def load_from_run_id(run_id: str, to_rank: False):
oof = Data.load(f'../output/pred/{run_id}-train.pkl')
pred = Data.load(f'../output/pred/{run_id}-test.pkl')
if to_rank:
oof = rankdata(oof) / len(oof)
pred = rankdata(pred) / len(pred)
return (oof, pred)
def load(self):
X_train = Data.load(
join(self.output_dir, f"X_train_{self.run_name}.pkl"))
y_train = Data.load(
join(self.output_dir, f"y_train_{self.run_name}.pkl"))
X_test = Data.load(join(self.output_dir,
f"X_test_{self.run_name}.pkl"))
return X_train, X_test, y_train
def load_from_run_id(run_id: str, to_rank: False):
oof = Data.load(f'../output/pred/{run_id}-train.pkl')
pred = Data.load(f'../output/pred/{run_id}-test.pkl')
if run_id in ('run015'):
oof = oof.reshape(-1, )
pred = pred.reshape(-1, )
if to_rank:
oof = rankdata(oof) / len(oof)
pred = rankdata(pred) / len(pred)
return (oof, pred)
def submission(self) -> None:
pred = Data.load(f"../output/pred/{self.run_name}-test.pkl")
sub = pd.read_csv(self.sample_submission)
if self.evaluation_metric == "log_loss":
sub[self.cols_definition["target_col"]] = np.argmax(pred, axis=1)
else:
oof = Data.load(f"../output/pred/{self.run_name}-train.pkl")
oof = np.array([convert(v) for v in oof])
pred = np.array([convert(v) for v in pred])
sub[self.cols_definition["target_col"]] = pred
sub[self.cols_definition["target_col"]] = sub[
self.cols_definition["target_col"]].astype(float)
sub.to_csv(f"../output/submissions/submission_{self.run_name}.csv",
index=False)
def load_oof_from_run_id(run_id: str, to_rank: False):
oof = Data.load(f'../output/pred/{run_id}-train.pkl')
if run_id in ('run091', 'run092', 'run097'):
oof = oof.reshape(-1, )
if to_rank:
oof = rankdata(oof) / len(oof)
return oof
def load_pred_from_run_id(run_id: str, to_rank: False):
pred = Data.load(f'../output/pred/{run_id}-test.pkl')
if run_id in ('run091', 'run092', 'run097'):
pred = pred.reshape(-1, )
if to_rank:
pred = rankdata(pred) / len(pred)
return pred
def submission(self):
pred = Data.load(f'../output/pred/{self.run_name}-test.pkl')
sub = pd.read_csv(self.sample_submission)
if self.advanced and 'predict_exp' in self.advanced:
sub[self.cols_definition['target_col']] = np.expm1(pred)
else:
sub[self.cols_definition['target_col']] = pred
sub.to_csv(f'../output/submissions/submission_{self.run_name}.csv', index=False)
def submission(self) -> None:
pred = Data.load(f"../output/pred/{self.run_name}-test.pkl")
sub = pd.read_csv(self.sample_submission)
if self.advanced and "predict_exp" in self.advanced:
sub[self.cols_definition["target_col"]] = np.exp(pred)
else:
sub[self.cols_definition["target_col"]] = pred
sub.to_csv(f"../output/submissions/submission_{self.run_name}.csv",
index=False)
def __init__(self, configs: dict, cv):
self.exp_name = configs['exp_name']
self.run_name = configs['run_name']
self.run_id = None
self.fe_name = configs['fe_name']
self.X_train = Data.load(f"../input/X_train_{configs['fe_name']}.pkl")
self.y_train = Data.load(f"../input/y_train_{configs['fe_name']}.pkl")
self.X_test = Data.load(f"../input/X_test_{configs['fe_name']}.pkl")
self.evaluation_metric = configs['evaluation_metric']
self.params = configs['params']
self.cols_definition = configs['cols_definition']
self.cv = cv
self.sample_submission = configs['data']['sample_submission']
self.description = configs['description']
self.advanced = configs['advanced'] if 'advanced' in configs else None
if configs['model_name'] in models_map.keys():
self.model_cls = models_map[configs['model_name']]
else:
raise ValueError
