keras搭建基于自动编码器的异常检测技术进行欺诈识别（二）

df = pd.read_csv('creditcard.csv')
x = df[df.columns[1:30]].to_numpy()
y = df[df.columns[30]].to_numpy()
# prepare data
df = pd.concat([pd.DataFrame(x), pd.DataFrame({'anomaly': y})], axis=1)
normal_events = df[df['anomaly'] == 0]
abnormal_events = df[df['anomaly'] == 1]
normal_events = normal_events.loc[:, normal_events.columns != 'anomaly']
abnormal_events = abnormal_events.loc[:, abnormal_events.columns != 'anomaly']
# scaling
scaler = preprocessing.MinMaxScaler()
scaler.fit(df.drop('anomaly', 1))
scaled_data = scaler.transform(normal_events)
# 80% percent of dataset is designated to training
train_data, test_data = model_selection.train_test_split(scaled_data, test_size=0.2)
n_features = x.shape[1]
# model
encoder = models.Sequential(name='encoder')
encoder.add(layer=layers.Dense(units=20, activation=activations.relu, input_shape=[n_features]))
encoder.add(layers.Dropout(0.1))
encoder.add(layer=layers.Dense(units=10, activation=activations.relu))
encoder.add(layer=layers.Dense(units=5, activation=activations.relu))
decoder = models.Sequential(name='decoder')
decoder.add(layer=layers.Dense(units=10, activation=activations.relu, input_shape=[5]))
decoder.add(layer=layers.Dense(units=20, activation=activations.relu))
decoder.add(layers.Dropout(0.1))
decoder.add(layer=layers.Dense(units=n_features, activation=activations.sigmoid))
autoencoder = models.Sequential([encoder, decoder])
autoencoder.compile(
loss=losses.MSE,
optimizer=optimizers.Adam(),
metrics=[metrics.mean_squared_error])
# train model
es = EarlyStopping(monitor='val_loss', min_delta=0.00001, patience=20, restore_best_weights=True)
history = autoencoder.fit(x=train_data, y=train_data, epochs=100, verbose=1, validation_data=[test_data, test_data], callbacks=[es])
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('Model Loss')
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.legend(['Train', 'Test'], loc='upper left')
plt.show()

train_predicted_x = autoencoder.predict(x=train_data)
train_events_mse = losses.mean_squared_error(train_data, train_predicted_x)
cut_off = np.percentile(train_events_mse, 95)

plot_samples = 100
# normal event
real_x = test_data[:plot_samples].reshape(plot_samples, n_features)
predicted_x = autoencoder.predict(x=real_x)
normal_events_mse = losses.mean_squared_error(real_x, predicted_x)
normal_events_df = pd.DataFrame({
'mse': normal_events_mse,
'n': np.arange(0, plot_samples),
'anomaly': np.zeros(plot_samples)})
# abnormal event
abnormal_x = scaler.transform(abnormal_events)[:plot_samples].reshape(plot_samples, n_features)
predicted_x = autoencoder.predict(x=abnormal_x)
abnormal_events_mse = losses.mean_squared_error(abnormal_x, predicted_x)
abnormal_events_df = pd.DataFrame({
'mse': abnormal_events_mse,
'n': np.arange(0, plot_samples),
'anomaly': np.ones(plot_samples)})
mse_df = pd.concat([normal_events_df, abnormal_events_df])
plot = sns.lineplot(x=mse_df.n, y=mse_df.mse, hue=mse_df.anomaly)
line = lines.Line2D(
xdata=np.arange(0, plot_samples),
ydata=np.full(plot_samples, cut_off),
color='#CC2B5E',
linewidth=1.5,
linestyle='dashed')
plot.add_artist(line)
plt.title('Threshlold: {threshold}'.format(threshold=cut_off))
plt.show()