基于CNN的IMDB电影数据集文本分类

记录一下自己的实验
实验：使用IMDB电影数据集做文本二分类实验，基于深度学习的卷积神经网络模型
平台：pychram,tensorflow2.0
代码块：

"""
# -*- coding: utf-8 -*-

@author: SYM 
@software: PyCharm
@time: 2022/5/10 0030 15:34
"""
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import Flatten
from tensorflow.python.keras.layers.embeddings import Embedding
from tensorflow.keras.preprocessing import sequence
import matplotlib.pyplot as plt
from tensorflow.keras import models
from tensorflow.keras import layers
from tensorflow.keras.layers import Dropout, Activation
from tensorflow.keras.layers import Conv1D, GlobalMaxPooling1D,MaxPooling1D
from tensorflow.python.keras.layers.recurrent import SimpleRNN

import keras
import numpy as np
old = np.load
np.load = lambda *a,**k: old(*a,**k,allow_pickle=True)
from keras.datasets import imdb
#(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)

max_features = 10000
maxlen = 500
batch_size = 32
(input_train, y_train), (input_test, y_test) = imdb.load_data( num_words = max_features)

print('pad sequences (smaples x time)')
input_train = sequence.pad_sequences(input_train, maxlen = maxlen)
input_test = sequence.pad_sequences(input_test, maxlen = maxlen)
print('input_train shape: ', input_train.shape)
print('input_test shape: ', input_test.shape)

num_word=10000
hidden_dims=250
model = models.Sequential() # Keras序列模型
model.add(Embedding(num_word, 32)) # 嵌入层，将正整数转换为固定尺寸的稠密向量
model.add(Dropout(0.2))
model.add(Conv1D(filters = 250, kernel_size = 3, padding = 'valid', activation = 'relu',strides=1))# 卷积层
model.add(GlobalMaxPooling1D()) # 时序数据全局最大池化
model.add(Dense(hidden_dims))
model.add(Dropout(0.2))
model.add(Activation('relu'))
model.add(Dense(1))
model.add(Activation('sigmoid'))


model.compile(optimizer = 'rmsprop', loss = 'binary_crossentropy', metrics = ['acc'])
#history = model.fit(input_train, y_train, epochs = 10, batch_size = 128, validation_split = 0.2)

history = model.fit(input_train, y_train, epochs = 4, batch_size = 512, validation_split = 0.2)


history_dict = history.history
print(history_dict.keys())


import matplotlib.pyplot as plt
acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']

epochs = range(1, len(acc) + 1)
plt.plot(epochs, acc, 'bo', label = 'Training acc')
plt.plot(epochs, val_acc, 'b', label = 'Validation acc')
plt.title('Training and validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend()

plt.figure()

plt.plot(epochs, loss, 'bo', label = 'Training loss')
plt.plot(epochs, val_loss, 'b', label = 'Validation loss')
plt.title("Training and validation loss")
plt.xlabel('Epochs')
plt.ylabel('loss')
plt.legend()

plt.show()

result = model.evaluate(input_test,y_test)
print(result)

predictResult = model.predict(input_test)
print(predictResult)