开发者社区> 桃子红了呐> 正文

使用神经网络-垃圾邮件检测-LSTM或者CNN(一维卷积)效果都不错【代码有问题,pass】

简介:
+关注继续查看
复制代码
from sklearn.feature_extraction.text import CountVectorizer
import os
from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import train_test_split
from sklearn import metrics
import matplotlib.pyplot as plt
import numpy as np
from sklearn import svm
from sklearn.feature_extraction.text import TfidfTransformer
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.conv import conv_2d, max_pool_2d
from tflearn.layers.merge_ops import merge
from tflearn.layers.estimator import regression
from tflearn.data_utils import to_categorical, pad_sequences
from sklearn.neural_network import MLPClassifier
from tflearn.layers.normalization import local_response_normalization
from tensorflow.contrib import learn


max_features=500
max_document_length=1024



def load_one_file(filename):
    x=""
    with open(filename) as f:
        for line in f:
            line=line.strip('\n')
            line = line.strip('\r')
            x+=line
    return x

def load_files_from_dir(rootdir):
    x=[]
    list = os.listdir(rootdir)
    for i in range(0, len(list)):
        path = os.path.join(rootdir, list[i])
        if os.path.isfile(path):
            v=load_one_file(path)
            x.append(v)
    return x

def load_all_files():
    ham=[]
    spam=[]
    for i in range(1,5):
        path="../data/mail/enron%d/ham/" % i
        print "Load %s" % path
        ham+=load_files_from_dir(path)
        path="../data/mail/enron%d/spam/" % i
        print "Load %s" % path
        spam+=load_files_from_dir(path)
    return ham,spam

def get_features_by_wordbag():
    ham, spam=load_all_files()
    x=ham+spam
    y=[0]*len(ham)+[1]*len(spam)
    vectorizer = CountVectorizer(
                                 decode_error='ignore',
                                 strip_accents='ascii',
                                 max_features=max_features,
                                 stop_words='english',
                                 max_df=1.0,
                                 min_df=1 )
    print vectorizer
    x=vectorizer.fit_transform(x)
    x=x.toarray()
    return x,y

def show_diffrent_max_features():
    global max_features
    a=[]
    b=[]
    for i in range(1000,20000,2000):
        max_features=i
        print "max_features=%d" % i
        x, y = get_features_by_wordbag()
        x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.4, random_state=0)
        gnb = GaussianNB()
        gnb.fit(x_train, y_train)
        y_pred = gnb.predict(x_test)
        score=metrics.accuracy_score(y_test, y_pred)
        a.append(max_features)
        b.append(score)
        plt.plot(a, b, 'r')
    plt.xlabel("max_features")
    plt.ylabel("metrics.accuracy_score")
    plt.title("metrics.accuracy_score VS max_features")
    plt.legend()
    plt.show()

def do_nb_wordbag(x_train, x_test, y_train, y_test):
    print "NB and wordbag"
    gnb = GaussianNB()
    gnb.fit(x_train,y_train)
    y_pred=gnb.predict(x_test)
    print metrics.accuracy_score(y_test, y_pred)
    print metrics.confusion_matrix(y_test, y_pred)

def do_svm_wordbag(x_train, x_test, y_train, y_test):
    print "SVM and wordbag"
    clf = svm.SVC()
    clf.fit(x_train, y_train)
    y_pred = clf.predict(x_test)
    print metrics.accuracy_score(y_test, y_pred)
    print metrics.confusion_matrix(y_test, y_pred)

def get_features_by_wordbag_tfidf():
    ham, spam=load_all_files()
    x=ham+spam
    y=[0]*len(ham)+[1]*len(spam)
    vectorizer = CountVectorizer(binary=True,
                                 decode_error='ignore',
                                 strip_accents='ascii',
                                 max_features=max_features,
                                 stop_words='english',
                                 max_df=1.0,
                                 min_df=1 )
    print vectorizer
    x=vectorizer.fit_transform(x)
    x=x.toarray()
    transformer = TfidfTransformer(smooth_idf=False)
    print transformer
    tfidf = transformer.fit_transform(x)
    x = tfidf.toarray()
    return  x,y


def do_cnn_wordbag(trainX, testX, trainY, testY):
    global max_document_length
    print "CNN and tf"

    trainX = pad_sequences(trainX, maxlen=max_document_length, value=0.)
    testX = pad_sequences(testX, maxlen=max_document_length, value=0.)
    # Converting labels to binary vectors
    trainY = to_categorical(trainY, nb_classes=2)
    testY = to_categorical(testY, nb_classes=2)

