def __init__(
self,
space: Optional[Dict] = None,
metric: Optional[str] = None,
mode: Optional[str] = None,
points_to_evaluate: Optional[List[Dict]] = None,
n_initial_points: int = 20,
random_state_seed: Optional[int] = None,
gamma: float = 0.25,
max_concurrent: Optional[int] = None,
use_early_stopped_trials: Optional[bool] = None,
):
assert hpo is not None, (
"HyperOpt must be installed! Run `pip install hyperopt`.")
if mode:
assert mode in ["min", "max"], "`mode` must be 'min' or 'max'."
from hyperopt.fmin import generate_trials_to_calculate
super(HyperOptSearch,
self).__init__(metric=metric,
mode=mode,
max_concurrent=max_concurrent,
use_early_stopped_trials=use_early_stopped_trials)
self.max_concurrent = max_concurrent
# hyperopt internally minimizes, so "max" => -1
if mode == "max":
self.metric_op = -1.
elif mode == "min":
self.metric_op = 1.
if n_initial_points is None:
self.algo = hpo.tpe.suggest
else:
self.algo = partial(hpo.tpe.suggest,
n_startup_jobs=n_initial_points)
if gamma is not None:
self.algo = partial(self.algo, gamma=gamma)
if points_to_evaluate is None:
self._hpopt_trials = hpo.Trials()
self._points_to_evaluate = 0
else:
assert isinstance(points_to_evaluate, (list, tuple))
self._hpopt_trials = generate_trials_to_calculate(
points_to_evaluate)
self._hpopt_trials.refresh()
self._points_to_evaluate = len(points_to_evaluate)
self._live_trial_mapping = {}
if random_state_seed is None:
self.rstate = np.random.RandomState()
else:
self.rstate = np.random.RandomState(random_state_seed)
self.domain = None
if isinstance(space, dict) and space:
resolved_vars, domain_vars, grid_vars = parse_spec_vars(space)
if domain_vars or grid_vars:
logger.warning(
UNRESOLVED_SEARCH_SPACE.format(par="space",
cls=type(self)))
space = self.convert_search_space(space)
self.domain = hpo.Domain(lambda spc: spc, space)
def __init__(self,
space,
max_concurrent=10,
reward_attr="episode_reward_mean",
points_to_evaluate=None,
**kwargs):
_import_hyperopt()
assert hpo is not None, "HyperOpt must be installed!"
from hyperopt.fmin import generate_trials_to_calculate
assert type(max_concurrent) is int and max_concurrent > 0
self._max_concurrent = max_concurrent
self._reward_attr = reward_attr
self.algo = hpo.tpe.suggest
self.domain = hpo.Domain(lambda spc: spc, space)
if points_to_evaluate is None:
self._hpopt_trials = hpo.Trials()
self._points_to_evaluate = 0
else:
assert type(points_to_evaluate) == list
self._hpopt_trials = generate_trials_to_calculate(
points_to_evaluate)
self._hpopt_trials.refresh()
self._points_to_evaluate = len(points_to_evaluate)
self._live_trial_mapping = {}
self.rstate = np.random.RandomState()
super(HyperOptSearch, self).__init__(**kwargs)
def get_iter(fn, space, algo, max_evals, trials=None, rstate=None,
pass_expr_memo_ctrl=None,
catch_eval_exceptions=False,
verbose=0,
points_to_evaluate=None,
max_queue_len=1,
show_progressbar=False,
):
if rstate is None:
env_rseed = os.environ.get('HYPEROPT_FMIN_SEED', '')
if env_rseed:
rstate = np.random.RandomState(int(env_rseed))
else:
rstate = np.random.RandomState()
if trials is None:
if points_to_evaluate is None:
trials = base.Trials()
else:
assert type(points_to_evaluate) == list
trials = generate_trials_to_calculate(points_to_evaluate)
domain = base.Domain(fn, space,
pass_expr_memo_ctrl=pass_expr_memo_ctrl)
rval = FMinIter(algo, domain, trials, max_evals=max_evals,
rstate=rstate,
verbose=verbose,
max_queue_len=max_queue_len,
show_progressbar=show_progressbar)
rval.catch_eval_exceptions = catch_eval_exceptions
return rval
def __init__(self,
space,
max_concurrent=10,
reward_attr="episode_reward_mean",
points_to_evaluate=None,
**kwargs):
assert hpo is not None, "HyperOpt must be installed!"
from hyperopt.fmin import generate_trials_to_calculate
assert type(max_concurrent) is int and max_concurrent > 0
self._max_concurrent = max_concurrent
self._reward_attr = reward_attr
self.algo = hpo.tpe.suggest
self.domain = hpo.Domain(lambda spc: spc, space)
if points_to_evaluate is None:
self._hpopt_trials = hpo.Trials()
self._points_to_evaluate = 0
else:
assert type(points_to_evaluate) == list
self._hpopt_trials = generate_trials_to_calculate(
points_to_evaluate)
self._hpopt_trials.refresh()
self._points_to_evaluate = len(points_to_evaluate)
self._live_trial_mapping = {}
self.rstate = np.random.RandomState()
super(HyperOptSearch, self).__init__(**kwargs)
def generate_trial(isDef=False):
'''
Generate an initial Trial object.
Inputs:
isDef: Bool, if true initial guess defined
Returns:
empty or pre-defined trials object
'''
# Modify pts to have a different initial guess
# NOTE: Hyperopt reads dict keys and values separately,
# and organizes keys in alphabetical order. While values order
# remains the same. Thus, place keys in alphabetical order.
if isDef:
pts = [{
'aint_dense': 1,
'batch_size': 0,
'nint_dense': 2,
'optim_type': 0,
'sint_dense': 0,
'train_loss': 0
}]
new_trials = generate_trials_to_calculate(pts)
else:
new_trials = Trials()
return new_trials
def process_meta(self, fn_name, space, algo, max_evals):
fn = getattr(self, fn_name)
if fn_name == 'xgb_reg':
trials = generate_trials_to_calculate([self.meta_param_xgb_reg()])
else:
trials = generate_trials_to_calculate([self.meta_param_xgb_clf()])
try:
result = fmin(fn=fn,
space=space,
algo=algo,
max_evals=max_evals,
trials=trials)
except Exception as e:
return {'status': STATUS_FAIL, 'exception': str(e)}
return trials
def __init__(self,
space,
max_concurrent=10,
reward_attr=None,
metric="episode_reward_mean",
mode="max",
points_to_evaluate=None,
n_initial_points=20,
random_state_seed=None,
gamma=0.25,
**kwargs):
assert hpo is not None, "HyperOpt must be installed!"
from hyperopt.fmin import generate_trials_to_calculate
assert type(max_concurrent) is int and max_concurrent > 0
assert mode in ["min", "max"], "`mode` must be 'min' or 'max'!"
if reward_attr is not None:
mode = "max"
metric = reward_attr
logger.warning(
"`reward_attr` is deprecated and will be removed in a future "
"version of Tune. "
"Setting `metric={}` and `mode=max`.".format(reward_attr))
self._max_concurrent = max_concurrent
self._metric = metric
# hyperopt internally minimizes, so "max" => -1
if mode == "max":
self._metric_op = -1.
elif mode == "min":
self._metric_op = 1.
