ml_memory_limit=1024 * 8,
time_left_for_this_task=3600,
resampling_strategy='cv',
# ensemble_size=1,
# initial_configurations_via_metalearning=0,
resampling_strategy_arguments={'folds': 5})
start = time.time()
#X_train = X_train.astype('float') # when?
automl.fit(X_train, y_train,
dataset_name='boston_housing') #change dataset name accordingly
automl.refit(X_train.copy(), y_train.copy())
print(
'[INFO] Elapsed time finding best model: {} seconds.'.format(time.time() -
start))
predictions = automl.predict(X_test)
#print('--- CLASSIFICATION REPORT: ---') #not for regression
#print(classification_report(y_test, predictions, digits=5))
print('\n\n--- MODELS: ---')
print(automl.show_models())
print('\n\n--- STATISTICS: ---')
print(automl.sprint_statistics())
#-----CLASSIFIER-----
#print('\n\n--- SCORE: ---')
#print("Balanced error score", 1 - balanced_accuracy_score(y_test, predictions))
#-----REGRESSION-----
print('\n\n--- SCORE: ---')
print("R2 score", r2_score(y_test, predictions))
if __name__ == '__main__':
# load dataset
url = 'https://raw.githubusercontent.com/jbrownlee/Datasets/master/auto-insurance.csv'
dataframe = read_csv(url, header=None)
# split into input and output elements
data = dataframe.values
data = data.astype('float32')
X, y = data[:, :-1], data[:, -1]
# split into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.33,
random_state=1)
# define search
model = AutoSklearnRegressor(time_left_for_this_task=20 * 60,
per_run_time_limit=45,
n_jobs=6,
metric=auto_mean_absolute_error)
# perform the search
model.fit(X_train, y_train)
# summarize
print(model.sprint_statistics())
# evaluate best model
y_hat = model.predict(X_test)
mae = mean_absolute_error(y_test, y_hat)
print("MAE: %.3f" % mae)
print("Show models")
models_def = model.show_models()
print(models_def)
output_folder=outpath + 'output_folder',
)
print("start searching")
# perform the search
model.fit(X_train,
y_train,
dataset_name=ml_type + '_t' + str(time_left_for_this_task) +
'_lead' + str(l))
# summarize
file = open(
'log_files/' + ml_type + '_t' + str(time_left_for_this_task) +
'_lead' + str(l) + '.txt', 'w')
file.write(model.sprint_statistics())
file.write('\n')
file.write(model.show_models())
file.close()
print(model.sprint_statistics())
print(model.show_models())
# evaluate best model
y_hat = model.predict(X_val)
metric = calc_metrics(y_val, y_hat, ml_type)
if ml_type == 'regression':
metrics[l] = metric
elif ml_type == 'classification':
metrics[l, :] = metric
print("************************************")
print("lead:" + str(l) + ", metric: " + str(metric))
include_preprocessors=preprocessing_to_use,
exclude_preprocessors=None,
ml_memory_limit=6156,
resampling_strategy="cv",
resampling_strategy_arguments={"folds": 5})
# Train models
auto_sklearn.fit(X=X_train.copy(), y=y_train.copy(), metric=mean_squared_error)
it_fits = auto_sklearn.refit(X=X_train.copy(), y=y_train.copy())
# Predict
y_hat = auto_sklearn.predict(X_test)
# Show results
auto_sklearn.cv_results_
auto_sklearn.sprint_statistics()
auto_sklearn.show_models()
auto_sklearn.get_models_with_weights()
# TPOT
from tpot import TPOTRegressor
tpot_config = {
"sklearn.linear_model.Ridge": {},
"sklearn.ensemble.RandomForestClassifier": {},
"sklearn.ensemble.ExtraTreesClassifier": {},
"sklearn.ensemble.GradientBoostingClassifier": {},
}
auto_tpot = TPOTRegressor(generations=100,
