Python data_utils.to_categorical函数代码示例

def do_rnn(trainX, testX, trainY, testY):
    max_document_length=64
    y_test=testY
    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=64)
    net = tflearn.lstm(net, 64, dropout=0.1)
    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,tensorboard_dir="dga_log")
    model.fit(trainX, trainY, validation_set=(testX, testY), show_metric=True,
              batch_size=10,run_id="dga",n_epoch=1)

    y_predict_list = model.predict(testX)
    #print y_predict_list

    y_predict = []
    for i in y_predict_list:
        print  i[0]
        if i[0] > 0.5:
            y_predict.append(0)
        else:
            y_predict.append(1)

    print(classification_report(y_test, y_predict))
    print metrics.confusion_matrix(y_test, y_predict)

def do_cnn_doc2vec(trainX, testX, trainY, testY):
    global max_features
    print "CNN and doc2vec"

    #trainX = pad_sequences(trainX, maxlen=max_features, value=0.)
    #testX = pad_sequences(testX, maxlen=max_features, 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_features], name='input')
    network = tflearn.embedding(network, input_dim=1000000, output_dim=128,validate_indices=False)
    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="review")

def  do_cnn(trainX, trainY,testX, testY):
    global n_words
    # Data preprocessing
    # Sequence padding
    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=n_words+1, 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, 0.5)
    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 = 20, shuffle=True, validation_set=(testX, testY), show_metric=True, batch_size=32)

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_rnn(x_train,x_test,y_train,y_test):
    global n_words
    # Data preprocessing
    # Sequence padding
    print "GET n_words embedding %d" % n_words


    #x_train = pad_sequences(x_train, maxlen=100, value=0.)
    #x_test = pad_sequences(x_test, maxlen=100, value=0.)
    # Converting labels to binary vectors
    y_train = to_categorical(y_train, nb_classes=2)
    y_test = to_categorical(y_test, nb_classes=2)

    # Network building
    net = tflearn.input_data(shape=[None, 100,n_words])
    net = tflearn.lstm(net, 10,  return_seq=True)
    net = tflearn.lstm(net, 10, )
    net = tflearn.fully_connected(net, 2, activation='softmax')
    net = tflearn.regression(net, optimizer='adam', learning_rate=0.1,name="output",
                             loss='categorical_crossentropy')

    # Training

    model = tflearn.DNN(net, tensorboard_verbose=3)
    model.fit(x_train, y_train, validation_set=(x_test, y_test), show_metric=True,
             batch_size=32,run_id="maidou")

def do_rnn(x,y):
    global max_document_length
    print "RNN"
    trainX, testX, trainY, testY = train_test_split(x, y, test_size=0.4, random_state=0)
    y_test=testY

    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=0.1, show_metric=True,
              batch_size=10,run_id="webshell",n_epoch=5)

    y_predict_list=model.predict(testX)
    y_predict=[]
    for i in y_predict_list:
        if i[0] > 0.5:
            y_predict.append(0)
        else:
            y_predict.append(1)

    do_metrics(y_test, y_predict)

def do_cnn(x,y):
    global max_document_length
    print "CNN and tf"
    trainX, testX, trainY, testY = train_test_split(x, y, test_size=0.4, random_state=0)
    y_test=testY

    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')

    model = tflearn.DNN(network, tensorboard_verbose=0)
    #if not os.path.exists(pkl_file):
        # Training
    model.fit(trainX, trainY,
                  n_epoch=5, shuffle=True, validation_set=0.1,
                  show_metric=True, batch_size=100,run_id="webshell")
    #    model.save(pkl_file)
    #else:
    #    model.load(pkl_file)

    y_predict_list=model.predict(testX)
    #y_predict = list(model.predict(testX,as_iterable=True))

    y_predict=[]
    for i in y_predict_list:
        print  i[0]
        if i[0] > 0.5:
            y_predict.append(0)
        else:
            y_predict.append(1)
    print 'y_predict_list:'
    print y_predict_list
    print 'y_predict:'
    print  y_predict
    #print  y_test

    do_metrics(y_test, y_predict)

def process_form_data(filename) :
    data = h5py.File(filename, 'r')
    output = h5py.File('forms_out.h5', 'w')

    test_image = output.create_dataset('test_image', (330, 3, 256, 256), dtype=np.uint8)
    train_image = output.create_dataset('train_image', (770, 3, 256, 256), dtype=np.uint8)
    test_label  = output.create_dataset('test_label', (330,11), dtype=np.int8)
    train_label  = output.create_dataset('train_label', (770,11), dtype=np.int8)

    image, labels = shuffle(data['image'], data['form'])

    onehot_labels = to_categorical(labels, 11)


    count = {}
    train_count = 0
    test_count = 0
    for i, l in enumerate(labels) :

        if l not in count :
            count[l] = 0

        if count[l] > 29 :
            train_image[train_count] = image[i]
            train_label[train_count] = onehot_labels[i]
            train_count += 1

        else :
            test_image[test_count] = image[i]
            test_label[test_count] = onehot_labels[i]
            test_count += 1

        count[l] += 1

    output.close()

def do_rnn(trainX, testX, trainY, testY):
    global max_sequences_len
    global max_sys_call
    # Data preprocessing
    # Sequence padding