def __init__(self, configs: Dict, cv) -> None: # type: ignore
self.exp_name = configs["exp_name"]
self.run_name = configs["run_name"]
self.run_id = None
self.fe_name = configs["fe_name"]
self.X_train = Data.load(f"../input/X_train_{configs['fe_name']}.pkl")
self.y_train = Data.load(f"../input/y_train_{configs['fe_name']}.pkl")
self.X_test = Data.load(f"../input/X_test_{configs['fe_name']}.pkl")
self.evaluation_metric = configs["evaluation_metric"]
self.params = configs["params"]
self.cols_definition = configs["cols_definition"]
self.cv = cv
self.sample_submission = configs["data"]["sample_submission"]
self.description = configs["description"]
self.advanced = configs["advanced"] if "advanced" in configs else None
if configs["model_name"] in models_map.keys():
self.model_cls = models_map[configs["model_name"]]
else:
raise ValueError
import japanize_matplotlib
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.model_selection import train_test_split
from ayniy.utils import Data
if __name__ == '__main__':
oof = Data.load('../output/pred/run003-train.pkl')
train_player = pd.read_csv('../input/train_player.csv')
train_pitch = pd.read_csv('../input/train_pitch.csv')
train_pitch = train_pitch[train_pitch['試合種別詳細'] != 'パ・リーグ公式戦'].reset_index(
drop=True)
# 投手情報の紐付け
train = pd.merge(train_pitch,
train_player,
left_on=['年度', '投手ID'],
right_on=['年度', '選手ID'],
how='inner')
# 打者情報の紐付け
train = pd.merge(train,
train_player,
left_on=['年度', '打者ID'],
right_on=['年度', '選手ID'],
how='inner',
suffixes=('_p', '_b'))
X_train, _, _, _ = train_test_split(train.drop('試合種別詳細', axis=1),
import numpy as np
import pandas as pd
import yaml
from ayniy.model.model_cat import ModelCatRegressor
from ayniy.model.runner import Runner
from ayniy.utils import Data
X_train = Data.load('../input/X_train_00.pkl')
y_train = Data.load('../input/y_train.pkl')
X_test = Data.load('../input/X_test_00.pkl')
X_train.drop(['fiscal_year'], axis=1, inplace=True)
X_test.drop(['fiscal_year'], axis=1, inplace=True)
y_train = np.log(np.sqrt(y_train))
f = open("configs/fe_00.yml", "r+")
configs = yaml.load(f)
categorical_cols = configs['cols_definition']['categorical_col']
params_cat = {
'depth': 6,
'learning_rate': 0.1,
'iterations': 10000,
'loss_function': 'RMSE',
'eval_metric': 'RMSE',
'random_seed': 777,
'allow_writing_files': False,
'task_type': "CPU",
'early_stopping_rounds': 50
from sklearn.metrics import roc_auc_score, confusion_matrix
from ayniy.utils import Data
if __name__ == '__main__':
pred = Data.load('../output/pred/run003-test.pkl')
y_test = Data.load('../input/y_test_fe003.pkl')
print(roc_auc_score(y_test, pred))
print(confusion_matrix(y_test, (pred > 0.5).astype(int)))
else:
pred += d[1] * (1 - sum(weights))
Data.dump(pred, f'../output/pred/{run_name}-test.pkl')
return pred
def make_submission(pred, run_name: str):
sub = pd.read_csv('../input/solafune-light/UploadFileTemplate.csv')
sub['LandPrice'] = np.expm1(pred)
sub.to_csv(f'../output/submissions/submission_{run_name}.csv', index=False)
run_ids = [
'run004',
'run005',
]
run_name = 'weight001'
if __name__ == '__main__':
y_train = Data.load('../input/pickle/y_train_fe000.pkl')
data = [load_from_run_id(ri, to_rank=False) for ri in run_ids]
for d in data:
print(np.sqrt(mean_squared_error(y_train, d[0])))
init_state = [round(1 / len(data), 3) for _ in range(len(data) - 1)]
result = minimize(f, init_state, method='Nelder-Mead')
print('optimized CV: ', result['fun'])
print('w: ', result['x'])
make_submission(make_predictions(data, result['x']), run_name)
def load_model(self):
model_path = os.path.join('../output/model',
