def fit(self, X_train, y_train, X_validation=None, y_validation=None):
"""
Fit AutoML
:param X_train: Pandas DataFrame with training data.
:param y_train: Numpy Array with target training data.
:param X_validation: Pandas DataFrame with validation data. (Not implemented yet)
:param y_validation: Numpy Array with target of validation data. (Not implemented yet)
"""
try:
if self._best_model is not None:
print("Best model is already set, no need to run fit. Skipping ...")
return
start_time = time.time()
if not isinstance(X_train, pd.DataFrame):
raise AutoMLException(
"AutoML needs X_train matrix to be a Pandas DataFrame"
)
if X_train is not None:
X_train = X_train.copy(deep=False)
X_train, y_train, X_validation, y_validation = self._initial_prep(
X_train, y_train, X_validation, y_validation
)
self._save_data(X_train, y_train, X_validation, y_validation)
self._set_ml_task(y_train)
self._set_algorithms()
self._set_metric()
self._estimate_training_times()
if self._ml_task in [BINARY_CLASSIFICATION, MULTICLASS_CLASSIFICATION]:
self._check_imbalanced(y_train)
tuner = MljarTuner(
self._tuner_params,
self._algorithms,
self._ml_task,
self._validation,
self._seed,
)
# not so random step
generated_params = tuner.get_not_so_random_params(X_train, y_train)
self._del_data_variables(X_train, y_train)
for params in generated_params:
self.train_model(params)
# hill climbing
for params in tuner.get_hill_climbing_params(self._models):
self.train_model(params)
self.ensemble_step()
max_loss = 10e12
for i, m in enumerate(self._models):
if m.get_final_loss() < max_loss:
self._best_model = m
max_loss = m.get_final_loss()
self.get_additional_metrics()
self._fit_time = time.time() - start_time
# self._progress_bar.close()
with open(os.path.join(self._results_path, "best_model.txt"), "w") as fout:
fout.write(f"{self._best_model.get_name()}")
with open(os.path.join(self._results_path, "params.json"), "w") as fout:
params = {
"ml_task": self._ml_task,
"optimize_metric": self._optimize_metric,
"saved": self._model_paths,
}
fout.write(json.dumps(params, indent=4))
ldb = self.get_leaderboard()
ldb.to_csv(os.path.join(self._results_path, "leaderboard.csv"), index=False)
# save report
ldb["Link"] = [f"[Results link]({m}/README.md)" for m in ldb["name"].values]
ldb.insert(loc=0, column="Best model", value="")
ldb.loc[
ldb.name == self._best_model.get_name(), "Best model"
] = "*** the best ***"
with open(os.path.join(self._results_path, "README.md"), "w") as fout:
fout.write(f"# AutoML Leaderboard\n\n")
fout.write(tabulate(ldb.values, ldb.columns, tablefmt="pipe"))
except Exception as e:
raise e
finally:
if self._X_train_path is not None:
self._load_data_variables(X_train)
def fit(self, X_train, y_train, X_validation=None, y_validation=None):
"""
Fit AutoML
:param X_train: Pandas DataFrame with training data.
:param y_train: Numpy Array with target training data.
:param X_validation: Pandas DataFrame with validation data. (Not implemented yet)
:param y_validation: Numpy Array with target of validation data. (Not implemented yet)
"""
try:
if self._best_model is not None:
print(
"Best model is already set, no need to run fit. Skipping ..."
