Compare commits
1 Commits
master
...
bugfix/fla
Author | SHA1 | Date |
---|---|---|
Taiga Noumi | 3683b1e093 |
|
@ -24,7 +24,7 @@ result = run_experiment(params,
|
|||
X_train,
|
||||
y_train,
|
||||
X_test,
|
||||
'./wine-quality-{time}',
|
||||
'./wine-quality-{time}',
|
||||
type_of_target='continuous',
|
||||
with_mlflow=True,
|
||||
with_auto_hpo=True)
|
||||
|
|
|
@ -1 +1,5 @@
|
|||
from nyaggle.version import __version__
|
||||
|
||||
__all__ = [
|
||||
"__version__",
|
||||
]
|
||||
|
|
|
@ -1,2 +1,8 @@
|
|||
from nyaggle.ensemble.averaging import averaging, averaging_opt
|
||||
from nyaggle.ensemble.stacking import stacking
|
||||
from nyaggle.ensemble.stacking import stacking
|
||||
|
||||
__all__ = [
|
||||
"averaging",
|
||||
"averaging_opt",
|
||||
"stacking",
|
||||
]
|
||||
|
|
|
@ -1,6 +1,3 @@
|
|||
from collections import namedtuple
|
||||
|
||||
EnsembleResult = namedtuple('EnsembleResult', ['test_prediction', 'oof_prediction', 'score'])
|
||||
|
||||
|
||||
|
||||
|
|
|
@ -1,7 +1,7 @@
|
|||
# pytorch
|
||||
|
||||
try:
|
||||
import torch
|
||||
import torch # noQA
|
||||
_has_torch = True
|
||||
except ImportError:
|
||||
_has_torch = False
|
||||
|
@ -15,7 +15,7 @@ def requires_torch():
|
|||
# mlflow
|
||||
|
||||
try:
|
||||
import mlflow
|
||||
import mlflow # noQA
|
||||
_has_mlflow = True
|
||||
except ImportError:
|
||||
_has_mlflow = False
|
||||
|
@ -30,7 +30,7 @@ def requires_mlflow():
|
|||
|
||||
|
||||
try:
|
||||
import lightgbm
|
||||
import lightgbm # noQA
|
||||
_has_lightgbm = True
|
||||
except ImportError:
|
||||
_has_lightgbm = False
|
||||
|
@ -45,7 +45,7 @@ def requires_lightgbm():
|
|||
|
||||
|
||||
try:
|
||||
import catboost
|
||||
import catboost # noQA
|
||||
_has_catboost = True
|
||||
# TODO check catboost version >= 0.17
|
||||
except ImportError:
|
||||
|
@ -61,7 +61,7 @@ def requires_catboost():
|
|||
|
||||
|
||||
try:
|
||||
import xgboost
|
||||
import xgboost # noQA
|
||||
_has_xgboost = True
|
||||
except ImportError:
|
||||
_has_xgboost = False
|
||||
|
|
|
@ -1,2 +1,10 @@
|
|||
from nyaggle.experiment.experiment import Experiment, add_leaderboard_score
|
||||
from nyaggle.experiment.run import autoprep_gbdt, run_experiment, find_best_lgbm_parameter
|
||||
|
||||
__all__ = [
|
||||
"Experiment",
|
||||
"add_leaderboard_score",
|
||||
"autoprep_gbdt",
|
||||
"run_experiment",
|
||||
"find_best_lgbm_parameter",
|
||||
]
|
||||
|
|
|
@ -1 +1,6 @@
|
|||
from nyaggle.feature.category_encoder.target_encoder import KFoldEncoderWrapper, TargetEncoder
|
||||
|
||||
__all__ = [
|
||||
"KFoldEncoderWrapper",
|
||||
"TargetEncoder",
|
||||
]
|
||||
|
|
|
@ -7,19 +7,19 @@
|
|||
# https://github.com/pfnet-research/xfeat/blob/master/xfeat/helper.py
|
||||
# -----------------------------------------------------------------------------
|
||||
# MIT License
|
||||
#
|
||||
#
|
||||
# Copyright (c) 2020 Preferred Networks, Inc.
|
||||
#
|
||||
#
|
||||
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
# of this software and associated documentation files (the "Software"), to deal
|
||||
# in the Software without restriction, including without limitation the rights
|
||||
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
# copies of the Software, and to permit persons to whom the Software is
|
||||
# furnished to do so, subject to the following conditions:
|
||||
#
|
||||
#
|
||||
# The above copyright notice and this permission notice shall be included in all
|
||||
# copies or substantial portions of the Software.
|
||||
#
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
|
@ -71,7 +71,8 @@ def aggregation(
|
|||
Used to aggregate values for the groupby.
