warnings.filterwarnings("ignore")
if __name__ == '__main__':
test_mode = 0 # 0: FullTest / 1: run_rest (5000) / 2: train_sampler
base_models = [
MyLightGBM(param_pattern=0), # 深い / baggingあり
MyLightGBM(param_pattern=1), # 普通
MyLightGBM(param_pattern=2), # 超浅い
Kernels('Kernel_nffm'),
Kernels('Kernel_xdeepfm'),
#MySklearn('RandomForest'),
#MySklearn('ExtraTrees'),
#MyXGBoost(),
#MyCatBoost(),
]
stacker = LogisticRegression()
stack = Ensemble(n_splits=3,
n_stacks=5,
stacker=stacker,
base_models=base_models,
use_rank=True,
use_adv_train=False,
corr_threshold=1.0,
test_mode=test_mode)
val_score, oof, pred, df_test = stack.fit_predict()
save_commits(df_test, pred, "./commits/stack_{}.csv".format(val_score))
'max_depth': 6,
'n_estimators': 1000,
'learning_rate': 0.025,
'subsample': 0.9
}
models = {
"LGB-1": LGBMClassifier(**lgb_params),
"XGB-1": XGBClassifier(**xgb_params),
"LGB-2": LGBMClassifier(**lgb_params2),
#"LGB-3": LGBMClassifier(**lgb_params3),
"XGB-2": XGBClassifier(**xgb_params2),
#"CAT": CatBoostClassifier(**cat_params),
#"GBM": GradientBoostingClassifier(**gb_params),
#"RF": RandomForestClassifier(**rf_params),
#"ET": ExtraTreesClassifier(**et_params),
#"ABC": AdaBoostClassifier(n_estimators=100),
}
start = time.time()
stack = Ensemble(4,
models.values(),
stacker=SGDClassifier(loss="log", max_iter=1000))
y_pred = stack.fit_predict(X, y, X_test)
print("Finished ensembling in %.2f seconds" % (time.time() - start))
sub = pd.DataFrame()
sub['id'] = id_test
sub['target'] = y_pred
sub.to_csv("%s.csv" % ("-".join(models.keys())), index=False)
"PassengerId": test["PassengerId"],
"Survived": pre
})
print("write submit file: *.csv")
submit_file = '../sub/{}.csv'.format(datetime.now().strftime('%Y%m%d_%H_%M'))
submission.to_csv(submit_file, encoding="utf-8", index=False)
if __name__ == '__main__':
train = pd.read_csv('../data/feature_train.csv')
test = pd.read_csv('../data/feature_test.csv')
base_models = [svc, rf, xgb, lgb, rf, gbm]
stack = Ensemble(n_splits=8,
stacker=DecisionTreeClassifier(),
base_models=base_models)
# Stacker score: 0.8239 LB: 0.779
clfs = [DecisionTreeClassifier(),
XGBClassifier(n_estimators=100, max_depth=4, min_child_weight=2),
RandomForestClassifier(n_estimators=140, max_depth=4, min_samples_split=6, min_samples_leaf=4, n_jobs=4),
GradientBoostingClassifier(n_estimators=140, max_depth=4, min_samples_split=6, min_samples_leaf=4)]
ensemble = Ensemble(clfs, rf)
prediction = ensemble.fit_predict(x_train, y_train, x_test)
submit(prediction)
