def save(self, results_path, model_subpath):
start_time = time.time()
model_path = os.path.join(results_path, model_subpath)
logger.info(f"Save the model {model_path}")
type_of_predictions = (
"validation" if "k_folds" not in self.validation_params else "out_of_folds"
)
predictions_fname = os.path.join(
model_subpath, f"predictions_{type_of_predictions}.csv"
)
self._oof_predictions_fname = os.path.join(results_path, predictions_fname)
predictions = self.get_out_of_folds()
predictions.to_csv(self._oof_predictions_fname, index=False)
saved = [os.path.join(model_subpath, l.get_fname()) for l in self.learners]
with open(os.path.join(model_path, "framework.json"), "w") as fout:
preprocessing = [p.to_json() for p in self.preprocessings]
learners_params = [learner.get_params() for learner in self.learners]
desc = {
"uid": self.uid,
"name": self._name,
"preprocessing": preprocessing,
"learners": learners_params,
"params": self.params,
"saved": saved,
"predictions_fname": predictions_fname,
"metric_name": self.get_metric_name(),
"final_loss": self.get_final_loss(),
"train_time": self.get_train_time(),
"is_stacked": self._is_stacked,
}
if self._threshold is not None:
desc["threshold"] = self._threshold
fout.write(json.dumps(desc, indent=4))
learning_curve_metric = self.learners[0].get_metric_name()
if learning_curve_metric is None:
learning_curve_metric = self.get_metric_name()
LearningCurves.plot(
[l.name for l in self.learners],
learning_curve_metric,
model_path,
trees_in_iteration=self.additional_params.get("trees_in_step"),
)
# call additional metics just to be sure they are computed
self._additional_metrics = self.get_additional_metrics()
AdditionalMetrics.save(
self._additional_metrics, self._ml_task, self.model_markdown(), model_path
)
with open(os.path.join(model_path, "status.txt"), "w") as fout:
fout.write("ALL OK!")
# I'm adding save time to total train time
# there is always save after the training
self.train_time += time.time() - start_time
def save(self, model_path):
logger.info(f"Save the ensemble to {model_path}")
with open(os.path.join(model_path, "ensemble.json"), "w") as fout:
ms = []
for selected in self.selected_models:
ms += [{"model": selected["model"]._name, "repeat": selected["repeat"]}]
desc = {
"name": self._name,
"ml_task": self._ml_task,
"optimize_metric": self._optimize_metric,
"selected_models": ms,
}
if self._threshold is not None:
desc["threshold"] = self._threshold
fout.write(json.dumps(desc, indent=4))
predictions = self.get_out_of_folds()
predictions.to_csv(
os.path.join(model_path, f"predictions_ensemble.csv"), index=False
)
LearningCurves.plot_for_ensemble(self._scores, self.metric.name, model_path)
self._additional_metrics = self.get_additional_metrics()
AdditionalMetrics.save(
self._additional_metrics, self._ml_task, self.model_markdown(), model_path
)
with open(os.path.join(model_path, "status.txt"), "w") as fout:
fout.write("ALL OK!")
def save(self, model_path):
start_time = time.time()
logger.info(f"Save the model {model_path}")
type_of_predictions = ("validation"
if "k_folds" not in self.validation_params else
"out_of_folds")
predictions_fname = os.path.join(
model_path, f"predictions_{type_of_predictions}.csv")
predictions = self.get_out_of_folds()
predictions.to_csv(predictions_fname, index=False)
saved = []
for i, l in enumerate(self.learners):
p = os.path.join(model_path, f"learner_{i+1}.{l.file_extension()}")
# l.save(p)
saved += [p]
with open(os.path.join(model_path, "framework.json"), "w") as fout:
preprocessing = [p.to_json() for p in self.preprocessings]
learners_params = [
learner.get_params() for learner in self.learners
]
desc = {
"uid": self.uid,
"name": self._name,
"preprocessing": preprocessing,
"learners": learners_params,
"params": self.params,
"saved": saved,
"predictions_fname": predictions_fname,
"metric_name": self.get_metric_name(),
"final_loss": self.get_final_loss(),
"train_time": self.get_train_time(),
"is_stacked": self._is_stacked,
}
if self._threshold is not None:
desc["threshold"] = self._threshold
fout.write(json.dumps(desc, indent=4))
LearningCurves.plot(
self.validation.get_n_splits(),
self.get_metric_name(),
model_path,
trees_in_iteration=self.additional_params.get("trees_in_step"),
)
self._additional_metrics = self.get_additional_metrics()
AdditionalMetrics.save(self._additional_metrics, self._ml_task,
self.model_markdown(), model_path)
with open(os.path.join(model_path, "status.txt"), "w") as fout:
fout.write("ALL OK!")