    # Building convolutional network
    network = input_data(shape=[None,max_document_length], name='input')
    network = tflearn.embedding(network, input_dim=1000000, output_dim=128)
    branch1 = conv_1d(network, 128, 3, padding='valid', activation='relu', regularizer="L2")
    branch2 = conv_1d(network, 128, 4, padding='valid', activation='relu', regularizer="L2")
    branch3 = conv_1d(network, 128, 5, padding='valid', activation='relu', regularizer="L2")
    network = merge([branch1, branch2, branch3], mode='concat', axis=1)
    network = tf.expand_dims(network, 2)
    network = global_max_pool(network)
    network = dropout(network, 0.8)
    network = fully_connected(network, 2, activation='softmax')
    network = regression(network, optimizer='adam', learning_rate=0.001,
                         loss='categorical_crossentropy', name='target')
    # Training
    model = tflearn.DNN(network, tensorboard_verbose=0)
    model.fit(trainX, trainY,
              n_epoch=5, shuffle=True, validation_set=(testX, testY),
              show_metric=True, batch_size=100,run_id="spam")

def do_rnn_wordbag(trainX, testX, trainY, testY):
    global max_document_length
    print "RNN and wordbag"

    trainX = pad_sequences(trainX, maxlen=max_document_length, value=0.)
    testX = pad_sequences(testX, maxlen=max_document_length, value=0.)
    # Converting labels to binary vectors
    trainY = to_categorical(trainY, nb_classes=2)
    testY = to_categorical(testY, nb_classes=2)

    # Network building
    net = tflearn.input_data([None, max_document_length])
    net = tflearn.embedding(net, input_dim=10240000, output_dim=128)
    net = tflearn.lstm(net, 128, dropout=0.8)
    net = tflearn.fully_connected(net, 2, activation='softmax')
    net = tflearn.regression(net, optimizer='adam', learning_rate=0.001,
                             loss='categorical_crossentropy')

    # Training
    model = tflearn.DNN(net, tensorboard_verbose=0)
    model.fit(trainX, trainY, validation_set=(testX, testY), show_metric=True,
              batch_size=10,run_id="spm-run",n_epoch=5)


def do_dnn_wordbag(x_train, x_test, y_train, y_testY):
    print "DNN and wordbag"

    # Building deep neural network
    clf = MLPClassifier(solver='lbfgs',
                        alpha=1e-5,
                        hidden_layer_sizes = (5, 2),
                        random_state = 1)
    print  clf
    clf.fit(x_train, y_train)
    y_pred = clf.predict(x_test)
    print metrics.accuracy_score(y_test, y_pred)
    print metrics.confusion_matrix(y_test, y_pred)



def  get_features_by_tf():
    global  max_document_length
    x=[]
    y=[]
    ham, spam=load_all_files()
    x=ham+spam
    y=[0]*len(ham)+[1]*len(spam)
    vp=tflearn.data_utils.VocabularyProcessor(max_document_length=max_document_length,
                                              min_frequency=0,
                                              vocabulary=None,
                                              tokenizer_fn=None)
    x=vp.fit_transform(x, unused_y=None)
    x=np.array(list(x))
    return x,y



if __name__ == "__main__":
    print "Hello spam-mail"
    #print "get_features_by_wordbag"
    #x,y=get_features_by_wordbag()
    #x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.4, random_state = 0)

    #print "get_features_by_wordbag_tfidf"
    #x,y=get_features_by_wordbag_tfidf()
    #x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.4, random_state = 0)
    #NB
    #do_nb_wordbag(x_train, x_test, y_train, y_test)
    #show_diffrent_max_features()

    #SVM
    #do_svm_wordbag(x_train, x_test, y_train, y_test)

    #DNN
    #do_dnn_wordbag(x_train, x_test, y_train, y_test)

    print "get_features_by_tf"
    x,y=get_features_by_wordbag()
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.4, random_state = 0)
    #CNN
    do_cnn_wordbag(x_train, x_test, y_train, y_test)


    #RNN
    #do_rnn_wordbag(x_train, x_test, y_train, y_test)
复制代码

自己写检测算法的时候也记得多个算法比较下

posted on 2017-11-28 11:08 bonelee 阅读(75) 评论(3编辑 收藏

  
#1楼[楼主2017-12-11 16:12 | bonelee  
感觉有些问题,因为LSTM要记住序列位置,而词袋模型,破坏了序列先后顺序!
http://www.cnblogs.com/bonelee/p/7639920.html
见这个DGA LSTM的文章!!!才应该是正解!
  