if n_initial_points is None:
self.algo = hpo.tpe.suggest
else:
self.algo = partial(hpo.tpe.suggest,
n_startup_jobs=n_initial_points)
if gamma is not None:
self.algo = partial(self.algo, gamma=gamma)
self.domain = hpo.Domain(lambda spc: spc, space)
if points_to_evaluate is None:
self._hpopt_trials = hpo.Trials()
self._points_to_evaluate = 0
else:
assert type(points_to_evaluate) == list
self._hpopt_trials = generate_trials_to_calculate(
points_to_evaluate)
self._hpopt_trials.refresh()
self._points_to_evaluate = len(points_to_evaluate)
self._live_trial_mapping = {}
if random_state_seed is None:
self.rstate = np.random.RandomState()
else:
self.rstate = np.random.RandomState(random_state_seed)
super(HyperOptSearch, self).__init__(metric=self._metric,
mode=mode,
**kwargs)
def test_early_stop_no_progress_loss():
trials = generate_trials_to_calculate([{'x': -100}])
fmin(fn=lambda x: x,
space=hp.uniform("x", -5, 5),
algo=rand.suggest,
max_evals=500,
trials=trials,
early_stop_fn=no_progress_loss(10))
assert len(trials) == 10
def __init__(
self,
space=None,
metric=None,
mode=None,
points_to_evaluate=None,
n_initial_points=20,
random_state_seed=None,
gamma=0.25,
max_concurrent=None,
use_early_stopped_trials=None,
):
assert hpo is not None, (
"HyperOpt must be installed! Run `pip install hyperopt`.")
if mode:
assert mode in ["min", "max"], "`mode` must be 'min' or 'max'."
from hyperopt.fmin import generate_trials_to_calculate
super(HyperOptSearch, self).__init__(
metric=metric,
mode=mode,
max_concurrent=max_concurrent,
use_early_stopped_trials=use_early_stopped_trials)
self.max_concurrent = max_concurrent
# hyperopt internally minimizes, so "max" => -1
if mode == "max":
self.metric_op = -1.
elif mode == "min":
self.metric_op = 1.
if n_initial_points is None:
self.algo = hpo.tpe.suggest
else:
self.algo = partial(
hpo.tpe.suggest, n_startup_jobs=n_initial_points)
if gamma is not None:
self.algo = partial(self.algo, gamma=gamma)
if points_to_evaluate is None:
self._hpopt_trials = hpo.Trials()
self._points_to_evaluate = 0
else:
assert isinstance(points_to_evaluate, (list, tuple))
self._hpopt_trials = generate_trials_to_calculate(
points_to_evaluate)
self._hpopt_trials.refresh()
self._points_to_evaluate = len(points_to_evaluate)
self._live_trial_mapping = {}
if random_state_seed is None:
self.rstate = np.random.RandomState()
else:
self.rstate = np.random.RandomState(random_state_seed)
self.domain = None
if space:
self.domain = hpo.Domain(lambda spc: spc, space)
def process_xgb_clf(self, max_evals):
trials = generate_trials_to_calculate([self.meta_param_xgb_clf()])
try:
result = fmin(fn=self.xgb_clf,
space=xgb_para,
trials=trials,
algo=tpe.suggest,
max_evals=max_evals)
except Exception as e:
return {'status': STATUS_FAIL, 'exception': str(e)}
return result
def gen_trials(self):
'''
Generate an initial Trial object.
Redefine this function if you want custom guesses.
Returns:
trials: empty or pre-defined trials object
'''
# Modify pts to have a different initial guess
# NOTE: Hyperopt reads dict keys and values separately,
# and organizes keys in alphabetical order. While values order
# remains the same. Thus, place keys in alphabetical order.
if self.hps_guess is not None:
trials = generate_trials_to_calculate(self.hps_guess)
else:
trials = Trials()
return trials
def hyper_optimization(self, train_mask, val_mask):
def objective(hyperparams):
model = GCN({**self.params, **hyperparams, 'timer': self.timer}).to(self.device)
pred, pred_val, flag = model.train_predict(self.data, train_mask=train_mask, val_mask=val_mask)
if flag:
self.flag_end = True
score = accuracy_score(self.data.y[val_mask].cpu().numpy(), (pred_val.max(1)[1]).cpu().numpy())
return {'loss': -score, 'status': STATUS_OK, 'pred': pred.cpu().numpy(), 'flag': self.flag_end}
trials = generate_trials_to_calculate(self.points)
if self.timer.remain_time() < 5 or self.flag_end:
self.flag_end = True
return None, -1.0, None
best = fmin(fn=objective, space=self.space, trials=trials,
algo=tpe.suggest, max_evals=5, verbose=0,
timeout=self.timer.remain_time()-5)
hyperparams = space_eval(self.space, best)
best_score = -trials.best_trial['result']['loss']
pprint.pprint(hyperparams, width=1)
print('>>>>>>> ', best_score)
pred = trials.best_trial['result']['pred']
return pred, best_score, hyperparams
def _setup_hyperopt(self) -> None:
from hyperopt.fmin import generate_trials_to_calculate
if self._metric is None and self._mode:
# If only a mode was passed, use anonymous metric
self._metric = DEFAULT_METRIC
if self._points_to_evaluate is None:
self._hpopt_trials = hpo.Trials()
self._points_to_evaluate = 0
else:
assert isinstance(self._points_to_evaluate, (list, tuple))
for i in range(len(self._points_to_evaluate)):
config = self._points_to_evaluate[i]
self._convert_categories_to_indices(config)
# HyperOpt treats initial points as LIFO, reverse to get FIFO
self._points_to_evaluate = list(reversed(self._points_to_evaluate))
self._hpopt_trials = generate_trials_to_calculate(self._points_to_evaluate)
self._hpopt_trials.refresh()
self._points_to_evaluate = len(self._points_to_evaluate)
self.domain = hpo.Domain(lambda spc: spc, self._space)
def get_new_params(experiment: Experiment,
rstate,
algo=tpe.suggest,
n_points=1):
params = [{p.name: p.value
for p in result.params} for result in experiment.results]
trials = generate_trials_to_calculate(params)
trials.refresh()
space = convert_parameter_space(experiment.parameter_spaces)
domain = base.Domain(
lambda args: experiment.results[params.index(args)].value, space)
FMinIter(algo, domain, trials, rstate=rstate).serial_evaluate()
new_ids = trials.new_trial_ids(n_points)
new_points = algo(new_ids, domain, trials, rstate.randint(2**31 - 1))
new_params = [[
Parameter(name=k, value=v[0])
for k, v in point['misc']['vals'].items()
] for point in new_points]
if experiment.results:
experiment.best_params = [
Parameter(name=k, value=v[0])
for k, v in trials.best_trial['misc']['vals'].items()
]
return new_params
def main():
