PaddlePaddle垃圾邮件处理实战（二）
前文回顾
在上篇文章中我们讲了如何用支持向量机对垃圾邮件进行分类，auc为73.3%，本篇讲继续讲如何用PaddlePaddle实现邮件分类，将深度学习方法运用到文本分类中。
构建网络模型
用PaddlePaddle来构建网络模型其实很简单，首先得明确paddlepaddle的输入数据的格式要求，知道如何构建网络模型，以及如何训练。关于输入数据的预处理等可以参考我之前写的这篇文章【深度学习系列】PaddlePaddle之数据预处理。首先我们先采用一个浅层的神经网络来进行训练。
具体步骤
- 读取数据
- 划分训练集和验证集
- 定义网络结构
- 打印训练日志
- 可视化训练结果
读取数据
在PaddlePaddle中，我们需要创建一个reador来读取数据，在上篇文章中，我们已经对原始数据处理好了，正负样本分别为ham.txt和spam.txxt，这里我们只需要加载数据即可。
代码实现：
# 加载数据
def loadfile():
# 加载正样本
fopen = open('ham.txt','r')
pos = []
for line in fopen:
pos.append(line)
#加载负样本
fopen = open('spam.txt','r')
neg = []
for line in fopen:
neg.append(line)
combined=np.concatenate((pos, neg))
# 创建label
y = np.concatenate((np.ones(len(pos),dtype=int), np.zeros(len(neg),dtype=int)))
return combined,y
# 创建paddlepaddle读取数据的reader
def reader_creator(dataset,label):
def reader():
for i in xrange(len(dataset)):
yield dataset[i,:],int(label[i])
return reader
创建词语索引：
#创建词语字典，并返回每个词语的索引，词向量，以及每个句子所对应的词语索引
def create_dictionaries(model=None,
combined=None):
if (combined is not None) and (model is not None):
gensim_dict = Dictionary()
gensim_dict.doc2bow(model.wv.vocab.keys(),
allow_update=True)
w2indx = {v: k+1 for k, v in gensim_dict.items()}#所有频数超过10的词语的索引
w2vec = {word: model[word] for word in w2indx.keys()}#所有频数超过10的词语的词向量
def parse_dataset(combined):
''' Words become integers
'''
data=[]
for sentence in combined:
new_txt = []
sentences = sentence.split(' ')
for word in sentences:
try:
word = unicode(word, errors='ignore')
new_txt.append(w2indx[word])
except:
new_txt.append(0)
data.append(new_txt)
return data
combined=parse_dataset(combined)
combined= sequence.pad_sequences(combined, maxlen=maxlen)#每个句子所含词语对应的索引，所以句子中含有频数小于10的词语，索引为0
return w2indx, w2vec,combined
else:
print 'No data provided...'
划分训练集和验证集
这里我们采取sklearn的train_test_split函数对数据集进行划分，训练集和验证集的比例为4：1。
代码实现：
# 导入word2vec模型
def word2vec_train(combined):
model = Word2Vec.load('lstm_data/model/Word2vec_model.pkl')
index_dict, word_vectors,combined = create_dictionaries(model=model,combined=combined)
return index_dict, word_vectors,combined
# 获取训练集、验证集
def get_data(index_dict,word_vectors,combined,y):
n_symbols = len(index_dict) + 1 # 所有单词的索引数，频数小于10的词语索引为0，所以加1
embedding_weights = np.zeros((n_symbols, vocab_dim))#索引为0的词语，词向量全为0
for word, index in index_dict.items():#从索引为1的词语开始，对每个词语对应其词向量
embedding_weights[index, :] = word_vectors[word]
x_train, x_val, y_train, y_val = train_test_split(combined, y, test_size=0.2)
print x_train.shape,y_train.shape
return n_symbols,embedding_weights,x_train,y_train,x_val,y_val
定义网络结构
class NeuralNetwork(object):
def __init__(self,X_train,Y_train,X_val,Y_val,vocab_dim,n_symbols,num_classes=2):
paddle.init(use_gpu = with_gpu,trainer_count=1)
self.X_train = X_train
self.Y_train = Y_train
self.X_val = X_val
self.Y_val = Y_val
self.vocab_dim = vocab_dim
self.n_symbols = n_symbols
self.num_classes=num_classes
# 定义网络模型
def get_network(self):
# 分类模型
x = paddle.layer.data(name='x', type=paddle.data_type.dense_vector(self.vocab_dim))
y = paddle.layer.data(name='y', type=paddle.data_type.integer_value(self.num_classes))
fc1 = paddle.layer.fc(input = x,size = 1280,act = paddle.activation.Linear())
fc2 = paddle.layer.fc(input = fc1,size = 640,act = paddle.activation.Relu())
prob = paddle.layer.fc(input = fc2,size = self.num_classes,act = paddle.activation.Softmax())
predict = paddle.layer.mse_cost(input = prob,label = y)
return predict
# 定义训练器
def get_trainer(self):
cost = self.get_network()
#获取参数
parameters = paddle.parameters.create(cost)
#定义优化方法
optimizer0 = paddle.optimizer.Momentum(
momentum=0.9,
regularization=paddle.optimizer.L2Regularization(rate=0.0002 * 128),
learning_rate=0.01 / 128.0,
learning_rate_decay_a=0.01,
learning_rate_decay_b=50000 * 100)
optimizer1 = paddle.optimizer.Momentum(
momentum=0.9,
regularization=paddle.optimizer.L2Regularization(rate=0.0002 * 128),