|
||||
agg_methods:
|
||||
List of function or function names, e.g. ['mean', 'max', 'min', numpy.mean].
|
||||
Do not use a lambda function because the name attribute of the lambda function cannot generate a unique string of column names in <lambda>.
|
||||
Do not use a lambda function because the name attribute of the lambda function
|
||||
cannot generate a unique string of column names in <lambda>.
|
||||
Returns:
|
||||
Tuple of output dataframe and new column names.
|
||||
"""
|
||||
|
|
|
@ -1 +1,5 @@
|
|||
from nyaggle.feature.nlp.bert import BertSentenceVectorizer
|
||||
|
||||
__all__ = [
|
||||
"BertSentenceVectorizer",
|
||||
]
|
||||
|
|
|
@ -58,7 +58,7 @@ class BertSentenceVectorizer(BaseFeaturizer):
|
|||
self.tokenizer = transformers.BertJapaneseTokenizer.from_pretrained(pretrained_model_name)
|
||||
self.model = transformers.BertModel.from_pretrained(pretrained_model_name)
|
||||
else:
|
||||
raise ValueError('Specified language type () is invalid.'.format(lang))
|
||||
raise ValueError(f'Specified language type ({lang}) is invalid.')
|
||||
|
||||
self.lang = lang
|
||||
self.n_components = n_components
|
||||
|
|
|
@ -1 +1,8 @@
|
|||
from nyaggle.feature_store.feature_store import cached_feature, save_feature, load_feature, load_features
|
||||
|
||||
__all__ = [
|
||||
"cached_feature",
|
||||
"save_feature",
|
||||
"load_feature",
|
||||
"load_features"
|
||||
]
|
||||
|
|
|
@ -1 +1,6 @@
|
|||
from nyaggle.hyper_parameters.parameters import get_hyperparam_byname, list_hyperparams
|
||||
|
||||
__all__ = [
|
||||
"get_hyperparam_byname",
|
||||
"list_hyperparams",
|
||||
]
|
||||
|
|
|
@ -1,7 +1,7 @@
|
|||
parameters = [
|
||||
{
|
||||
"name": "ieee-2019-17th",
|
||||
"url": "https://nbviewer.jupyter.org/github/tmheo/IEEE-Fraud-Detection-17th-Place-Solution/blob/master/notebook/IEEE-17th-Place-Solution-CatBoost-Ensemble.ipynb",
|
||||
"url": "https://nbviewer.jupyter.org/github/tmheo/IEEE-Fraud-Detection-17th-Place-Solution/blob/master/notebook/IEEE-17th-Place-Solution-CatBoost-Ensemble.ipynb", # noQA
|
||||
"competition": "ieee-fraud-detection",
|
||||
"rank": 17,
|
||||
"metric": "auc",
|
||||
|
@ -42,4 +42,3 @@ parameters = [
|
|||
}
|
||||
},
|
||||
]
|
||||
|
||||
|
|
|
@ -28,7 +28,7 @@ parameters = [
|
|||
},
|
||||
{
|
||||
"name": "ieee-2019-17th",
|
||||
"url": "https://nbviewer.jupyter.org/github/tmheo/IEEE-Fraud-Detection-17th-Place-Solution/blob/master/notebook/IEEE-17th-Place-Solution-LightGBM.ipynb",
|
||||
"url": "https://nbviewer.jupyter.org/github/tmheo/IEEE-Fraud-Detection-17th-Place-Solution/blob/master/notebook/IEEE-17th-Place-Solution-LightGBM.ipynb", # noQA
|
||||
"competition": "ieee-fraud-detection",
|
||||
"rank": 17,
|
||||
"metric": "auc",
|
||||
|
@ -98,7 +98,7 @@ parameters = [
|
|||
# 2019, Santander Customer Transaction Prediction
|
||||
{
|
||||
"name": "santander-2019-2nd",
|
||||
"url": "https://github.com/KazukiOnodera/santander-customer-transaction-prediction/blob/master/py/990_2nd_place_solution_golf.py",
|
||||
"url": "https://github.com/KazukiOnodera/santander-customer-transaction-prediction/blob/master/py/990_2nd_place_solution_golf.py", # noQA