# Imports the dataset and labels and turns them into numpy arrays.
X = pd.read_csv('train_values.csv', index_col = 0).to_numpy()
y = np.array(pd.read_csv('train_labels.csv', index_col = 0).to_numpy().T[0])
# Preprocesses data (one hot or ordinal encoding)
X = preProcess(X, 'OneHotEncoding')
# Performs PCA on dataset for better visualizaion
print("Do you want to visualize dataset with PCA?\n")
pca_inp = input('(y/n): ').lower()
if pca_inp == 'y':
size = int(input("Define amount of samples to visualize with PCA: "))
pca = PCA(n_components = 2)
pca.fit(X)
PCX = pca.transform(X)
plt.scatter(PCX[:size,0], PCX[:size,1], c = y[:size])
plt.show()
print()
else:
print()
# Option to use entire dataset or a reduced set with a more balanced amount of each label.
print("Use reduced set?\n")
full = input('(y/n): ')
print()
# Create training set and test set
if full == 'y':
X1 = [X[i] for i in range(len(X)) if y[i] == 1]
X2 = [X[i] for i in range(len(X)) if y[i] == 2]
X3 = [X[i] for i in range(len(X)) if y[i] == 3]
y1 = [y[i] for i in range(len(y)) if y[i] == 1]
y2 = [y[i] for i in range(len(y)) if y[i] == 2]
y3 = [y[i] for i in range(len(y)) if y[i] == 3]
size = min(len(X1),len(X2),len(X3))
Xp = np.concatenate((X1[:size], X2[:size], X3[:size]))
yp = np.concatenate((y1[:size], y2[:size], y3[:size]))
train_X, test_X, train_y, test_y = train_test_split(
Xp, yp, test_size = 0.2)
else:
train_X, test_X, train_y, test_y = train_test_split(
X, y, test_size = 0.2, random_state=42)
# Initializes last_classifier variable.
last_classifier = None
# 'Front-end'
while True:
print("Choose the training model: ")
print(' - Network\n - GBM\n - LGBM\n - GridSearch\n - Hyperopt\n')
inp = input('>> ').lower()
print()
################################################################################################################################################################
if inp == 'network':
print('-- SkLearn MLP Classifier (neural network) --\n')
it = int(input('Define maximum number of iterations: '))
print()
layers = [int(x) for x in input("Define network architecture: ").replace(' ', '').split(',')]
print()
alpha = input("Define regularization term alpha (default = 0.0001): ")
if alpha == '':
alpha = 0.0001
print()
eps = input("Define stability term epsilon (default = 1e-8): ")
if eps == '':
eps = 0.00000001
print()
activation = input("Define activation function (default = 'relu'): ")
if activation == '':
activation = 'relu'
print()
l_rate = input("Define initial learning rate (default = 0.001): ")
if l_rate == '':
l_rate = 0.001
print()
solver = 'adam'
decay = input("Define learning rate decay (default = 'constant'): ")
if decay == '':
decay = 'constant'
print()
beta_1 = input("Define beta 1 (default = 0.999): ")
if beta_1 == '':
beta_1 = 0.999
print()
beta_2 = input("Define beta 2 (default = 0.999): ")
if beta_2 == '':
beta_2 = 0.999
print()
print("Want early stopping (default = False)?")
early = input('(y/n): ').lower()
if early == 'y':
early = True
else:
early = False
print()
print("Want warm start (default = False)?")
warm = input('(y/n): ').lower()
if early == 'y':
warm = True
else:
warm = False
print()
num = input("Define number of iterations without change, to declare convergence (default = 10): ")
if num == '':
num = 10
print()
tol = input("Finally, define the tolerance (default = 0.0001): ")
if tol == '':
tol = 0.0001
print('\n-- Training neural network --\n')
mlp = MLPClassifier(
hidden_layer_sizes = layers, max_iter = it, alpha = float(alpha), activation = activation,
learning_rate = decay, learning_rate_init = float(l_rate), verbose = True,
early_stopping = early, epsilon = float(eps), validation_fraction = 0.2, solver = solver,
beta_1 = float(beta_1), beta_2 = float(beta_2), warm_start = warm, tol = float(tol), n_iter_no_change = int(num))
mlp.fit(train_X, train_y)
print()
preds = mlp.predict(train_X)
print('Results on training set:')
print(classification_report(train_y, preds, zero_division = 1))
print('Micro averaged F1 Score: ', f1_score(train_y, preds, average='micro'), '\n')
print('-'*80, '\n')
preds = mlp.predict(test_X)
print('Results on cross-validation set:')
print(classification_report(test_y, preds, zero_division = 1))
print('Micro averaged F1 Score: ', f1_score(test_y, preds, average='micro'), '\n')
last_classifier = mlp
winsound.Beep(frequency, duration)
print('='*80, '\n')
################################################################################################################################################################
elif inp == 'gbm':
print('-- SkLearn GBM Classifier --\n')
learning_rate = input("Define learning rate (default = 0.1): ")
if learning_rate == '':
learning_rate = 0.1
print()
n_estimators = input("Define number of estimators (default = 100): ")
if n_estimators == '':
n_estimators = 100
print()
subsample = input("Define subsample percentage (default = 100 %): ")
if subsample == '' or float(subsample) > 100:
subsample = 100
print()
min_samples_split = input("Define minimum number of samples to split node (default = 2): ")
if min_samples_split == '':
min_samples_split = 2
print()
min_samples_leaf = input("Define minimum number of samples to make node a leaf (default = 1): ")
if min_samples_leaf == '':
min_samples_leaf = 1
print()
max_depth = input("Define maximum depth of individual estimators (default = 3): ")
if max_depth == '':
max_depth = 3
print()
print("Do you want cross-validation for early-stopping?")
n_iter_no_change = input("(y/n): ")
if n_iter_no_change == 'y':
n_iter_no_change = 15
else:
n_iter_no_change = None
print("\n-- Training GBM --\n")
gbm = GradientBoostingClassifier(
learning_rate = float(learning_rate), n_estimators = int(n_estimators), subsample = float(subsample)/100,
min_samples_split = int(min_samples_split), min_samples_leaf = int(min_samples_leaf), max_depth = int(max_depth),
verbose = True, n_iter_no_change = n_iter_no_change)
gbm.fit(train_X, train_y)
preds = gbm.predict(train_X)
print('Results on training set:')
print(classification_report(train_y, preds, zero_division = 1))
print('Micro averaged F1 Score: ', f1_score(train_y, preds, average='micro'), '\n')
print('-'*80, '\n')
preds = gbm.predict(test_X)
print('Results on cross-validation set:')
print(classification_report(test_y, preds, zero_division = 1))
print('Micro averaged F1 Score: ', f1_score(test_y, preds, average='micro'), '\n')
last_classifier = gbm
winsound.Beep(frequency, duration)
print('='*80, '\n')
################################################################################################################################################################
elif inp == 'lgbm':
print('-- SkLearn LightGBM API --\n')
max_depth = input('Define max depth of tree (default = -1): ')
if max_depth == '':
max_depth = -1
print()
min_data_in_leaf = input('Define min data in leaf (default = 20): ')
if min_data_in_leaf == '':
min_data_in_leaf = 20
print()
feature_fraction = input('Define feature fraction for random subsampling (default = 1): ')
if feature_fraction == '' or not (0 < float(feature_fraction) <= 1):
feature_fraction = 1
print()
bagging_freq = 0
bagging_fraction = input('Define bagging fraction for random sampling (default = 1): ')
if bagging_fraction == '' or not (0 < float(bagging_fraction) <= 1):
bagging_fraction = 1
print()
if float(bagging_fraction) < 1:
bagging_freq = input('Define frequecy for bagging (default = 0): ')
if bagging_freq == '':
bagging_freq = 0
print()
alpha = input('Define regularization alpha (default = 0): ')
if alpha == '':
alpha = 0
print()
lamb = input('Define regularization lambda (default = 0): ')
if lamb == '':
lamb = 0
print()
min_gain_to_split = input('Define min gain to split node (default = 0): ')
if min_gain_to_split == '':
min_gain_to_split = 0
print()
objective = input('Define objective (default = softmax)\n\nOptions: \n- num_class\n- softmax\n- ovr\n\n>> ').lower()
if objective == '':
objective = 'softmax'
print()
num_boost_round = input('Define number of iterations (default = 100): ')
if num_boost_round == '':
num_boost_round = 100
print()
l_rate = input('Define learning rate (default = 0.1): ')
if l_rate == '':
l_rate = 0.1
print()
num_leaves = input('Define max number of leaves in a tree (default = 31): ')
if num_leaves == '':
num_leaves = 31
print()
max_bin = input('Define max number of bins (default = 255): ')
if max_bin == '':
max_bin = 255
print()
min_sum_hessian_in_leaf = input('Define min hessian in leaf (default = 0.001): ')
if min_sum_hessian_in_leaf == '':
min_sum_hessian_in_leaf = 0.001
print()
print('Compensate for unbalanced dataset?')