learning_rate=0.001,
learning_rate_schedule = "pass_manual",
learning_rate_args = "1:1.0, 8:0.1, 13:0.01")
optimizer = paddle.optimizer.Adam(
learning_rate=2e-3,
regularization=paddle.optimizer.L2Regularization(rate=8e-4),
model_average=paddle.optimizer.ModelAverage(average_window=0.5))
# 创建训练器
trainer = paddle.trainer.SGD(
cost=cost, parameters=parameters, update_equation=optimizer)
return parameters,trainer
# 开始训练
def start_trainer(self,X_train,Y_train,X_val,Y_val):
parameters,trainer = self.get_trainer()
result_lists = []
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
print "\nPass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
if isinstance(event, paddle.event.EndPass):
# 保存训练好的参数
with open('params_pass_%d.tar' % event.pass_id, 'w') as f:
parameters.to_tar(f)
# feeding = ['x','y']
result = trainer.test(
reader=val_reader)
# feeding=feeding)
print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
result_lists.append((event.pass_id, result.cost,
result.metrics['classification_error_evaluator']))
# 开始训练
train_reader = paddle.batch(paddle.reader.shuffle(
reader_creator(X_train,Y_train),buf_size=20),
batch_size=4)
val_reader = paddle.batch(paddle.reader.shuffle(
reader_creator(X_val,Y_val),buf_size=20),
batch_size=4)
trainer.train(reader=train_reader,num_passes=5,event_handler=event_handler)
#找到训练误差最小的一次结果
best = sorted(result_lists, key=lambda list: float(list[1]))[0]
print 'Best pass is %s, testing Avgcost is %s' % (best[0], best[1])
print 'The classification accuracy is %.2f%%' % (100 - float(best[2]) * 100)
训练模型
#训练模型，并保存
def train():
print 'Loading Data...'
combined,y=loadfile()
print len(combined),len(y)
print 'Tokenising...'
combined = tokenizer(combined)
print 'Training a Word2vec model...'
index_dict, word_vectors,combined=word2vec_train(combined)
print 'Setting up Arrays for Keras Embedding Layer...'
n_symbols,embedding_weights,x_train,y_train,x_val,y_val=get_data(index_dict, word_vectors,combined,y)
print x_train.shape,y_train.shape
network = NeuralNetwork(X_train = x_train,Y_train = y_train,X_val = x_val, Y_val = y_val,vocab_dim = vocab_dim,n_symbols = n_symbols,num_classes = 2)
network.start_trainer(x_train,y_train,x_val,y_val)
if __name__=='__main__':
train()
性能测试
设置迭代5次，输出结果如下：
Using TensorFlow backend.
Loading Data...
63000 63000
Tokenising...
Building prefix dict from the default dictionary ...
[DEBUG 2018-01-29 00:29:19,184 __init__.py:111] Building prefix dict from the default dictionary ...
Loading model from cache /tmp/jieba.cache
[DEBUG 2018-01-29 00:29:19,185 __init__.py:131] Loading model from cache /tmp/jieba.cache
Loading model cost 0.253 seconds.
[DEBUG 2018-01-29 00:29:19,437 __init__.py:163] Loading model cost 0.253 seconds.
Prefix dict has been built succesfully.
[DEBUG 2018-01-29 00:29:19,437 __init__.py:164] Prefix dict has been built succesfully.
I0128 12:29:17.325337 16772 GradientMachine.cpp:101] Init parameters done.
Pass 0, Batch 0, Cost 0.519137, {'classification_error_evaluator': 0.25}
Pass 0, Batch 100, Cost 0.410812, {'classification_error_evaluator': 0}
Pass 0, Batch 200, Cost 0.486661, {'classification_error_evaluator': 0.25}
···
Pass 4, Batch 12200, Cost 0.508126, {'classification_error_evaluator': 0.25}
Pass 4, Batch 12300, Cost 0.312028, {'classification_error_evaluator': 0.25}
Pass 4, Batch 12400, Cost 0.259026, {'classification_error_evaluator': 0.0}
Pass 4, Batch 12500, Cost 0.177996, {'classification_error_evaluator': 0.25}
Test with Pass 4, {'classification_error_evaluator': 0.15238096714019775}
Best pass is 4, testing Avgcost is 0.716855627394
The classification accuracy is 84.76%
由此可以看到，仅迭代5次paddlepaddle的结果即可达到84.76%，如果增加迭代次数，可以达到更高的准确率。
总结
本篇文章讲了如何用paddlepaddle来进行垃圾邮件分类，采取一个简单的浅层神经网络来训练模型，迭代5次的准确率即为84.76%。在实际操作过程中，大家可以增加迭代次数，提高模型的精度，也可采取一些其他的方法，譬如文本CNN模型，LSTM模型来训练以获得更好的效果。
本文首发于景略集智，并由景略集智制作成“PaddlePaddle调戏邮件诈骗犯”系列视频。如果有不懂的，欢迎在评论区中提问~