《Web安全之机器学习入门》笔记：第十六章 16.3 恶意评论识别（二）

本小节使用NB和RNN两种方法识别恶意评论。

1、数据集获取

（1）正面影评

数据集的位置：../data/movie-review-data/review_polarity/txt_sentoken/pos/

x1,y1=load_files("../data/movie-review-data/review_polarity/txt_sentoken/pos/",0)

（2）负面影评

数据集的位置：../data/movie-review-data/review_polarity/txt_sentoken/neg/

x2,y2=load_files("../data/movie-review-data/review_polarity/txt_sentoken/neg/", 1)

（3）数据获取

def load_one_file(filename):
    x=""
    with open(filename) as f:
        for line in f:
            x+=line
    return x

def load_files(rootdir,label):
    list = os.listdir(rootdir)
    x=[]
    y=[]
    for i in range(0, len(list)):
        path = os.path.join(rootdir, list[i])
        if os.path.isfile(path):
            print("Load file %s" % path)
            y.append(label)
            x.append(load_one_file(path))
    return x,y

def load_data():
    x=[]
    y=[]
    x1,y1=load_files("../data/movie-review-data/review_polarity/txt_sentoken/pos/",0)
    x2,y2=load_files("../data/movie-review-data/review_polarity/txt_sentoken/neg/", 1)
    x=x1+x2
    y=y1+y2
    return x,y

def main(unused_argv):
    global n_words

    x,y=load_data()
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.4, random_state=0)

    vp = learn.preprocessing.VocabularyProcessor(max_document_length=MAX_DOCUMENT_LENGTH, min_frequency=1)
    vp.fit(x)
    x_train = np.array(list(vp.transform(x_train)))
    x_test = np.array(list(vp.transform(x_test)))
    n_words=len(vp.vocabulary_)
    print('Total words: %d' % n_words)

打印结果

Total words: 28334

2、RNN模型

def do_rnn(trainX, testX, trainY, testY):
    global n_words
    # Data preprocessing
    # Sequence padding
    print("GET n_words embedding %d" % n_words)


    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=n_words, 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=3)
    model.fit(trainX, trainY, validation_set=(testX, testY), show_metric=True,
             batch_size=32,run_id="maidou")

3、NB模型

def do_NB(x_train, x_test, y_train, y_test):
    gnb = GaussianNB()
    y_predict = gnb.fit(x_train, y_train).predict(x_test)
    score = metrics.accuracy_score(y_test, y_predict)
    print('NB Accuracy: {0:f}'.format(score))

4、完整代码

import tensorflow as tf
from tensorflow.contrib.learn.python import learn
from sklearn import metrics
from sklearn.model_selection import train_test_split
import numpy as np
from sklearn.naive_bayes import GaussianNB
import os
from sklearn.feature_extraction.text import CountVectorizer
from tensorflow.contrib.layers.python.layers import encoders
from sklearn import svm
import tflearn
from tflearn.data_utils import to_categorical, pad_sequences
from tflearn.datasets import imdb


MAX_DOCUMENT_LENGTH = 200
EMBEDDING_SIZE = 50

n_words=0


def load_one_file(filename):
    x=""
    with open(filename) as f:
        for line in f:
            x+=line
    return x

def load_files(rootdir,label):
    list = os.listdir(rootdir)
    x=[]
    y=[]
    for i in range(0, len(list)):
        path = os.path.join(rootdir, list[i])
        if os.path.isfile(path):
            print("Load file %s" % path)
            y.append(label)
            x.append(load_one_file(path))
    return x,y

def load_data():
    x=[]
    y=[]
    x1,y1=load_files("../data/movie-review-data/review_polarity/txt_sentoken/pos/",0)
    x2,y2=load_files("../data/movie-review-data/review_polarity/txt_sentoken/neg/", 1)
    x=x1+x2
    y=y1+y2
    return x,y

def do_rnn(trainX, testX, trainY, testY):
    global n_words
    # Data preprocessing
    # Sequence padding
    print("GET n_words embedding %d" % n_words)


    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=n_words, 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=3)
    model.fit(trainX, trainY, validation_set=(testX, testY), show_metric=True,
             batch_size=32,run_id="maidou")


def do_NB(x_train, x_test, y_train, y_test):
    gnb = GaussianNB()
    y_predict = gnb.fit(x_train, y_train).predict(x_test)
    score = metrics.accuracy_score(y_test, y_predict)
    print('NB Accuracy: {0:f}'.format(score))

def main(unused_argv):
    global n_words

    x,y=load_data()
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.4, random_state=0)

    vp = learn.preprocessing.VocabularyProcessor(max_document_length=MAX_DOCUMENT_LENGTH, min_frequency=1)
    vp.fit(x)
    x_train = np.array(list(vp.transform(x_train)))
    x_test = np.array(list(vp.transform(x_test)))
    n_words=len(vp.vocabulary_)
    print('Total words: %d' % n_words)
    do_NB(x_train, x_test, y_train, y_test)
    do_rnn(x_train, x_test, y_train, y_test)

if __name__ == '__main__':
  tf.app.run()

5、运行结果

RNN算法结果

......
Training Step: 378  | total loss: 0.08034 | time: 15.892s
| Adam | epoch: 010 | loss: 0.08034 - acc: 0.9874 -- iter: 1152/1200
Training Step: 379  | total loss: 0.07429 | time: 16.334s
| Adam | epoch: 010 | loss: 0.07429 - acc: 0.9887 -- iter: 1184/1200
Training Step: 380  | total loss: 0.07552 | time: 18.796s
| Adam | epoch: 010 | loss: 0.07552 - acc: 0.9867

| val_loss: 1.07911 - val_acc: 0.6188 -- iter: 1200/1200
--

NB算法结果

NB Accuracy: 0.493750

如上NB算法准确率仅为49.37%左右，RNN准确率仅61.88%左右。从RNN的训练准确率可达到98%以上，而测试准确率如此不理想，可见泛化性能差了些，还有调优空间

最后

以上就是害羞洋葱为你收集整理的《Web安全之机器学习入门》笔记：第十六章 16.3 恶意评论识别（二）的全部内容，希望文章能够帮你解决《Web安全之机器学习入门》笔记：第十六章 16.3 恶意评论识别（二）所遇到的程序开发问题。

如果觉得靠谱客网站的内容还不错，欢迎将靠谱客网站推荐给程序员好友。