is_unbalance = input('(y/n): ').lower()
if is_unbalance == 'y':
is_unbalance = True
else:
is_unbalance = False
print()
print('-- Training Light GBM --\n')
gbm = lgb.LGBMClassifier(max_depth = int(max_depth),
min_data_in_leaf = int(min_data_in_leaf),
feature_fraction = float(feature_fraction),
bagging_fraction = float(bagging_fraction),
bagging_freq = int(bagging_freq),
lambda_l1 = float(alpha),
lambda_l2 = float(lamb),
min_gain_to_split = float(min_gain_to_split),
objective = objective,
num_boost_round = int(num_boost_round),
learning_rate = float(l_rate),
num_leaves = int(num_leaves),
gpu_use_dp = True,
num_threads = 2,
num_class = 3,
is_unbalance = is_unbalance,
verbosity = 10,
max_bin = int(max_bin),
min_sum_hessian_in_leaf = float(min_sum_hessian_in_leaf),
)
warnings.filterwarnings("ignore")
gbm.fit(train_X, train_y)
warnings.filterwarnings("default")
preds = gbm.predict(train_X)
print('Results on training set:')
print(classification_report(train_y, preds, zero_division = 1))
print('Micro averaged F1 Score: ', f1_score(train_y, preds, average='micro'), '\n')
print('-'*80, '\n')
preds = gbm.predict(test_X)
print('Results on cross-validation set:')
print(classification_report(test_y, preds, zero_division = 1))
print('Micro averaged F1 Score: ', f1_score(test_y, preds, average='micro'), '\n')
last_classifier = gbm
winsound.Beep(frequency, duration)
print('='*80, '\n')
################################################################################################################################################################
elif inp == 'gridsearch':
print('-- Random GridSearchCV on LightGBM classifier --\n')
iters = input('Define number of iterations (default = 10): ')
if iters == '':
iters = 10
print()
cv = input('Define number of CV (default = 2): ')
if cv == '':
cv = 2
print()
param_distributions = {
'max_depth': [-1,10,30,60,100,200],
'min_data_in_leaf': [4,8,16,32,64,128],
'feature_fraction': [0.1,0.25,0.5,0.75,1],
'bagging_fraction': [0.1,0.25,0.5,0.75,1],
'bagging_freq': [0,2,8,32,128],
'lambda_l1': [0,0.1,1,2,4,175,512,1000],
'lambda_l2': [0,0.1,1,2,4,175,512,1000],
'min_gain_to_split': [0,0.01,0.03,0.1,0.3,0.5,0.9,1],
'num_boost_round': [100, 500, 1000, 2500, 5000, 10000, 15000, 20000],
'learning_rate': [0.5, 0.25, 0.1, 0.05, 0.01, 0.005, 0.001, 0.0005, 0.0001],
'num_leaves': [10, 31, 62, 124, 200, 500, 750, 1000],
'objective': ['softmax'],
'gpu_use_dp': [True],
'num_threads': [1],
'num_class': [3],
'max_bin': [128, 256, 512, 1024, 2048, 3000, 4000, 5000, 6000]
}
print('-- Finding best parameters --\n')
rSearch = RandomizedSearchCV(estimator = lgb.LGBMClassifier(), param_distributions = param_distributions, scoring = 'f1_micro', n_jobs = 2,
cv = int(cv), verbose = 10, n_iter = int(iters))
warnings.filterwarnings("ignore")
rSearch.fit(train_X, train_y)
warnings.filterwarnings("default")
print()
print('Best parameters:')
print(rSearch.best_params_, '\n')
print('Score:')
print(rSearch.best_score_, '\n')
winsound.Beep(frequency, duration)
print('='*80, '\n')
################################################################################################################################################################
elif inp == 'hyperopt':
print('-- Bayesian Optimization on LightGBM classifier (with Hyperopt) --\n')
iters = input('Define number of evaluations (default = 50): ')
if iters == '':
iters = 50
print()
def objective_fun(space):
print()
warnings.filterwarnings('ignore')
model = lgb.LGBMClassifier(**space)
accuracy = cross_val_score(model, X, y, cv = 3, scoring = 'f1_micro').mean()
warnings.filterwarnings('default')
return {'loss': - accuracy, 'status': STATUS_OK}
param_space = {
'max_depth': 0,
'min_data_in_leaf': scope.int(hp.quniform('min_data_in_leaf', 1, 5000, 1)),
'feature_fraction': hp.uniform('feature_fraction', 0, 1),
'bagging_fraction': hp.uniform('bagging_fraction', 0, 1),
'bagging_freq': scope.int(hp.quniform('bagging_freq', 0, 100 ,1)),
'lambda_l1': hp.uniform('lambda_l1', 0, 10000),
'lambda_l2': hp.uniform('lambda_l2', 0, 10000),
'min_gain_to_split': hp.uniform('min_gain_to_split', 0, 11),
'num_boost_round': scope.int(hp.quniform('num_boost_round', 100, 20000, 1)),
'learning_rate': hp.uniform('learning_rate', 0.000001, 1),
'num_leaves': scope.int(hp.quniform('num_leaves', 2, 2000, 1)),
'objective': 'softmax',
'gpu_use_dp': True,
'num_threads': 2,
'num_class': 3,
'max_bin': scope.int(hp.quniform('max_bin', 32, 4096, 1)),
'min_sum_hessian_in_leaf': hp.uniform('min_sum_hessian_in_leaf', 0, 5)
}
param_init_trials = {
'max_depth': 0,
'min_data_in_leaf': 40,
'feature_fraction': 0.5,
'bagging_fraction': 0.9,
'bagging_freq': 1,
'lambda_l1': 0,
'lambda_l2': 10,
'min_gain_to_split': 0,
'num_boost_round': 10000,
'learning_rate': 0.1,
'num_leaves': 31,
'objective': 'softmax',
'gpu_use_dp': True,
'num_threads': 2,
'num_class': 3,
'max_bin': 256,
'min_sum_hessian_in_leaf': 0.1
}
trials = generate_trials_to_calculate([param_init_trials])
best = fmin(fn = objective_fun, space = param_space,
algo = tpe.suggest, max_evals = int(iters),
trials = trials)
print()
print(best, '\n')
input()
################################################################################################################################################################
elif last_classifier != None:
# Decides if wants to submit
print('Want to submit?')
