input_dim = df_train.shape[1]
encoding_dim = input_dim
input_layer = Input(shape=(input_dim, ))
encoder = Dense(encoding_dim, activation="tanh",
                activity_regularizer=regularizers.l1(10e-5))(input_layer)
encoder = Dense(int(encoding_dim / 2), activation="relu")(encoder)
decoder = Dense(int(encoding_dim / 2), activation='tanh')(encoder)
decoder = Dense(input_dim, activation='relu')(decoder)
autoencoder = Model(inputs=input_layer, outputs=decoder)

autoencoder.compile(optimizer='adadelta', loss = 'binary_crossentropy')

checkpointer = ModelCheckpoint(filepath="model.h5",
                               verbose = 1,
                               save_best_only=True)

autoencoder.fit(df_train,
                df_train,
                epochs = 1,
                batch_size=128,
                shuffle=True,
                #validation_data=(df_test,df_test),
                callbacks=[TensorBoard(log_dir='../tensorboard-log-directory/')])

from keras import models
model = models.load_model("model.h5")
np_test = df_test.to_numpy()
np_test = np_test.reshape()
prediction = model.predict(np_test)