态，结果如下：

x shape is (50000,), y shape is (50000,)
Classes: [0 1]
Total words: 88585
Mean: 234.76 words (STD: 172.91)

二、词嵌入

==词嵌入：是一种将词向量化的概念。==原理是：单词在高维空间中被编码为实值向量，其中词语之间的相似性意味着空间中的接近度。离散词被映射到连续数的向量。

from keras.datasets import imdb
from keras.preprocessing import sequence
from keras.layers.embeddings import Embedding

(x_train, y_train), (x_validation, y_validation) = imdb.load_data(num_words=5000)

x_train = sequence.pad_sequences(x_train, maxlen=500)
x_validation = sequence.pad_sequences(x_validation, maxlen=500)

Embedding(5000, 32, input_length=500)

三、多层感知器模型

下面从开发一个仅有单个隐藏层的多层感知器模型研究情感分析的问题。

from keras.datasets import imdb
import numpy as np
from keras.preprocessing import sequence
from keras.layers.embeddings import Embedding
from keras.layers import Dense, Flatten
from keras.models import Sequential

seed = 7
top_words = 5000
max_words = 500
out_dimension = 32
batch_size = 128
epochs = 2

def create_model():
    model = Sequential()
    # 构建嵌入层
    model.add(Embedding(top_words, out_dimension, input_length=max_words))
    model.add(Flatten())
    model.add(Dense(250, activation='relu'))
    model.add(Dense(1, activation='sigmoid'))
    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
    model.summary()
    return model

if __name__ == '__main__':
    np.random.seed(seed=seed)
    # 导入数据
    (x_train, y_train), (x_validation, y_validation) = imdb.load_data(num_words=top_words)
    # 限定数据集的长度
    x_train = sequence.pad_sequences(x_train, maxlen=max_words)
    x_validation = sequence.pad_sequences(x_validation, maxlen=max_words)

    # 生成模型
    model = create_model()
    model.fit(x_train, y_train, validation_data=(x_validation, y_validation),
              batch_size=batch_size, epochs=epochs, verbose=2)

四、卷积神经网络

卷积神经网络被设计为符合图像数据的空间结构，对场景中学习对象的位置和方向是鲁棒的。这种相同的原则可以用于处理序列问题（例如电影审查中的一维单词序列）。卷积神经网络的“特征位置的技术不变性”，同样可以帮助学习单词段落的结构。接下来在词嵌入层之后，增加一层一维卷积层和池化层，代码如下：

from keras.datasets import imdb
import numpy as np
from keras.preprocessing import sequence
from keras.layers.embeddings import Embedding
from keras.layers.convolutional import Conv1D, MaxPooling1D
from keras.layers import Dense, Flatten
from keras.models import Sequential

seed = 7
top_words = 5000
max_words = 500
out_dimension = 32
batch_size = 128
epochs = 2

def create_model():
    model = Sequential()
    # 构建嵌入层
    model.add(Embedding(top_words, out_dimension, input_length=max_words))
    # 1维度卷积层
    model.add(Conv1D(filters=32, kernel_size=3, padding='same', activation='relu'))
    model.add(MaxPooling1D(pool_size=2))
    model.add(Flatten())
    model.add(Dense(250, activation='relu'))
    model.add(Dense(1, activation='sigmoid'))
    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
    model.summary()
    return model

if __name__ == '__main__':
    np.random.seed(seed=seed)
    # 导入数据
    (x_train, y_train), (x_validation, y_validation) = imdb.load_data(num_words=top_words)
    # 限定数据集的长度
    x_train = sequence.pad_sequences(x_train, maxlen=max_words)
    x_validation = sequence.pad_sequences(x_validation, maxlen=max_words)

    # 生成模型
    model = create_model()
    model.fit(x_train, y_train, validation_data=(x_validation, y_validation),
              batch_size=batch_size, epochs=epochs, verbose=2)