inp = input('(y/n): ').lower()
print()
if inp == 'y':
# Decides if wants to fit classifier again for the entirety of the dataset
print('Want to fit for entire dataset?')
inp = input('(y/n): ').lower()
print()
if inp == 'y':
print('-- Training the last classifier --\n')
warnings.filterwarnings("ignore")
last_classifier.fit(X, y)
warnings.filterwarnings("default")
print()
submit(last_classifier)
return
else:
pass
def main():
# Imports the dataset and labels and turns them into numpy arrays.
X = pd.read_csv('train_values.csv', index_col = 0).to_numpy()
y = np.array(pd.read_csv('train_labels.csv', index_col = 0).to_numpy().T[0])
# Preprocesses data (one hot or ordinal encoding)
X = preProcess(X, 'OneHotEncoding')
# Performs PCA on dataset for better visualizaion
print("Do you want to visualize dataset with PCA?\n")
pca_inp = input('(y/n): ').lower()
if pca_inp == 'y':
size = int(input("Define amount of samples to visualize with PCA: "))
pca = PCA(n_components = 2)
pca.fit(X)
PCX = pca.transform(X)
plt.scatter(PCX[:size,0], PCX[:size,1], c = y[:size])
plt.show()
print()
else:
print()
# Option to use entire dataset or a reduced set with a more balanced amount of each label.
print("Use reduced set?\n")
full = input('(y/n): ')
print()
# Create training set and test set
if full == 'y':
X1 = [X[i] for i in range(len(X)) if y[i] == 1]
X2 = [X[i] for i in range(len(X)) if y[i] == 2]
X3 = [X[i] for i in range(len(X)) if y[i] == 3]
y1 = [y[i] for i in range(len(y)) if y[i] == 1]
y2 = [y[i] for i in range(len(y)) if y[i] == 2]
y3 = [y[i] for i in range(len(y)) if y[i] == 3]
size = min(len(X1),len(X2),len(X3))
Xp = np.concatenate((X1[:size], X2[:size], X3[:size]))
yp = np.concatenate((y1[:size], y2[:size], y3[:size]))
train_X, test_X, train_y, test_y = train_test_split(
Xp, yp, test_size = 0.2)
else:
train_X, test_X, train_y, test_y = train_test_split(
X, y, test_size = 0.2, random_state=42)
# Initializes last_classifier variable.
last_classifier = None
# 'Front-end'
while True:
print("Choose the training model: ")
print(' - LGBM\n - GridSearch\n - Hyperopt\n - Evolve\n')
inp = input('>> ').lower()
print()
################################################################################################################################################################
if inp == 'lgbm':
print('-- SkLearn LightGBM API --\n')
max_depth = input('Define max depth of tree (default = -1): ')
if max_depth == '':
max_depth = -1
print()
min_data_in_leaf = input('Define min data in leaf (default = 20): ')
if min_data_in_leaf == '':
min_data_in_leaf = 20
print()
feature_fraction = input('Define feature fraction for random subsampling (default = 1): ')
if feature_fraction == '' or not (0 < float(feature_fraction) <= 1):
feature_fraction = 1
print()
bagging_freq = 0
bagging_fraction = input('Define bagging fraction for random sampling (default = 1): ')
if bagging_fraction == '' or not (0 < float(bagging_fraction) <= 1):
bagging_fraction = 1
print()
if float(bagging_fraction) < 1:
bagging_freq = input('Define frequecy for bagging (default = 0): ')
if bagging_freq == '':
bagging_freq = 0
print()
alpha = input('Define regularization alpha (default = 0): ')
if alpha == '':
alpha = 0
print()
lamb = input('Define regularization lambda (default = 0): ')
if lamb == '':
lamb = 0
print()
min_gain_to_split = input('Define min gain to split node (default = 0): ')
if min_gain_to_split == '':
min_gain_to_split = 0
print()
objective = input('Define objective (default = softmax)\n\nOptions: \n- num_class\n- softmax\n- ovr\n\n>> ').lower()
if objective == '':
objective = 'softmax'
print()
num_boost_round = input('Define number of iterations (default = 100): ')
if num_boost_round == '':
num_boost_round = 100
print()
l_rate = input('Define learning rate (default = 0.1): ')
if l_rate == '':
l_rate = 0.1
print()
num_leaves = input('Define max number of leaves in a tree (default = 31): ')
if num_leaves == '':
num_leaves = 31
print()
max_bin = input('Define max number of bins (default = 255): ')
if max_bin == '':
max_bin = 255
print()
min_sum_hessian_in_leaf = input('Define min hessian in leaf (default = 0.001): ')
if min_sum_hessian_in_leaf == '':
min_sum_hessian_in_leaf = 0.001
print()
print('Compensate for unbalanced dataset?')
is_unbalance = input('(y/n): ').lower()
if is_unbalance == 'y':
is_unbalance = True
else:
is_unbalance = False
print()
print('-- Training Light GBM --\n')
gbm = lgb.LGBMClassifier(max_depth = int(max_depth),
min_data_in_leaf = int(min_data_in_leaf),
feature_fraction = float(feature_fraction),
bagging_fraction = float(bagging_fraction),
bagging_freq = int(bagging_freq),
lambda_l1 = float(alpha),
lambda_l2 = float(lamb),
min_gain_to_split = float(min_gain_to_split),
objective = objective,
num_boost_round = int(num_boost_round),
learning_rate = float(l_rate),
num_leaves = int(num_leaves),
gpu_use_dp = True,
num_threads = 2,
num_class = 3,
is_unbalance = is_unbalance,
verbosity = 10,
max_bin = int(max_bin),
min_sum_hessian_in_leaf = float(min_sum_hessian_in_leaf),
)
warnings.filterwarnings("ignore")
gbm.fit(train_X, train_y)
warnings.filterwarnings("default")
preds = gbm.predict(train_X)
print('Results on training set:')
print(classification_report(train_y, preds, zero_division = 1))
print('Micro averaged F1 Score: ', f1_score(train_y, preds, average='micro'), '\n')
print('-'*80, '\n')
preds = gbm.predict(test_X)
print('Results on cross-validation set:')
print(classification_report(test_y, preds, zero_division = 1))
print('Micro averaged F1 Score: ', f1_score(test_y, preds, average='micro'), '\n')
last_classifier = gbm
winsound.Beep(frequency, duration)
print('='*80, '\n')
################################################################################################################################################################
elif inp == 'gridsearch':
print('-- Random GridSearchCV on LightGBM classifier --\n')
iters = input('Define number of iterations (default = 10): ')
