def init_parameters(self,
random_state=123,
input_stage=1,
target_stage=1,
train_size=0.5,
simulate_batch_size=200):
self.input_stage = input_stage
self.target_stage = target_stage
self.train_size = train_size
self.random_state = random_state
bae_set_seed(random_state)
liveline_datastream = Liveline_DataStream(output_stage=target_stage,
input_stage=input_stage,
train_size=train_size)
self.datastream = liveline_datastream
self.x_train = liveline_datastream._quantities["train"]
self.x_test = liveline_datastream._quantities["test"]
self.x_ood = liveline_datastream._quantities["ood"]
self.y_train = liveline_datastream._target["train"]
self.y_test = liveline_datastream._target["test"]
self.y_ood = liveline_datastream._target["ood"]
# for simulation
self.datastream_simulate = DataStreamMET4FOF()
self.datastream_simulate.set_data_source(
quantities=np.concatenate((self.x_test, self.x_ood)))
self.simulate_batch_size = simulate_batch_size
from baetorch.baetorch.plotting import *
from baetorch.baetorch.util.seed import bae_set_seed
from baetorch.baetorch.util.misc import save_csv_pd
from _train_models_images import train_model_images
import pandas as pd
#set seed for reproduciliblity
bae_set_seed(2020)
use_cuda = torch.cuda.is_available()
print("USE CUDA:" + str(use_cuda))
#----STATIC GLOBAL PARAMETERS---
#available choices -- static
decoder_sigma_choices = ["infer", "dense"]
latent_dim_multiplier_choices = [0.2, 0.5, 1, 2, 5]
capacity_multiplier_choices = [0.2, 0.5, 1, 2, 5]
#set likelihood and model hyperparameters
latent_dim_multiplier = latent_dim_multiplier_choices[
2] #for easy scaling of latent dims & capacity
capacity_multiplier = capacity_multiplier_choices[2]
decoder_sigma_choice = decoder_sigma_choices[
1] #aleatoric uncertainty, unused in this experiment runs
num_epoch_sigma = 0 #aleatoric uncertainty, unused
#Change here:
model_types_choices = ["vanilla", "ensemble", "mcdropout", "vi", "vae"]
likelihood_choices = ["bernoulli", "cbernoulli", "gaussian_none"]
train_set_choices = ["FashionMNIST", "MNIST", "SVHN", "CIFAR"]
num_epoch_mu = 1 #number of training epochs
import torch import numpy as np from sklearn.preprocessing import MinMaxScaler import matplotlib.pyplot as plt from baetorch.baetorch.util.convert_dataloader import convert_dataloader from baetorch.baetorch.lr_range_finder import run_auto_lr_range_v2 from baetorch.baetorch.models.bae_hydra import BAE_Hydra, Hydra_Autoencoder from baetorch.baetorch.models.base_autoencoder import Encoder, DenseLayers, infer_decoder from baetorch.baetorch.models.cholesky_layer import CholLayer from baetorch.baetorch.plotting import plot_contour, get_grid2d_latent from baetorch.baetorch.util.seed import bae_set_seed bae_set_seed(321) #=========load data from sklearn.datasets import make_blobs # iris_data = load_iris() # x_train = iris_data['data'] # y_train = iris_data['target'] # x_train, y_train = make_moons(n_samples=500) x_train, y_train = make_blobs(n_samples=100, centers=5, n_features=2) x_train = MinMaxScaler().fit_transform(x_train) x_train_torch = torch.tensor(x_train).float() y_train_torch = torch.tensor(y_train).int() #=======AutoEncoder latent_dim = 100
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
from agentMET4FOF_ml_extension.agentMET4FOF.agentMET4FOF.streams import DataStreamMET4FOF
from baetorch.baetorch.util.seed import bae_set_seed
from util.calc_outlier import get_num_outliers_df
bae_set_seed(1231)
class Liveline_DataStream(DataStreamMET4FOF):
def __init__(self,
dataset_folder="multi-stage-dataset/",
output_stage=1,
input_stage=1,
upper_quartile=80,
train_size=0.5,
apply_scaling=True):
lower_quartile = 100 - upper_quartile
df = pd.read_csv(dataset_folder + "continuous_factory_process.csv")
#drop columns
df = df.drop(["time_stamp"], axis=1)
column_names = df.columns
# filter Y columns
if output_stage == 1:
Y_df_actual = df[[