The generator

Set up modules

%matplotlib inline
import os
import random
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from tqdm import tqdm_notebook as tqdm
from keras.models import Model
from keras.layers import Input, Reshape
from keras.layers.core import Dense, Activation, Dropout, Flatten
from keras.layers.normalization import BatchNormalization
from keras.layers.convolutional import UpSampling1D, Conv1D
from keras.layers.advanced_activations import LeakyReLU
from keras.optimizers import Adam, SGD
from keras.callbacks import TensorBoard
from sklearn.preprocessing import StandardScaler

dim = 30
num = 246
g_data = f_x

Using TensorFlow backend.

Standard Scaler

ss = StandardScaler()
g_data = pd.DataFrame(ss.fit_transform(g_data))

def get_generative(G_in, dense_dim=200, out_dim= dim, lr=1e-3):
    x = Dense(dense_dim)(G_in)
    x = Activation('tanh')(x)
    G_out = Dense(out_dim, activation='tanh')(x)
    G = Model(G_in, G_out)
    opt = SGD(lr=lr)
    G.compile(loss='binary_crossentropy', optimizer=opt)
    return G, G_out

G_in = Input(shape=[10])
G, G_out = get_generative(G_in)
G.summary()

WARNING:tensorflow:From C:3-gpu-packages_backend.py:74: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.

WARNING:tensorflow:From C:3-gpu-packages_backend.py:517: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.

WARNING:tensorflow:From C:3-gpu-packages_backend.py:4138: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.

WARNING:tensorflow:From C:3-gpu-packages.py:790: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.

WARNING:tensorflow:From C:3-gpu-packages_backend.py:3376: The name tf.log is deprecated. Please use tf.math.log instead.

WARNING:tensorflow:From C:3-gpu-packagesimpl.py:180: add_dispatch_support..wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version. Instructions for updating: Use tf.where in 2.0, which has the same broadcast rule as np.where ________________________________________________________________ Layer (type) Output Shape Param #
================================================================= input_1 (InputLayer) (None, 10) 0
_________________________________________________________________ dense_1 (Dense) (None, 200) 2200
_________________________________________________________________ activation_1 (Activation) (None, 200) 0
_________________________________________________________________ dense_2 (Dense) (None, 30) 6030
================================================================= Total params: 8,230 Trainable params: 8,230 Non-trainable params: 0 _________________________________________________________________

建立判別器

def get_discriminative(D_in, lr=1e-3, drate=.25, n_channels= dim, conv_sz=5, leak=.2):
    x = Reshape((-1, 1))(D_in)
    x = Conv1D(n_channels, conv_sz, activation='relu')(x)
    x = Dropout(drate)(x)
    x = Flatten()(x)
    x = Dense(n_channels)(x)
    D_out = Dense(2, activation='sigmoid')(x)
    D = Model(D_in, D_out)
    dopt = Adam(lr=lr)
    D.compile(loss='binary_crossentropy', optimizer=dopt)
    return D, D_out

D_in = Input(shape=[dim])
D, D_out = get_discriminative(D_in)
D.summary()

WARNING:tensorflow:From C:3-gpu-packages_backend.py:133: The name tf.placeholder_with_default is deprecated. Please use tf.compat.v1.placeholder_with_default instead.

WARNING:tensorflow:From C:3-gpu-packagesbackend.py:3445: calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version. Instructions for updating: Please use rate instead of keep_prob. Rate should be set to rate = 1 - keep_prob. ________________________________________________________________ Layer (type) Output Shape Param #
================================================================= input_2 (InputLayer) (None, 30) 0
_________________________________________________________________ reshape_1 (Reshape) (None, 30, 1) 0
_________________________________________________________________ conv1d_1 (Conv1D) (None, 26, 30) 180
_________________________________________________________________ dropout_1 (Dropout) (None, 26, 30) 0
_________________________________________________________________ flatten_1 (Flatten) (None, 780) 0
_________________________________________________________________ dense_3 (Dense) (None, 30) 23430
_________________________________________________________________ dense_4 (Dense) (None, 2) 62
================================================================= Total params: 23,672 Trainable params: 23,672 Non-trainable params: 0 _________________________________________________________________

串接兩神經網路

def set_trainability(model, trainable=False):
    model.trainable = trainable
    for layer in model.layers:
        layer.trainable = trainable
        
def make_gan(GAN_in, G, D):
    set_trainability(D, False)
    x = G(GAN_in)
    GAN_out = D(x)
    GAN = Model(GAN_in, GAN_out)
    GAN.compile(loss='binary_crossentropy', optimizer=G.optimizer)
    return GAN, GAN_out