#2楼[楼主2017-12-11 16:23 | bonelee  
代码确实有问题!
RNN或者CNN都应该是针对原始数据进行编码!用:
Vocabulary Processor

tflearn.data_utils.VocabularyProcessor (max_document_length, min_frequency=0, vocabulary=None, tokenizer_fn=None)

Maps documents to sequences of word ids.



tf.contrib.learn.preprocessing.VocabularyProcessor (max_document_length, min_frequency=0, vocabulary=None, tokenizer_fn=None)

参数:
max_document_length: 文档的最大长度。如果文本的长度大于最大长度,那么它会被剪切,反之则用0填充。
min_frequency: 词频的最小值,出现次数小于最小词频则不会被收录到词表中。
vocabulary: CategoricalVocabulary 对象。
tokenizer_fn:分词函数

代码:

from tensorflow.contrib import learn
import numpy as np
max_document_length = 4
x_text =[
'i love you',
'me too'
]
vocab_processor = learn.preprocessing.VocabularyProcessor(max_document_length)
vocab_processor.fit(x_text)
print next(vocab_processor.transform(['i me too'])).tolist()
x = np.array(list(vocab_processor.fit_transform(x_text)))
print x

[1, 4, 5, 0]
[[1 2 3 0]
[4 5 0 0]]

文档地址:http://tflearn.org/data_utils/
























本文转自张昺华-sky博客园博客,原文链接:http://www.cnblogs.com/bonelee/p/7908573.html,如需转载请自行联系原作者


版权声明:本文内容由阿里云实名注册用户自发贡献,版权归原作者所有,阿里云开发者社区不拥有其著作权,亦不承担相应法律责任。具体规则请查看《阿里云开发者社区用户服务协议》和《阿里云开发者社区知识产权保护指引》。如果您发现本社区中有涉嫌抄袭的内容,填写侵权投诉表单进行举报,一经查实,本社区将立刻删除涉嫌侵权内容。

相关文章
Ubuntu中使用SSHSecure Shell测试Windows与Linux系统间操作及传输问题解决大全
安装SSH服务器 Linux终端下输入sudo apt-get install openssh-server 桥接模式IP设置 inux 与Windows 都是设置为自动获取 IP 地址,然后调到第一次测试一栏开始。
1149 0
PostMan使用手册
Postman 使用手册系列教程: Postman软件安装Postman使用手册1——导入导出和发送请求查看响应Postman使用手册2——管理收藏Postman使用手册3——环境变量Postman使用手册4——API test ...
3191 0
postman的基础使用
搜索进入postman官网下载客户端,或者安装谷歌浏览器postman扩展插件。
543 0
使用xshell连接服务器问题:ssh_exchange_identification: Connection closed by remote host
在连接服务器的时候遇到了如下的问题: 在网上查找方法: 1、让/etc/hosts.allow 和/etc/hosts.
1336 0
使用shell自动化诊断性能问题(一)(r11笔记第41天)
一直以来要做性能分析的自动化工作,但是久久没有动笔,今天索性来更新一版。 首先我希望得到的一个基本效果就是后台去扫描数据库的DB time,如果超出了阈值,比如这里我设置的为400(即DB time为400%),则会开启自动诊断的任务。
788 0
Nat.Commun.|使用基于注意力机制的多标签神经网络预测并解释12种RNA修饰
Nat.Commun.|使用基于注意力机制的多标签神经网络预测并解释12种RNA修饰
27 0
超干货|使用Keras和CNN构建分类器(内含代码和讲解)
为了让文章不那么枯燥,我构建了一个精灵图鉴数据集(Pokedex)这都是一些受欢迎的精灵图。我们在已经准备好的图像数据集上,使用Keras库训练一个卷积神经网络(CNN)。
10532 0
4269
文章
0
问答
文章排行榜
最热
最新
相关电子书
更多
OceanBase 入门到实战教程
立即下载
阿里云图数据库GDB,加速开启“图智”未来.ppt
立即下载
实时数仓Hologres技术实战一本通2.0版(下)
立即下载