if iters == '':
iters = 10
print()
cv = input('Define number of CV (default = 2): ')
if cv == '':
cv = 2
print()
param_distributions = {
'max_depth': [-1,10,30,60,100,200],
'min_data_in_leaf': [4,8,16,32,64,128],
'feature_fraction': [0.1,0.25,0.5,0.75,1],
'bagging_fraction': [0.1,0.25,0.5,0.75,1],
'bagging_freq': [0,2,8,32,128,256],
'lambda_l1': [0,0.1,1,2,4,175,512,1000],
'lambda_l2': [0,0.1,1,2,4,175,512,1000],
'min_gain_to_split': [0,0.01,0.03,0.1,0.3,0.5,0.9,1],
'num_boost_round': [100, 500, 1000, 2500, 5000, 10000, 15000, 20000],
'learning_rate': [0.5, 0.25, 0.1, 0.05, 0.01, 0.005, 0.001, 0.0005, 0.0001],
'num_leaves': [10, 31, 62, 124, 200, 500, 750, 1000],
'objective': ['softmax'],
'gpu_use_dp': [True],
'num_threads': [1],
'num_class': [3],
'max_bin': [128, 256, 512, 1024, 2048, 3000, 4000, 5000, 6000]
}
print('-- Finding best parameters --\n')
rSearch = RandomizedSearchCV(estimator = lgb.LGBMClassifier(), param_distributions = param_distributions, scoring = 'f1_micro', n_jobs = 2,
cv = int(cv), verbose = 10, n_iter = int(iters))
warnings.filterwarnings("ignore")
rSearch.fit(train_X, train_y)
warnings.filterwarnings("default")
print()
print('Best parameters:')
print(rSearch.best_params_, '\n')
print('Score:')
print(rSearch.best_score_, '\n')
winsound.Beep(frequency, duration)
print('='*80, '\n')
################################################################################################################################################################
elif inp == 'hyperopt':
print('-- Bayesian Optimization on LightGBM classifier (with Hyperopt) --\n')
iters = input('Define number of evaluations (default = 50): ')
if iters == '':
iters = 50
print()
def objective_fun(space):
print()
warnings.filterwarnings('ignore')
model = lgb.LGBMClassifier(**space)
accuracy = cross_val_score(model, X, y, cv = 3, scoring = 'f1_micro').mean()
warnings.filterwarnings('default')
return {'loss': - accuracy, 'status': STATUS_OK}
param_space = {
'max_depth': [0],
'min_data_in_leaf': scope.int(hp.quniform('min_data_in_leaf', 1, 5000, 1)),
'feature_fraction': hp.uniform('feature_fraction', 0, 1),
'bagging_fraction': hp.uniform('bagging_fraction', 0, 1),
'bagging_freq': scope.int(hp.quniform('bagging_freq', 0, 1000 ,1)),
'lambda_l1': hp.uniform('lambda_l1', 0, 10000),
'lambda_l2': hp.uniform('lambda_l2', 0, 10000),
'min_gain_to_split': hp.uniform('min_gain_to_split', 0, 1),
'num_boost_round': scope.int(hp.quniform('num_boost_round', 100, 20000, 1)),
'learning_rate': hp.uniform('learning_rate', 0.000001, 1),
'num_leaves': scope.int(hp.quniform('num_leaves', 2, 2000, 1)),
'objective': ['softmax'],
'gpu_use_dp': [True],
'num_threads': [2],
'num_class': [3],
'max_bin': scope.int(hp.quniform('max_bin', 32, 4096, 1)),
'min_sum_hessian_in_leaf': hp.uniform('min_sum_hessian_in_leaf', 0, 5)
}
param_init_trials = {
'max_depth': 0,
'min_data_in_leaf': 40,
'feature_fraction': 0.5,
'bagging_fraction': 0.9,
'bagging_freq': 1,
'lambda_l1': 0,
'lambda_l2': 10,
'min_gain_to_split': 0,
'num_boost_round': 10000,
'learning_rate': 0.1,
'num_leaves': 31,
'objective': 'softmax',
'gpu_use_dp': True,
'num_threads': 2,
'num_class': 3,
'max_bin': 256,
'min_sum_hessian_in_leaf': 0.1
}
trials = generate_trials_to_calculate([param_init_trials])
best = fmin(fn = objective_fun, space = param_space,
algo = tpe.suggest, max_evals = int(iters),
trials = trials)
print()
print(best, '\n')
input()
elif inp == 'evolve':
print('-- Evolutionary optimization on LightGBM --\n')
iters = input('Define number of generations (default = 10): ')
if iters == '':
iters = 10
print()
cv = input('Define number of cross-validation sets (default = 2): ')
if cv == '':
cv = 2
print()
c_size = input('Define size of change on each iteration (default = 1): ')
if c_size == '':
c_size = 1
print()
pop_size = input('Define size of population (default = 10): ')
if pop_size == '':
pop_size = 10
param_space = {
'max_depth': [-1],
'min_data_in_leaf': np.linspace(0, 5000, 5002, dtype = int),
'feature_fraction': np.linspace(0, 1, 1000),
'bagging_fraction': np.linspace(0, 1, 1000),
'bagging_freq': np.linspace(0, 100 ,102, dtype = int),
'lambda_l1': np.linspace(0, 10000, 100000),
'lambda_l2': np.linspace(0, 10000, 100000),
'min_gain_to_split': np.linspace(0, 0.9, 100),
'num_boost_round': np.linspace(100, 20000, 19902, dtype = int),
'learning_rate': np.linspace(0.0001, 1, 10000),
'num_leaves': np.linspace(2, 2000, 2000, dtype = int),
'objective': ['softmax'],
'gpu_use_dp': [True],
'num_threads': [2],
'num_class': [3],
'max_bin': np.linspace(32, 4096, 4066, dtype = int),
'min_sum_hessian_in_leaf': np.linspace(0, 5, 100)
}
common_ancestor = {
'max_depth': -1,
'min_data_in_leaf': 20,
'feature_fraction': 0.5,
'bagging_fraction': 0.9,
'bagging_freq': 1,
'lambda_l1': 0.,
'lambda_l2': 10.,
'min_gain_to_split': 0.,
'num_boost_round': 2000,
'learning_rate': 0.1,
'num_leaves': 31,
'objective': 'softmax',
'gpu_use_dp': True,
'num_threads': 2,
'num_class': 3,
'max_bin': 256,
'min_sum_hessian_in_leaf': 0.1
}
evolveSelect(X, y, param_space, int(iters), int(pop_size), float(c_size), int(cv), common_ancestor)
################################################################################################################################################################
elif last_classifier != None:
# Decides if wants to submit
print('Want to submit?')
inp = input('(y/n): ').lower()
print()
if inp == 'y':
# Decides if wants to fit classifier again for the entirety of the dataset
print('Want to fit for entire dataset?')
inp = input('(y/n): ').lower()
print()
if inp == 'y':
print('-- Training the last classifier --\n')
warnings.filterwarnings("ignore")
last_classifier.fit(X, y)
warnings.filterwarnings("default")
print()
submit(last_classifier)
return
else:
pass
def bayesian_parameter_optimisation(tree,
toolbox,
max_evals_without_progress=10):
"""
Optimises the parameters in tree with bayesian optimisation.
Returns a copy of the tree with the updated hyperparameters.
