def train_model_and_evaluate(lods, out_data, seed=10):
np.random.seed(seed)
tf.compat.v1.set_random_seed(seed)
n_knob_cols = len(lods.config['COLS_KNOBS'])
nn_params = HYPER_PARAMS['nn_params']
kpca_params = HYPER_PARAMS['kpca_params']
tmp_trainval = lods.trainval
tmp_shared_trainval = lods.shared_trainval
if N_TRAIN_PER_JOB != -1:
tmp_trainval = lods.trainval.get_x(N_TRAIN_PER_JOB)
if N_SHARED_TRAIN_PER_JOB != -1:
tmp_shared_trainval = lods.shared_trainval.get_x(
N_SHARED_TRAIN_PER_JOB)
if tmp_trainval is not None:
logging.info("shape of remaining trainval (X): {}".format(
tmp_trainval.X.shape))
else:
logging.info("tmp_trainval is None (perhaps because of get_x(0))")
if tmp_shared_trainval is not None:
logging.info("shape of remaining shared trainval (X): {}".format(
tmp_shared_trainval.X.shape))
else:
logging.info(
"tmp_shared_trainval is None (perhaps because of get_x(0))")
if tmp_trainval is None:
# in case we're invoking dataset.get_x(0)
ds_train = tmp_shared_trainval
else:
ds_train = tmp_trainval + tmp_shared_trainval
X_train = np.hstack([ds_train.a, ds_train.X, ds_train.Y])
y_train = ds_train.targets.ravel()
logging.info("Fitting KPCA on data of shape: {}".format(X_train.shape))
# Make PCA and fit on loaded data
fit_t = time.time()
pca = KernelPCA(**kpca_params)
pca.altered_centroids = None
logging.info("Fitting KPCA on data of shape: {}".format(ds_train.Y.shape))
if ENCODING_STRATEGY == 'shared':
shared_train = lods.shared_trainval.get_x(N_OBS)
pca.fit(ds_train.Y)
encods_shared = pca.transform(shared_train.Y)
centroids = compute_centroids(encods_shared, shared_train.a)
else:
encods = pca.fit_transform(ds_train.Y)
centroids = compute_centroids(encods, ds_train.a)
pca.centroids = centroids # thisis why I love Python! :-)
fit_t = time.time() - fit_t
logging.info("KPCA fitting time is: {} minutes and {} seconds".format(
fit_t // 60, int(fit_t / 60)))
# Adjust the X vector by transforming Y into job's centroid
X, y = translate_X_y(X_train, y_train, pca.centroids, n_knob_cols)
# Make and fit a NN Regressor
logging.info("Fitting regressor on data of shapes: {}, {}".format(
X.shape, y.shape))
reg = NNregressor(with_calibration=True,
**nn_params,
v1_compat_mode=True,
random_state=seed)
reg.fit(X, y, log_time=True)
training_mape = reg.MAPE(X, y)
logging.info("Training Error: {:.2f}%".format(training_mape))
out_data['training_errs'].append(training_mape)
if ENCODING_STRATEGY == 'shared':
observed_traces = lods.shared_traincomplement.get_x(N_OBS)
else:
observed_traces = lods.traincomplement.get_x(N_OBS)
logging.info("observed_traces description: ")
observed_traces.describe()
observed_traces_slices = observed_traces.slice_by_job_id(
alias_to_id=lods.alias_to_id)
test_aliases = sorted(list(set(lods.test.a.ravel())))
for test_job in observed_traces_slices:
evaluate(test_job, pca, reg, lods, observed_traces,
observed_traces_slices, out_data, test_aliases)
out_data['regressors'].append(reg.get_persist_info())
persist_data(copyDict(out_data), DATA_FNAME)
