def dont_test_smac_choice(self):
import numpy as np
from sklearn import svm, datasets
from sklearn.model_selection import cross_val_score
# Import ConfigSpace and different types of parameters
from smac.configspace import ConfigurationSpace
# Import SMAC-utilities
from smac.tae.execute_func import ExecuteTAFuncDict
from smac.scenario.scenario import Scenario
from smac.facade.smac_facade import SMAC
tfm = PCA() | Nystroem() | NoOp()
planned_pipeline1 = (
OneHotEncoder(handle_unknown='ignore', sparse=False)
| NoOp()) >> tfm >> (LogisticRegression() | KNeighborsClassifier())
cs: ConfigurationSpace = get_smac_space(planned_pipeline1,
lale_num_grids=5)
# Scenario object
scenario = Scenario({
"run_obj":
"quality", # we optimize quality (alternatively runtime)
"runcount-limit": 1, # maximum function evaluations
"cs": cs, # configuration space
"deterministic": "true"
})
# Optimize, using a SMAC-object
tae = test_iris_fmin_tae(planned_pipeline1, num_folds=2)
print(
"Optimizing! Depending on your machine, this might take a few minutes."
)
smac = SMAC(scenario=scenario,
rng=np.random.RandomState(42),
tae_runner=tae)
incumbent = smac.optimize()
inc_value = tae(incumbent)
print("Optimized Value: %.2f" % (inc_value))
def test_smac(self):
import numpy as np
from sklearn import svm, datasets
from sklearn.model_selection import cross_val_score
# Import ConfigSpace and different types of parameters
from smac.configspace import ConfigurationSpace
# Import SMAC-utilities
from smac.tae.execute_func import ExecuteTAFuncDict
from smac.scenario.scenario import Scenario
from smac.facade.smac_facade import SMAC
from lale.search.SMAC import get_smac_space
lr = LogisticRegression()
cs: ConfigurationSpace = get_smac_space(lr)
# Scenario object
scenario = Scenario({
"run_obj":
"quality", # we optimize quality (alternatively runtime)
"runcount-limit": 1, # maximum function evaluations
"cs": cs, # configuration space
"deterministic": "true",
"abort_on_first_run_crash": False
})
# Optimize, using a SMAC-object
tae = test_iris_fmin_tae(lr, num_folds=2)
print(
"Optimizing! Depending on your machine, this might take a few minutes."
)
smac = SMAC(scenario=scenario,
rng=np.random.RandomState(42),
tae_runner=tae)
incumbent = smac.optimize()
inc_value = tae(incumbent)
print("Optimized Value: %.2f" % (inc_value))
def dont_test_car_smac(self):
import numpy as np
from lale.datasets.auto_weka import fetch_car
from sklearn.metrics import accuracy_score, make_scorer
from sklearn.preprocessing import LabelEncoder
import pandas as pd
from lale.lib.weka import J48
from lalegpl.lib.r import ArulesCBAClassifier
from lale.operators import make_pipeline
from lale.lib.lale import HyperoptClassifier
from lale.lib.sklearn import LogisticRegression, KNeighborsClassifier
from smac.scenario.scenario import Scenario
from smac.facade.smac_facade import SMAC
from smac.configspace import ConfigurationSpace
(X_train, y_train), (X_test, y_test) = fetch_car()
y_name = y_train.name
le = LabelEncoder()
y_train = le.fit_transform(y_train)
y_test = le.transform(y_test)
y_train = pd.Series(y_train, name=y_name)
y_test = pd.Series(y_test, name=y_name)
# planned_pipeline = make_pipeline(J48() | ArulesCBAClassifier() | LogisticRegression() | KNeighborsClassifier())
planned_pipeline = make_pipeline(ArulesCBAClassifier()
| KNeighborsClassifier()
| LogisticRegression())
cs: ConfigurationSpace = get_smac_space(planned_pipeline)
print(cs)
# X_train = X_train[0:20]
# y_train = y_train[0:20]
# Scenario object
run_count_limit = 1
scenario = Scenario({
"run_obj":
"quality", # we optimize quality (alternatively runtime)
"runcount-limit": run_count_limit, # maximum function evaluations
"cs": cs, # configuration space
"deterministic": "true",
"abort_on_first_run_crash": False
})
# Optimize, using a SMAC-object
def f_min(op):
return test_f_min(op, X_train, y_train, num_folds=2)
tae = lale_op_smac_tae(planned_pipeline, f_min)
print(
"Optimizing! Depending on your machine, this might take a few minutes."
)
smac = SMAC(scenario=scenario,
rng=np.random.RandomState(42),
tae_runner=tae)
incumbent = smac.optimize()
trainable_pipeline = lale_trainable_op_from_config(
planned_pipeline, incumbent)
trained_pipeline = trainable_pipeline.fit(X_train, y_train)
pred = trained_pipeline.predict(X_test)
accuracy = accuracy_score(y_test, pred)
print("Accuracy: %.2f" % (accuracy))
inc_value = tae(incumbent)
print("Optimized Value: %.2f" % (inc_value))
print(f"Run count limit: {run_count_limit}")