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

    # Network building
    print "GET max_sequences_len embedding %d" % max_sequences_len
    print "GET max_sys_call embedding %d" % max_sys_call

    net = tflearn.input_data([None, max_sequences_len])
    net = tflearn.embedding(net, input_dim=max_sys_call+1, output_dim=128)
    net = tflearn.lstm(net, 128, dropout=0.3)
    net = tflearn.fully_connected(net, 2, activation='softmax')
    net = tflearn.regression(net, optimizer='adam', learning_rate=0.1,
                             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")

    y_predict_list = model.predict(testX)
    #print y_predict_list

    y_predict = []
    for i in y_predict_list:
        #print  i[0]
        if i[0] > 0.5:
            y_predict.append(0)
        else:
            y_predict.append(1)

    #y_predict=to_categorical(y_predict, nb_classes=2)

    print(classification_report(testY_old, y_predict))
    print metrics.confusion_matrix(testY_old, y_predict)

def do_cnn_word2vec_2d(trainX, testX, trainY, testY):
    global max_features
    global max_document_length
    print "CNN and word2vec2d"
    y_test = testY
    #trainX = pad_sequences(trainX, maxlen=max_features, value=0.)
    #testX = pad_sequences(testX, maxlen=max_features, 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,max_features,1], name='input')

    network = conv_2d(network, 32, 3, activation='relu', regularizer="L2")
    network = max_pool_2d(network, 2)
    network = local_response_normalization(network)
    network = conv_2d(network, 64, 3, activation='relu', regularizer="L2")
    network = max_pool_2d(network, 2)
    network = local_response_normalization(network)
    network = fully_connected(network, 128, activation='tanh')
    network = dropout(network, 0.8)
    network = fully_connected(network, 256, activation='tanh')
    network = dropout(network, 0.8)
    network = fully_connected(network, 2, activation='softmax')
    network = regression(network, optimizer='adam', learning_rate=0.01,
                         loss='categorical_crossentropy', name='target')

    model = tflearn.DNN(network, tensorboard_verbose=0)
    model.fit(trainX, trainY,
              n_epoch=5, shuffle=True, validation_set=(testX, testY),
              show_metric=True,run_id="sms")

    y_predict_list = model.predict(testX)
    print y_predict_list

    y_predict = []
    for i in y_predict_list:
        print  i[0]
        if i[0] > 0.5:
            y_predict.append(0)
        else:
            y_predict.append(1)

    print(classification_report(y_test, y_predict))
    print metrics.confusion_matrix(y_test, y_predict)

def bi_lstm(trainX, trainY,testX, testY):
    trainX = pad_sequences(trainX, maxlen=200, value=0.)
    testX = pad_sequences(testX, maxlen=200, 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(shape=[None, 200])
    net = tflearn.embedding(net, input_dim=20000, output_dim=128)
    net = tflearn.bidirectional_rnn(net, BasicLSTMCell(128), BasicLSTMCell(128))
    net = tflearn.dropout(net, 0.5)
    net = tflearn.fully_connected(net, 2, activation='softmax')
    net = tflearn.regression(net, optimizer='adam', loss='categorical_crossentropy')

    # Training
    model = tflearn.DNN(net, clip_gradients=0., tensorboard_verbose=2)
    model.fit(trainX, trainY, validation_set=0.1, show_metric=True, batch_size=64,run_id="rnn-bilstm")

def do_cnn_word2vec_2d_345(trainX, testX, trainY, testY):
    global max_features
    global max_document_length
    print "CNN and word2vec_2d_345"
    y_test = testY

    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,max_features,1], name='input')
    network = tflearn.embedding(network, input_dim=1, output_dim=128,validate_indices=False)
    branch1 = conv_2d(network, 128, 3, padding='valid', activation='relu', regularizer="L2")
    branch2 = conv_2d(network, 128, 4, padding='valid', activation='relu', regularizer="L2")
    branch3 = conv_2d(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_2d(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="sms")

    y_predict_list = model.predict(testX)
    print y_predict_list

    y_predict = []
    for i in y_predict_list:
        print  i[0]
        if i[0] > 0.5:
            y_predict.append(0)
        else:
            y_predict.append(1)

    print(classification_report(y_test, y_predict))
    print metrics.confusion_matrix(y_test, y_predict)

def lstm(trainX, trainY,testX, testY):
    # Data preprocessing
    # Sequence padding
    trainX = pad_sequences(trainX, maxlen=100, value=0.)
    testX = pad_sequences(testX, maxlen=100, 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, 100])
    net = tflearn.embedding(net, input_dim=10000, 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=32,run_id="rnn-lstm")

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="review",n_epoch=5)

def create_datasets(file_path, vocab_size=30000, val_fraction=0.0):

    # IMDB Dataset loading
    train, test, _ = imdb.load_data(
        path=file_path,
        n_words=vocab_size,
        valid_portion=val_fraction,
        sort_by_len=False)
    trainX, trainY = train
    testX, testY = test

    # Data preprocessing
    # Sequence padding
    trainX = pad_sequences(trainX, maxlen=FLAGS.max_len, value=0.)
    testX = pad_sequences(testX, maxlen=FLAGS.max_len, value=0.)
    # Converting labels to binary vectors
    trainY = to_categorical(trainY, nb_classes=2)
    testY = to_categorical(testY, nb_classes=2)

    train_dataset = DataSet(trainX, trainY)

    return train_dataset