# I'm adding save time to total train time
# there is always save after the training
self.train_time += time.time() - start_time
def test_plot_close(self):
"""
Test if we close plots. To avoid following warning:
RuntimeWarning: More than 20 figures have been opened.
Figures created through the pyplot interface (`matplotlib.pyplot.figure`)
are retained until explicitly closed and may consume too much memory.
"""
for _ in range(
1
): # you can increase the range, for tests speed reason I keep it low
LearningCurves.plot_for_ensemble([3, 2, 1], "random_metrics", ".")
os.remove(LearningCurves.output_file_name)
def save(self, results_path, model_subpath):
model_path = os.path.join(results_path, model_subpath)
logger.info(f"Save the ensemble to {model_path}")
predictions = self.get_out_of_folds()
predictions_fname = os.path.join(model_subpath,
f"predictions_ensemble.csv")
self._oof_predictions_fname = os.path.join(results_path,
predictions_fname)
predictions.to_csv(self._oof_predictions_fname, index=False)
with open(os.path.join(model_path, "ensemble.json"), "w") as fout:
ms = []
for selected in self.selected_models:
ms += [{
"model": selected["model"]._name,
"repeat": selected["repeat"]
}]
desc = {
"name": self._name,
"ml_task": self._ml_task,
"optimize_metric": self._optimize_metric,
"selected_models": ms,
"predictions_fname": predictions_fname,
"metric_name": self.get_metric_name(),
"final_loss": self.get_final_loss(),
"train_time": self.get_train_time(),
"is_stacked": self._is_stacked,
}
if self._threshold is not None:
desc["threshold"] = self._threshold
fout.write(json.dumps(desc, indent=4))
LearningCurves.plot_for_ensemble(self._scores, self.metric.name,
model_path)
# call additional metics just to be sure they are computed
self._additional_metrics = self.get_additional_metrics()
AdditionalMetrics.save(self._additional_metrics, self._ml_task,
self.model_markdown(), model_path)
with open(os.path.join(model_path, "status.txt"), "w") as fout:
fout.write("ALL OK!")
def save(self, model_path):
logger.info(f"Save the model {model_path}")
saved = []
for i, l in enumerate(self.learners):
p = os.path.join(model_path,
f"learner_{i+1}.{l.file_extenstion()}")
l.save(p)
saved += [p]
with open(os.path.join(model_path, "framework.json"), "w") as fout:
preprocessing = [p.to_json() for p in self.preprocessings]
learners_params = [
learner.get_params() for learner in self.learners
]
desc = {
"uid": self.uid,
"name": self._name,
"preprocessing": preprocessing,
"learners": learners_params,
"params": self.params,
"saved": saved,
}
if self._threshold is not None:
desc["threshold"] = self._threshold
fout.write(json.dumps(desc, indent=4))
type_of_predictions = ("validation"
if "k_folds" not in self.validation_params else
"out_of_folds")
predictions = self.get_out_of_folds()
predictions.to_csv(
os.path.join(model_path, f"predictions_{type_of_predictions}.csv"),
index=False,
)
LearningCurves.plot(self.validation.get_n_splits(),
self.get_metric_name(), model_path)
self._additional_metrics = self.get_additional_metrics()
AdditionalMetrics.save(self._additional_metrics, self._ml_task,
self.model_markdown(), model_path)
with open(os.path.join(model_path, "status.txt"), "w") as fout:
fout.write("ALL OK!")