f'{self.run_fold_name}.model')
self.model = Data.load(model_path)
"../input/feather/count_encoding_interact.ftr",
"../input/feather/aggregation.ftr",
"../input/feather/target_encoding.ftr",
],
target_col=target_col,
)
X_train_u = features.X_train
y_train = features.y_train
X_test_u = features.X_test
fe_id_u = 'fe006'
run_id = 'run021'
N_FEATURES = 300
X_train_u = Data.load(f'../input/pickle/X_train_{fe_id_u}.pkl')
X_test_u = Data.load(f'../input/pickle/X_test_{fe_id_u}.pkl')
fi = pd.read_csv(f'../output/importance/{run_id}-fi.csv')['Feature'][:N_FEATURES]
X_train_u = X_train_u[fi]
X_test_u = X_test_u[fi].reset_index(drop=True)
X_train_u.columns = [f'u_{c}' for c in fi]
X_test_u.columns = [f'u_{c}' for c in fi]
fe_id = 'fe_siavrez'
X_train = Data.load(f'../input/pickle/X_train_{fe_id}.pkl')
X_test = Data.load(f'../input/pickle/X_test_{fe_id}.pkl')
print(X_train.shape, X_train_u.shape)
print(X_test.shape, X_test_u.shape)
X_train = pd.concat([X_train, X_train_u], axis=1)
def load_oof_from_run_id(run_id: str, to_rank: False):
oof = Data.load(f'../output/pred/{run_id}-train.pkl')
if to_rank:
oof = rankdata(oof) / len(oof)
return oof
def load_pred_from_run_id(run_id: str, to_rank: False):
pred = Data.load(f'../output/pred/{run_id}-test.pkl')
if to_rank:
pred = rankdata(pred) / len(pred)
return pred
def load_pred_from_run_id(run_id: str):
pred = Data.load(f'../output/pred/{run_id}-test.pkl')
if run_id in ('run013', 'run014', 'run015'):
pred = pred.reshape(-1, )
return pred
def load_model(self) -> None:
model_path = os.path.join("../output/model", f"{self.run_fold_name}.model")
self.model = Data.load(model_path)
def train_fold(self, i_fold: int) -> Tuple[Any, Any, Any, Any]:
"""クロスバリデーションでのfoldを指定して学習・評価を行う
他のメソッドから呼び出すほか、単体でも確認やパラメータ調整に用いる
:param i_fold: foldの番号（すべてのときには'all'とする）
:return: （モデルのインスタンス、レコードのインデックス、予測値、評価によるスコア）のタプル
"""
# 学習データの読込
X_train = self.X_train
y_train = self.y_train
# 残差の設定
if self.advanced and "ResRunner" in self.advanced:
oof = Data.load(self.advanced["ResRunner"]["oof"])
X_train["res"] = (y_train - oof).abs()
# 学習データ・バリデーションデータをセットする
tr_idx, va_idx = self.load_index_fold(i_fold)
X_tr, y_tr = X_train.iloc[tr_idx], y_train.iloc[tr_idx]
X_val, y_val = X_train.iloc[va_idx], y_train.iloc[va_idx]
# 残差でダウンサンプリング
if self.advanced and "ResRunner" in self.advanced:
X_tr = X_tr.loc[(
X_tr["res"] <
self.advanced["ResRunner"]["res_threshold"]).values]
y_tr = y_tr.loc[(
X_tr["res"] <
self.advanced["ResRunner"]["res_threshold"]).values]
print(X_tr.shape)
X_tr.drop("res", axis=1, inplace=True)
X_val.drop("res", axis=1, inplace=True)
# Pseudo Lebeling
if self.advanced and "PseudoRunner" in self.advanced:
y_test_pred = Data.load(
self.advanced["PseudoRunner"]["y_test_pred"])
if "pl_threshold" in self.advanced["PseudoRunner"]:
X_add = self.X_test.loc[
(y_test_pred < self.
advanced["PseudoRunner"]["pl_threshold"])
| (y_test_pred > 1 -
self.advanced["PseudoRunner"]["pl_threshold"])]
y_add = pd.DataFrame(y_test_pred).loc[
(y_test_pred < self.
advanced["PseudoRunner"]["pl_threshold"])
| (y_test_pred > 1 -
self.advanced["PseudoRunner"]["pl_threshold"])]
y_add = pd.DataFrame(
([1 if ya > 0.5 else 0 for ya in y_add[0]]))
elif "pl_threshold_neg" in self.advanced["PseudoRunner"]:
X_add = self.X_test.loc[
(y_test_pred < self.
advanced["PseudoRunner"]["pl_threshold_neg"])
| (y_test_pred > self.
advanced["PseudoRunner"]["pl_threshold_pos"])]
y_add = pd.DataFrame(y_test_pred).loc[
(y_test_pred < self.
advanced["PseudoRunner"]["pl_threshold_neg"])
| (y_test_pred > self.