:param tree:
:return:
"""
hyperparameters, hyperparameter_indices, default_values = _get_hyperparameters_from_tree(
tree)
if not hyperparameters:
# Cant optimise a tree with no tunable args, so just return a copy of the original tree
return toolbox.clone(tree)
print("Original tree", tree)
# Start the search at the existing values rather than randomly
trials = generate_trials_to_calculate([default_values])
# Each time we do bayesian optimisation we should use a new random seed to prevent overfitting
# to a particular split
seed = random.randint(0, 1000)
stopping_critera_met = False
optimised_params = space_eval(hyperparameters, default_values)
n_iters_without_progress = 0
best_loss = inf
# Run one iteration of bayesian optimisation till stopping criteria is met (timeout or no improvement)
while not stopping_critera_met:
try:
# A single iteration of bayesian optimisation
best = fmin(fn=partial(_objective_function, tree, toolbox,
hyperparameter_indices, seed),
space=hyperparameters,
algo=tpe.suggest,
max_evals=len(trials) + 1,
trials=trials,
show_progressbar=False)
optimised_params = space_eval(hyperparameters, best)
# Check if progress was made
current_loss = trials.losses()[-1]
if current_loss >= best_loss:
n_iters_without_progress += 1
else:
n_iters_without_progress = 0
best_loss = min(current_loss, best_loss)
except TimeoutError:
# Ran out of time while optimising. Break out of loop and return best we have
break
stopping_critera_met = n_iters_without_progress >= max_evals_without_progress
tree = _fill_with_hyperparameters(tree, toolbox, hyperparameter_indices,
optimised_params)
print("Optimised tree", tree)
return tree
def fmin(
fn,
space,
algo,
max_evals,
early_stop_round_mode_fun=None,
early_stop_round=None,
trials=None,
rstate=None,
allow_trials_fmin=False,
pass_expr_memo_ctrl=None,
catch_eval_exceptions=False,
verbose=0,
return_argmin=True,
points_to_evaluate=None,
max_queue_len=1,
show_progressbar=True,
):
"""Minimize a function over a hyperparameter space.
More realistically: *explore* a function over a hyperparameter space
according to a given algorithm, allowing up to a certain number of
function evaluations. As points are explored, they are accumulated in
`trials`
Parameters
----------
fn : callable (trial point -> loss)
This function will be called with a value generated from `space`
as the first and possibly only argument. It can return either
a scalar-valued loss, or a dictionary. A returned dictionary must
contain a 'status' key with a value from `STATUS_STRINGS`, must
contain a 'loss' key if the status is `STATUS_OK`. Particular
optimization algorithms may look for other keys as well. An
optional sub-dictionary associated with an 'attachments' key will
be removed by fmin its contents will be available via
`trials.trial_attachments`. The rest (usually all) of the returned
dictionary will be stored and available later as some 'result'
sub-dictionary within `trials.trials`.
space : hyperopt.pyll.Apply node
The set of possible arguments to `fn` is the set of objects
that could be created with non-zero probability by drawing randomly
from this stochastic program involving involving hp_<xxx> nodes
(see `hyperopt.hp` and `hyperopt.pyll_utils`).
algo : search algorithm
This object, such as `hyperopt.rand.suggest` and
`hyperopt.tpe.suggest` provides logic for sequential search of the
hyperparameter space.
max_evals : int
Allow up to this many function evaluations before returning.
trials : None or base.Trials (or subclass)
Storage for completed, ongoing, and scheduled evaluation points. If
None, then a temporary `base.Trials` instance will be created. If
a trials object, then that trials object will be affected by
side-effect of this call.
rstate : numpy.RandomState, default numpy.random or `$HYPEROPT_FMIN_SEED`
Each call to `algo` requires a seed value, which should be different
on each call. This object is used to draw these seeds via `randint`.
The default rstate is
`numpy.random.RandomState(int(env['HYPEROPT_FMIN_SEED']))`
if the `HYPEROPT_FMIN_SEED` environment variable is set to a non-empty
string, otherwise np.random is used in whatever state it is in.
verbose : int
Print out some information to stdout during search.
allow_trials_fmin : bool, default True
If the `trials` argument
pass_expr_memo_ctrl : bool, default False
If set to True, `fn` will be called in a different more low-level
way: it will receive raw hyperparameters, a partially-populated
`memo`, and a Ctrl object for communication with this Trials
object.
return_argmin : bool, default True
If set to False, this function returns nothing, which can be useful
for example if it is expected that `len(trials)` may be zero after
fmin, and therefore `trials.argmin` would be undefined.
points_to_evaluate : list, default None
Only works if trials=None. If points_to_evaluate equals None then the
trials are evaluated normally. If list of dicts is passed then
given points are evaluated before optimisation starts, so the overall
number of optimisation steps is len(points_to_evaluate) + max_evals.
Elements of this list must be in a form of a dictionary with variable
names as keys and variable values as dict values. Example
points_to_evaluate value is [{'x': 0.0, 'y': 0.0}, {'x': 1.0, 'y': 2.0}]
max_queue_len : integer, default 1
Sets the queue length generated in the dictionary or trials. Increasing this
value helps to slightly speed up parallel simulatulations which sometimes lag
on suggesting a new trial.
show_progressbar : bool, default True
Show a progressbar.
Returns
-------
argmin : dictionary
If return_argmin is True returns `trials.argmin` which is a dictionary. Otherwise
this function returns the result of `hyperopt.space_eval(space, trails.argmin)` if there
were succesfull trails. This object shares the same structure as the space passed.
If there were no succesfull trails, it returns None.
"""
if rstate is None:
env_rseed = os.environ.get('HYPEROPT_FMIN_SEED', '')
if env_rseed:
rstate = np.random.RandomState(int(env_rseed))
else:
rstate = np.random.RandomState()
if allow_trials_fmin and hasattr(trials, 'fmin'):
return trials.fmin(
fn,
space,
algo=algo,
max_evals=max_evals,
max_queue_len=max_queue_len,
rstate=rstate,
pass_expr_memo_ctrl=pass_expr_memo_ctrl,
verbose=verbose,
catch_eval_exceptions=catch_eval_exceptions,
return_argmin=return_argmin,
show_progressbar=show_progressbar,
)
if trials is None:
if points_to_evaluate is None:
trials = base.Trials()
else:
assert type(points_to_evaluate) == list
trials = generate_trials_to_calculate(points_to_evaluate)
domain = base.Domain(fn, space, pass_expr_memo_ctrl=pass_expr_memo_ctrl)
if early_stop_round is not None:
# max_evals = 1000
if early_stop_round_mode_fun is None:
early_stop_round_mode_fun = lambda x: 1
rval = FMinIter(algo,
domain,
trials,
max_evals=max_evals,
early_stop_round_mode_fun=early_stop_round_mode_fun,
early_stop_round=early_stop_round,
rstate=rstate,
verbose=verbose,
max_queue_len=max_queue_len,
show_progressbar=show_progressbar)
rval.catch_eval_exceptions = catch_eval_exceptions
rval.exhaust()
if return_argmin:
if len(trials.trials) == 0:
raise Exception(
"There are no evaluation tasks, cannot return argmin of task losses."
