# -*- coding: utf-8 -*-
"""
@from:www.linerect.com
@author: duimu
@contact: duimu@qq.com
@Created on: 2019/11/28 11:44
"""
import tensorflow as tf
import tflearn
from tflearn.layers.core import input_data,dropout,fully_connected
from tflearn.layers.conv import conv_1d,global_max_pool
from tflearn.layers.merge_ops import merge
from tflearn.layers.estimator import regression
from tflearn.data_utils import to_categorical,pad_sequences
from tflearn.datasets import imdb
"""
字典有固定的长度，字典囊括了数据集中出现的词，词在字典中的位置按照词在数据集中出现的次数从大到小排列。
比如这个字典中，‘the’在评论中出现次数最大，the放在字典的第一个位置上；‘and’出现的次数第二多，所以排在第二 …
例如：
评论为“I like this movie！”
‘I’在字典中的index为9；
‘like’在字典中的index为37；
‘this’‘在字典中的index为10；
‘movie’在字典中的index为16；
‘！’在字典中的index为28；
这个评论对应的词向量为[9 37 10 16 28]
"""
train,test,_=imdb.load_data(path='.\imdb\imdb.pkl',n_words=10000,valid_portion=0.1)
trainX,trainY=train
testX,testY=test
trainX=pad_sequences(trainX,maxlen=100,value=0.)
testX=pad_sequences(testX,maxlen=100,value=0.)
trainY=to_categorical(trainY,nb_classes=2)
testY=to_categorical(testY,nb_classes=2)
print("size trianX",trainX.size)
print("size testX",testX.size)
print("size trainY",trainY.size)
print("size testY",testY.size)
network=input_data(shape=[None,100],name='input')
network=tflearn.embedding(network,input_dim=10000,output_dim=128)
#build network
brach1=conv_1d(network,128,3,padding='valid',activation='relu',regularizer='L2')
brach2=conv_1d(network,128,4,padding='valid',activation='relu',regularizer='L2')
brach3=conv_1d(network,128,5,padding='valid',activation='relu',regularizer='L2')
network=merge({brach1,brach2,brach3},mode='concat',axis=1)
network=tf.expand_dims(network,2)
network=global_max_pool(network)
network=dropout(network,0.5)
network=fully_connected(network,2,activation='softmax')
network=regression(network,optimizer='adam',learning_rate=0.001,loss='categorical_crossentropy',name='target')
model=tflearn.DNN(network,tensorboard_verbose=1,tensorboard_dir='log/情感分析/')
model.fit(trainX,trainY,n_epoch=5,shuffle=True,validation_set=(testX,testY),
show_metric=True,batch_size=32)
model.save("model\文字情感分析.dat")
#------------------------------------------------------
#.....
| Adam | epoch: 005 | loss: 0.12761 - acc: 0.9614 -- iter: 22368/22500
Training Step: 3516 | total loss: 0.12156 | time: 24.766s
| Adam | epoch: 005 | loss: 0.12156 - acc: 0.9652 -- iter: 22400/22500
Training Step: 3517 | total loss: 0.11845 | time: 24.800s
| Adam | epoch: 005 | loss: 0.11845 - acc: 0.9656 -- iter: 22432/22500
Training Step: 3518 | total loss: 0.11626 | time: 24.834s
| Adam | epoch: 005 | loss: 0.11626 - acc: 0.9659 -- iter: 22464/22500
Training Step: 3519 | total loss: 0.11048 | time: 24.868s
| Adam | epoch: 005 | loss: 0.11048 - acc: 0.9693 -- iter: 22496/22500
Training Step: 3520 | total loss: 0.10427 | time: 25.941s
| Adam | epoch: 005 | loss: 0.10427 - acc: 0.9724 | val_loss: 0.55094 - val_acc: 0.7912 -- iter: 22500/22500
--
Process finished with exit code 0
