Open maciekmalachowski opened 2 weeks ago
Please provide code to reproduce the issue.
def generate_models():
datasets = [
kddcup09_upselling.get_data()
]
algorithms=[
'Baseline',
'CatBoost',
'Decision Tree',
'Extra Trees',
'LightGBM',
'Neural Network',
'Random Forest',
'Xgboost'
]
for data in datasets:
for alg in algorithms:
# create directions for AutoML
if not os.path.exists(f"AutoML/{data[2]}/{alg}"):
os.makedirs(f"AutoML/{data[2]}/{alg}")
# various datasets need either rmse or accuracy as metric
if data[-1] == "reg":
eval_metric = "rmse"
else:
eval_metric = "accuracy"
# create automl object
automl = AutoML(
mode="Compete",
total_time_limit=600,
results_path=f"AutoML/{data[2]}/{alg}",
algorithms=[alg],
train_ensemble=False,
golden_features=False,
features_selection=False,
stack_models=False,
kmeans_features=False,
explain_level=0,
boost_on_errors=False,
eval_metric=eval_metric,
validation_strategy={
"validation_type": "kfold",
"k_folds": 5,
"shuffle": True,
"stratify": True,
"random_seed": 123
},
start_random_models=10,
hill_climbing_steps=3,
top_models_to_improve=3,
random_state=1234)
# train automl
automl.fit(data[0], data[1])
from sklearn.datasets import fetch_openml
def get_data():
# read data from openml page
name = "Kddcup09_upselling"
dataset_type = "binary"
data = fetch_openml(data_id=1114, as_frame=True)
X = data.data
y = data.target
return X, y, name, dataset_type
miniconda3\Lib\site-packages\supervised\preprocessing\preprocessing_categorical.py:81:
FutureWarning: Setting an item of incompatible dtype is deprecated and will raise in a future error of pandas. Value '[0 0 0 ... 0 0 0]' has dtype incompatible with category, please explicitly cast to a compatible dtype first.
Dataset: https://www.openml.org/search?type=data&sort=runs&status=active&id=1114