)
return trials.argmin
elif len(trials) > 0:
# Only if there are some succesfull trail runs, return the best point in the evaluation space
return space_eval(space, trials.argmin)
else:
return None
def opt_method(data, initializers, resdir, max_evals):
dataset = data.dataset_name
__location__ = os.path.realpath(os.path.join(os.getcwd(),
os.path.dirname(__file__)))
datapath = data.data_path
init_endmembers = data.init_endmembers
n_band, n_end = init_endmembers.shape
def objective_func(data, hyperpars):
data.load_data(normalize=True, shuffle=False)
activation = LeakyReLU(0.2)
unmixer = Autoencoder(n_end=n_end, data=my_data, activation=activation,
optimizer=hyperpars['optimizer'], l2=hyperpars['l2'], l1=hyperpars['l1'], plot_every_n=0)
unmixer.create_model(SAD)
my_data.make_patches(1, num_patches=hyperpars['num_patches'], use_orig=True)
history = unmixer.fit(epochs=100, batch_size=hyperpars['batch_size'])
endmembers = unmixer.get_endmembers().transpose()
abundances = unmixer.get_abundances()
Y = np.transpose(data.orig_data)
GT = np.transpose(data.GT)
sad, idx_org, idx_hat, sad_k_m, s0 = calc_SAD_2(GT, endmembers)
MSE = mse(Y, endmembers, np.transpose(abundances))
abundances = abundances.reshape(data.n_rows, data.n_cols, endmembers.shape[1]).transpose((1, 0, 2))
resdict = {'endmembers': endmembers,
'abundances': abundances,
'loss': history.history['loss'],
'SAD': sad,
'MSE': MSE}
del unmixer
K.clear_session()
return {'loss': sad, 'status': STATUS_OK, 'attachments': resdict}
space = {
'optimizer': {'class_name': 'RMSprop', 'config': {'lr': hp.qloguniform('ACCESS_' + dataset + '_lr', -16, -1, 1e-7)}},
'l1': hp.qloguniform('ACCESS_' + dataset + '_l1', -16, 2, 1e-7),
'l2': hp.qloguniform('ACCESS_' + dataset + '_l2', -16, 2, 1e-7),
'num_patches': scope.int(hp.quniform('ACCESS_' + dataset + '_num_patches', 8, 8192, 1)),
'batch_size': scope.int(hp.quniform('ACCESS_' + dataset + '_batch_size', 1, 50, 1)),
}
my_data = HSI(datapath)
trials = generate_trials_to_calculate([{
'ACCESS_' + dataset + '_lr': 0.001,
'ACCESS_' + dataset + '_l1': 0,
'ACCESS_' + dataset + '_l2': 0,
'ACCESS_' + dataset + '_num_patches': 1028,
'ACCESS_' + dataset + '_batch_size': 32
}])
pars = fmin(lambda x: objective_func(my_data, x),
space=space,
trials=trials,
algo=tpe.suggest,
max_evals=max_evals,
rstate=np.random.RandomState(random_seed))
improvements = reduce(improvement_only, trials.losses(), [])
save_config(resdir, dataset, pars, trials.average_best_error())
return improvements, pars, trials
def runOptim(self, budget, b, initData=None, initResult=None):
if initData is not None and initResult is not None:
Xinit = initData[:]
Yinit = initResult[:]
else:
# set a random number
np.random.seed(self.trial_num)
# Xinit: points in BO format and Pinit: points in TPE format
# Yinit: max/auc values and Finit: min/loss values
Xinit, Pinit, Yinit, Finit = self.initialize_all_methods()
# get variable names
bounds_keys = list(self.bounds.keys())
# compute besty of initial points
besty = np.max(Yinit)
# compute bestx of initial points
besty_idx = np.argmax(Yinit)
bestp = Pinit[besty_idx]
# get selected arm for categorical variable (the first parameter)
first_para_name = bounds_keys[0]
bestarm = bestp[first_para_name]
print("n_init: {}, bestarm: {}, bestx: {}, besty: {}".format(len(Finit), bestarm, bestp, round(besty, 4)))
# store the result for this trial (becoming one col of matrix best_vals)
result_list = []
# store the selected arms of initial points
arm_list = []
for b_ele_idx in range(b):
# store selected arms in all iterations for all trials
self.arm_recommendations.append(bestarm)
arm_list.append(bestarm)
# store the bestx and besty of initial points
result_list.append([0, arm_list, bestp, besty])
# use initial points for TPE
tpe_algorithm = partial(tpe.suggest, n_startup_jobs=len(Finit))
# create trials with initial points
trials = generate_trials_to_calculate(Pinit, Finit)
# store best point and best function value so far
bestx_sofar = []
besty_sofar = []
if b > 1:
budget = int(budget / b) + 1
for t in range(1, budget):
print("iteration: {}".format(t))
# store <batch_size> arms selected in this iteration
arm_list = []
# store suggested data points in batch
x_batch = np.zeros((b, self.n_dim)) # batch_size x dim of a data point
y_batch = np.zeros(b) # store max function values
f_batch = np.zeros(b) # store min function values
# in an iteration, suggest a batch of points
# only after selecting all points in the batch, we can compute their function values
for b_ele_idx in range(b):
# run TPE to suggest the next point which is stored in trials
best_params = fmin(self.f, self.bounds, tpe_algorithm, len(trials) + 1, trials)
# get best_x and best_y so far
bestx_sofar.append(best_params)
# max/auc of objective function
best_result = trials.best_trial["result"]["loss"]
if self.f_type == "func":
best_result = -1.0 * best_result
elif self.f_type == "class":
best_result = 1.0 - best_result
besty_sofar.append(best_result)
# get selected arm for categorical variable (the first parameter)
first_para_name = bounds_keys[0]
arm = int(trials.vals[first_para_name][-1])
# store selected arms in all iterations for all trials
self.arm_recommendations.append(arm)
arm_list.append(arm)
# get other variables
x_next = []
for d in range(1, self.n_dim):
para_name = bounds_keys[d]
x_next.append(trials.vals[para_name][-1])
x_batch[b_ele_idx, :] = [arm] + x_next
# get function value of the next point (indeed, we don't know this function value)
y_next = trials.results[-1]["loss"]
f_batch[b_ele_idx] = y_next # store min function value
if self.f_type == "func":
y_next = -1.0 * y_next
elif self.f_type == "class":
y_next = 1.0 - y_next
y_batch[b_ele_idx] = y_next # store max function value
print("arm_next: {}, x_next: {}, y_next: {}".format(arm, np.around(x_next, 4), round(y_next, 4)))
if b > 1:
# reset trials to suggest the next batch element
trials = generate_trials_to_calculate(Pinit, Finit)
# end batch
if b > 1:
# update the data with suggested points in batch
for ele_idx, x in enumerate(x_batch):
point = {bounds_keys[idx]: val for idx, val in enumerate(x)}
point[bounds_keys[0]] = int(point[bounds_keys[0]])
Pinit.append(point)
Finit.append(f_batch[ele_idx])
# create trails with new batch elements
trials = generate_trials_to_calculate(Pinit, Finit)
# instead of computing function values of batch elements,
# we already have them in y_batch
for b_ele_idx in range(b):
# get the best function value till now
end = (t - 1) * b + (b_ele_idx + 1)
besty = max(besty_sofar[:end])
bestx = bestx_sofar[np.argmax(besty_sofar[:end])]
# get selected arm for categorical variable (the first parameter)
first_para_name = bounds_keys[0]
bestarm = bestx[first_para_name]
print("bestarm: {}, bestx: {}, besty: {}".format(bestarm, bestx, round(besty, 4)))
# store the results of this iteration
result_list.append([t, arm_list, bestx, besty])
if b > 1:
result_list = result_list[:-1]
print("Finished ", self.method, " for trial: ", self.trial_num)
# store the result for all iterations in this trial
df = pd.DataFrame(result_list, columns=["iter", "arm_list", "best_input", "best_value"])
return df