|
||||
"competition": "santander-customer-transaction-prediction",
|
||||
"rank": 2,
|
||||
"metric": "auc",
|
||||
|
@ -120,7 +120,7 @@ parameters = [
|
|||
},
|
||||
{
|
||||
"name": "santander-2019-5th",
|
||||
"url": "https://github.com/tnmichael309/Kaggle-Santander-Customer-Transaction-Prediction-5th-Place-Partial-Solution/blob/master/notebooks/LGB%20Model.ipynb",
|
||||
"url": "https://github.com/tnmichael309/Kaggle-Santander-Customer-Transaction-Prediction-5th-Place-Partial-Solution/blob/master/notebooks/LGB%20Model.ipynb", # noQA
|
||||
"competition": "santander-customer-transaction-prediction",
|
||||
"rank": 5,
|
||||
"metric": "auc",
|
||||
|
@ -193,7 +193,7 @@ parameters = [
|
|||
# 2018, Microsoft Malware Prediction
|
||||
{
|
||||
"name": "microsoft-2018-2nd",
|
||||
"url": "https://github.com/imor-de/microsoft_malware_prediction_kaggle_2nd/blob/master/code/7_Submission_M2.ipynb",
|
||||
"url": "https://github.com/imor-de/microsoft_malware_prediction_kaggle_2nd/blob/master/code/7_Submission_M2.ipynb", # noQA
|
||||
"competition": "microsoft-malware-prediction",
|
||||
"rank": 2,
|
||||
"metric": "auc",
|
||||
|
|
|
@ -1 +1,7 @@
|
|||
from nyaggle.testing.util import *
|
||||
from nyaggle.testing.util import make_classification_df, make_regression_df, get_temp_directory
|
||||
|
||||
__all__ = [
|
||||
"make_classification_df",
|
||||
"make_regression_df",
|
||||
"get_temp_directory",
|
||||
]
|
||||
|
|
|
@ -60,8 +60,6 @@ def make_regression_df(n_samples: int = 1024,
|
|||
return X, y
|
||||
|
||||
|
||||
|
||||
|
||||
@contextmanager
|
||||
def get_temp_directory() -> str:
|
||||
path = None
|
||||
|
@ -71,4 +69,3 @@ def get_temp_directory() -> str:
|
|||
finally:
|
||||
if path:
|
||||
shutil.rmtree(path, ignore_errors=True)
|
||||
|
||||
|
|
|
@ -1,3 +1,10 @@
|
|||
from nyaggle.util.plot_importance import plot_importance
|
||||
from nyaggle.util.traits import is_instance, is_gbdt_instance
|
||||
from nyaggle.util.submission import make_submission_df
|
||||
|
||||
__all__ = [
|
||||
"plot_importance",
|
||||
"is_instance",
|
||||
"is_gbdt_instance",
|
||||
"make_submission_df",
|
||||
]
|
||||
|
|
|
@ -63,7 +63,7 @@ def is_instance(obj, class_path_str: Union[str, List, Tuple]) -> bool:
|
|||
# Check module exists
|
||||
try:
|
||||
spec = importlib.util.find_spec(module_name)
|
||||
except:
|
||||
except (ValueError, AttributeError, ModuleNotFoundError):
|
||||
spec = None
|
||||
if spec is None:
|
||||
continue
|
||||
|
|
|
@ -2,3 +2,15 @@ from nyaggle.validation.cross_validate import cross_validate
|
|||
from nyaggle.validation.adversarial_validate import adversarial_validate
|
||||
from nyaggle.validation.split import \
|
||||
check_cv, TimeSeriesSplit, SlidingWindowSplit, Take, Nth, Skip, StratifiedGroupKFold
|
||||
|
||||
__all__ = [
|
||||
"cross_validate",
|
||||
"adversarial_validate",
|
||||
"check_cv",
|
||||
"TimeSeriesSplit",
|
||||
"SlidingWindowSplit",
|
||||
"Take",
|
||||
"Nth",
|
||||
"Skip",
|
||||
"StratifiedGroupKFold",
|
||||
]
|
||||
|
|
Loading…
Reference in New Issue