)
return
self._start_time = time.time()
if not isinstance(X_train, pd.DataFrame):
raise AutoMLException(
"AutoML needs X_train matrix to be a Pandas DataFrame")
self._set_ml_task(y_train)
if X_train is not None:
X_train = X_train.copy(deep=False)
X_train, y_train, X_validation, y_validation = self._initial_prep(
X_train, y_train, X_validation, y_validation)
self._save_data(X_train, y_train, X_validation, y_validation)
self._set_algorithms()
self._set_metric()
# self._estimate_training_times()
if self._ml_task in [
BINARY_CLASSIFICATION, MULTICLASS_CLASSIFICATION
]:
self._check_imbalanced(y_train)
tuner = MljarTuner(
self._tuner_params,
self._algorithms,
self._ml_task,
self._validation,
self._explain_level,
self._data_info,
self._seed,
)
self.tuner = tuner
self._time_spend = {}
self._time_start = {}
# 1. Check simple algorithms
self._fit_level = "simple_algorithms"
start = time.time()
self._time_start[self._fit_level] = start
for params in tuner.simple_algorithms_params():
self.train_model(params)
self._time_spend["simple_algorithms"] = np.round(
time.time() - start, 2)
# 2. Default parameters
self._fit_level = "default_algorithms"
start = time.time()
self._time_start[self._fit_level] = start
for params in tuner.default_params(len(self._models)):
self.train_model(params)
self._time_spend["default_algorithms"] = np.round(
time.time() - start, 2)
# 3. The not-so-random step
self._fit_level = "not_so_random"
start = time.time()
self._time_start[self._fit_level] = start
generated_params = tuner.get_not_so_random_params(len(
self._models))
for params in generated_params:
self.train_model(params)
self._time_spend["not_so_random"] = np.round(
time.time() - start, 2)
# 4. The hill-climbing step
self._fit_level = "hill_climbing"
start = time.time()
self._time_start[self._fit_level] = start
for params in tuner.get_hill_climbing_params(self._models):
self.train_model(params)
self._time_spend["hill_climbing"] = np.round(
time.time() - start, 2)
# 5. Ensemble unstacked models
self._fit_level = "ensemble_unstacked"
start = time.time()
self._time_start[self._fit_level] = start
self.ensemble_step()
self._time_spend["ensemble_unstacked"] = np.round(
time.time() - start, 2)
if self._stack:
# 6. Stack best models
self._fit_level = "stack"
start = time.time()
self._time_start[self._fit_level] = start
self.stacked_ensemble_step()
self._time_spend["stack"] = np.round(time.time() - start, 2)
# 7. Ensemble all models (original and stacked)
any_stacked = False
for m in self._models:
if m._is_stacked:
any_stacked = True
break
if any_stacked:
self._fit_level = "ensemble_all"
start = time.time()
self.ensemble_step(is_stacked=True)
self._time_spend["ensemble_all"] = np.round(
time.time() - start, 2)
self._fit_time = time.time() - self._start_time
logger.info(f"AutoML fit time: {self._fit_time}")
except Exception as e:
raise e
finally:
if self._X_train_path is not None:
self._load_data_variables(X_train)
def fit(self, X_train, y_train, X_validation=None, y_validation=None):
"""
Fit AutoML
:param X_train: Pandas DataFrame with training data.
:param y_train: Numpy Array with target training data.
:param X_validation: Pandas DataFrame with validation data. (Not implemented yet)
:param y_validation: Numpy Array with target of validation data. (Not implemented yet)
"""
try:
if self._best_model is not None:
print(
"Best model is already set, no need to run fit. Skipping ..."
)
return
self._start_time = time.time()
if not isinstance(X_train, pd.DataFrame):
raise AutoMLException(
"AutoML needs X_train matrix to be a Pandas DataFrame")
if X_train is not None:
X_train = X_train.copy(deep=False)
X_train, y_train, X_validation, y_validation = self._initial_prep(
X_train, y_train, X_validation, y_validation)
self._save_data(X_train, y_train, X_validation, y_validation)
self._set_ml_task(y_train)
self._set_algorithms()
self._set_metric()
self._estimate_training_times()
if self._ml_task in [
BINARY_CLASSIFICATION, MULTICLASS_CLASSIFICATION
]:
self._check_imbalanced(y_train)
tuner = MljarTuner(
self._tuner_params,
self._algorithms,
self._ml_task,
self._validation,
self._explain_level,
self._seed,
)
# not so random step
generated_params = tuner.get_not_so_random_params(X_train, y_train)
self._del_data_variables(X_train, y_train)
# Shuffle generated params
# do not shuffle Baseline, Linear and Decision Trees
dont_shuffle = []
to_shuffle = []
for p in generated_params:
if p["learner"]["model_type"] in [
"Baseline",
"Linear",
"Decision Tree",
]:
dont_shuffle += [p]
else:
to_shuffle += [p]
np.random.shuffle(to_shuffle)
generated_params = dont_shuffle + to_shuffle
for params in generated_params:
self.train_model(params)
# hill climbing
for params in tuner.get_hill_climbing_params(self._models):
self.train_model(params)
self.ensemble_step()
self._fit_time = time.time() - self._start_time
except Exception as e:
raise e
finally:
if self._X_train_path is not None:
self._load_data_variables(X_train)