advanced["PseudoRunner"]["pl_threshold_pos"])]
y_add = pd.DataFrame(
([1 if ya > 0.5 else 0 for ya in y_add[0]]))
else:
X_add = self.X_test
y_add = pd.DataFrame(y_test_pred)
print(f"added X_test: {len(X_add)}")
X_tr = pd.concat([X_tr, X_add])
y_tr = pd.concat([y_tr, y_add])
# 学習を行う
model = self.build_model(i_fold)
model.train(X_tr, y_tr, X_val, y_val, self.X_test) # type: ignore
# バリデーションデータへの予測・評価を行う
pred_val = model.predict(X_val)
if self.evaluation_metric == "log_loss":
score = log_loss(y_val, pred_val, eps=1e-15, normalize=True)
elif self.evaluation_metric == "mean_absolute_error":
score = mean_absolute_error(y_val, pred_val)
elif self.evaluation_metric == "rmse":
score = np.sqrt(mean_squared_error(y_val, pred_val))
elif self.evaluation_metric == "auc":
score = roc_auc_score(y_val, pred_val)
elif self.evaluation_metric == "prauc":
score = average_precision_score(y_val, pred_val)
# モデル、インデックス、予測値、評価を返す
return model, va_idx, pred_val, score
# sub = pd.read_csv('../input/atmaCup5__sample_submission.csv')
# train = pd.read_csv('../input/train.csv')
# test = pd.read_csv('../input/test.csv')
# fitting = pd.read_csv('../input/fitting.csv')
# train = pd.merge(train, fitting, on='spectrum_id', how='inner')
# test = pd.merge(test, fitting, on='spectrum_id', how='inner')
# train.to_csv('../input/train_fitting.csv', index=False)
# test.to_csv('../input/test_fitting.csv', index=False)
add_tr = pd.read_csv('../input/additional_features_train.csv')
add_te = pd.read_csv('../input/additional_features_test.csv')
fe005_tr = Data.load('../input/X_train_fe005.pkl')
fe005_te = Data.load('../input/X_test_fe005.pkl')
# fe001_tr = Data.load('../input/X_train_fe001.pkl')
# fe001_te = Data.load('../input/X_test_fe001.pkl')
# top10_tr = Data.load('../input/X_train_fe004_top10.pkl')
# top10_te = Data.load('../input/X_test_fe004_top10.pkl')
# top10_tr, top10_te = standerize(top10_tr, top10_te, {'encode_col': top10_tr.columns})
# print(top10_tr.head())
train_fitting_ef_add = pd.concat([fe005_tr, add_tr], axis=1)
test_fitting_ef_add = pd.concat([fe005_te, add_te], axis=1)
fe_name = 'fe005_add'
Data.dump(train_fitting_ef_add, f'../input/X_train_{fe_name}.pkl')
def load_oof_from_run_id(run_id: str):
oof = Data.load(f'../output/pred/{run_id}-train.pkl')
if run_id in ('run013', 'run014', 'run015'):
oof = oof.reshape(-1, )
return oof
from ayniy.utils import Data
from sklearn.preprocessing import StandardScaler
if __name__ == "__main__":
fe_id = "fe000"
fe_name = f"{fe_id}_nn_small"
X_train = Data.load(f"../input/pickle/X_train_{fe_id}.pkl")
y_train = Data.load(f"../input/pickle/y_train_{fe_id}.pkl")
X_test = Data.load(f"../input/pickle/X_test_{fe_id}.pkl")
del_col = []
for c in X_train.columns:
X_train[c].fillna(-1, inplace=True)
X_test[c].fillna(-1, inplace=True)
try:
prep = StandardScaler()
X_train[c] = prep.fit_transform(X_train[[c]])
X_test[c] = prep.transform(X_test[[c]])
except ValueError:
del_col.append(c)
print(del_col)
print(len(del_col))
X_train.drop(del_col, axis=1, inplace=True)
X_test.drop(del_col, axis=1, inplace=True)
print(X_train.shape)
X_train = X_train.loc[:100]
y_train = y_train.loc[:100]
ython select_features.py --n 100
"""
import argparse
import pandas as pd
from ayniy.utils import Data
parser = argparse.ArgumentParser()
parser.add_argument('--n')
args = parser.parse_args()
fe_id = 'fe005'
run_id = 'run046'
N_FEATURES = int(args.n)
fe_name = f'fe005_top{N_FEATURES}'
X_train = Data.load(f'../input/X_train_{fe_id}.pkl')
y_train = Data.load(f'../input/y_train_{fe_id}.pkl')
X_test = Data.load(f'../input/X_test_{fe_id}.pkl')
fi = pd.read_csv(
f'../output/importance/{run_id}-fi.csv')['Feature'][:N_FEATURES]
X_train = X_train[fi]
X_test = X_test[fi]
Data.dump(X_train, f'../input/X_train_{fe_name}.pkl')
Data.dump(y_train, f'../input/y_train_{fe_name}.pkl')
Data.dump(X_test, f'../input/X_test_{fe_name}.pkl')
import pandas as pd
from ayniy.utils import Data
if __name__ == '__main__':
ef_tr = pd.read_csv('../input/efficient_tr.csv')
ef_te = pd.read_csv('../input/efficient_te.csv')
fe001_top500_tr = Data.load('../input/X_train_fe001_top500.pkl')
fe001_top500_te = Data.load('../input/X_test_fe001_top500.pkl')
train_tag = pd.concat([fe001_top500_tr, ef_tr], axis=1)
test_tag = pd.concat([fe001_top500_te, ef_te], axis=1)
fe_name = 'fe001_top500_ef'
Data.dump(train_tag, f'../input/X_train_{fe_name}.pkl')
Data.dump(test_tag, f'../input/X_test_{fe_name}.pkl')