GAN_in = Input([10])
GAN, GAN_out = make_gan(GAN_in, G, D)
GAN.summary()

---

Layer (type) Output Shape Param #
================================================================= input_3 (InputLayer) (None, 10) 0
_________________________________________________________________ model_1 (Model) (None, 30) 8230
_________________________________________________________________ model_2 (Model) (None, 2) 23672
================================================================= Total params: 31,902 Trainable params: 8,230 Non-trainable params: 23,672 _________________________________________________________________

def sample_data_and_gen(G, noise_dim=10, n_samples= num):
    XT = np.array(g_data)
    XN_noise = np.random.uniform(0, 1, size=[n_samples, noise_dim])
    XN = G.predict(XN_noise)
    X = np.concatenate((XT, XN))
    y = np.zeros((2*n_samples, 2))
    y[:n_samples, 1] = 1
    y[n_samples:, 0] = 1
    return X, y

def pretrain(G, D, noise_dim=10, n_samples = num, batch_size=32):
    X, y = sample_data_and_gen(G, n_samples=n_samples, noise_dim=noise_dim)
    set_trainability(D, True)
    D.fit(X, y, epochs=1, batch_size=batch_size)
    
pretrain(G, D)

def sample_noise(G, noise_dim=10, n_samples=num):
    X = np.random.uniform(0, 1, size=[n_samples, noise_dim])
    y = np.zeros((n_samples, 2))
    y[:, 1] = 1
    return X, y

Epoch 1/1 492/492 [==============================] - ETA: 7s - loss: 0.662 - 1s 1ms/step - loss: 0.4410

訓練生成對抗網路

訓練生成對抗網路，並存取最後一次生成器產生結果

def train(GAN, G, D, epochs=100, n_samples= num, noise_dim=10, batch_size=32, verbose=False, v_freq=dim,):
    d_loss = []
    g_loss = []
    e_range = range(epochs)
    if verbose:
        e_range = tqdm(e_range)
    for epoch in e_range:
        X, y = sample_data_and_gen(G, n_samples=n_samples, noise_dim=noise_dim)
        set_trainability(D, True)
        d_loss.append(D.train_on_batch(X, y))
        xx,yy = X,y
        
        X, y = sample_noise(G, n_samples=n_samples, noise_dim=noise_dim)
        set_trainability(D, False)
        g_loss.append(GAN.train_on_batch(X, y))
        if verbose and (epoch + 1) % v_freq == 0:
            print("Epoch #{}: Generative Loss: {}, Discriminative Loss: {}".format(epoch + 1, g_loss[-1], d_loss[-1]))
    return d_loss, g_loss, xx, yy

d_loss, g_loss ,xx,yy= train(GAN, G, D, verbose=True)

HBox(children=(IntProgress(value=0), HTML(value=’’)))

Epoch #30: Generative Loss: 4.016930103302002, Discriminative Loss: 0.05247233808040619 Epoch #60: Generative Loss: 4.552446365356445, Discriminative Loss: 0.03850032016634941 Epoch #90: Generative Loss: 4.267617702484131, Discriminative Loss: 0.12488271296024323

自動化echo

損失函數

ax = pd.DataFrame(
    {
        'Generative Loss': g_loss,
        'Discriminative Loss': d_loss,
    }
).plot(title='Training loss', logy=True)
ax.set_xlabel("Epochs")
ax.set_ylabel("Loss")

Text(0, 0.5, ‘Loss’)

new_data = xx[num:num*2+1]
#pd.DataFrame(new_data)

#pd.DataFrame(ss.inverse_transform(xx[0:492]))
#pd.DataFrame(ss.inverse_transform(xx))

one class svm

from sklearn import svm

clf = svm.OneClassSVM(kernel='rbf', gamma='auto').fit(xx[0:246])

origin = pd.DataFrame(clf.score_samples(xx[0:246]))
origin.describe()

new = pd.DataFrame(clf.score_samples(xx[246:493]))
new.describe()

occ = pd.concat([pd.DataFrame(new[0] < origin[0].min()),pd.DataFrame(new[0] > origin[0].max())], axis=1)
occ['ava'] = pd.DataFrame(occ.iloc[:,1:2] == occ.iloc[:,0:1])
occ

err = sum(occ['ava'] == False)/len(occ['ava'])
err

0.0