Skip to content

more detail for calculate features #61

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
threeTrave wants to merge 2 commits into
base: master
Choose a base branch
from
Open

more detail for calculate features #61

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a5ac200
more detail for calculate features
threeTrave May 30, 2025
34204b3
Fixed LightGBM verbosity issue
threeTrave May 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions openfe/FeatureSelector.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -234,7 +234,7 @@ def get_metric(self):

def get_estimator(self):
if self.estimator is None:
params = {'n_jobs': self.n_jobs, 'importance_type': 'gain', 'n_estimators': 200, "verbose": 1 if self.verbose else -1 }
params = {'n_jobs': self.n_jobs, 'importance_type': 'gain', 'n_estimators': 200, "verbose": -1 }
if self.task == 'classification':
self.estimator = lgb.LGBMClassifier(**params)
else:
Expand Down Expand Up @@ -530,7 +530,7 @@ def stage2_select(self):
self.myprint("Finish data processing.")
if self.stage2_params is None:
params = {"n_estimators": 1000, "importance_type": "gain", "num_leaves": 16,
"seed": 1, "n_jobs": self.n_jobs, "verbose": 1 if self.verbose else -1}
"seed": 1, "n_jobs": self.n_jobs, "verbose": -1}
else:
params = self.stage2_params
if self.metric is not None:
Expand Down Expand Up @@ -609,7 +609,7 @@ def _evaluate(self, data_temp, candidate_feature, train_y, val_y, train_init, va
val_x = pd.DataFrame(data_temp[candidate_feature].loc[val_y.index])
if self.stage1_metric == 'predictive':
params = {"n_estimators": 100, "importance_type": "gain", "num_leaves": 16,
"seed": 1, "deterministic": True, "n_jobs": 1, "verbose": 1 if self.verbose else -1 }
"seed": 1, "deterministic": True, "n_jobs": 1, "verbose": -1 }
if self.metric is not None:
params.update({"metric": self.metric})
if self.task == 'classification':
Expand Down
6 changes: 3 additions & 3 deletions openfe/openfe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -406,7 +406,7 @@ def get_init_score(self, init_scores, use_train=False):
label = self.label.copy()

params = {"n_estimators": 10000, "learning_rate": 0.1, "metric": self.metric,
"seed": self.seed, "n_jobs": self.n_jobs, "verbose": 1 if self.verbose else -1 }
"seed": self.seed, "n_jobs": self.n_jobs, "verbose": -1}
if self.task == "regression":
gbm = lgb.LGBMRegressor(**params)
else:
Expand Down Expand Up @@ -536,7 +536,7 @@ def stage2_select(self):
self.myprint("Finish data processing.")
if self.stage2_params is None:
params = {"n_estimators": 1000, "importance_type": "gain", "num_leaves": 16,
"seed": 1, "n_jobs": self.n_jobs, "verbose": 1 if self.verbose else -1 }
"seed": 1, "n_jobs": self.n_jobs, "verbose": -1 }
else:
params = self.stage2_params
if self.metric is not None:
Expand Down Expand Up @@ -602,7 +602,7 @@ def _evaluate(self, candidate_feature, train_y, val_y, train_init, val_init, ini
val_x = pd.DataFrame(candidate_feature.data.loc[val_y.index])
if self.stage1_metric == 'predictive':
params = {"n_estimators": 100, "importance_type": "gain", "num_leaves": 16,
"seed": 1, "deterministic": True, "n_jobs": 1, "verbose": 1 if self.verbose else -1 }
"seed": 1, "deterministic": True, "n_jobs": 1, "verbose": -1}
if self.metric is not None:
params.update({"metric": self.metric})
if self.task == 'classification':
Expand Down
13 changes: 9 additions & 4 deletions openfe/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,9 @@
import traceback
from .FeatureGenerator import Node, FNode
from concurrent.futures import ProcessPoolExecutor
from concurrent.futures import ProcessPoolExecutor, as_completed
import pandas as pd
import numpy as np

from tqdm import tqdm

def tree_to_formula(tree):
if isinstance(tree, Node):
Expand Down Expand Up @@ -135,8 +135,13 @@ def transform(X_train, X_test, new_features_list, n_jobs, name=""):
n_train = len(X_train)
ex = ProcessPoolExecutor(n_jobs)
results = []
for feature in new_features_list:
results.append(ex.submit(_cal, feature, n_train))
with tqdm(
total=len(new_features_list), desc="Calculating new features..."
) as progress_bar:
results = [ex.submit(_cal, feature, n_train) for feature in new_features_list]
for feature in as_completed(results):
progress_bar.set_postfix(feature=feature.result()[-1])
progress_bar.update(1)
ex.shutdown(wait=True)
_train = []
_test = []
Expand Down