def stack_catboost():
"""Стекинг catboost."""
x_train = add_stacking_feat(load_oof())
_, y_train = processing.train_set()
x_test = add_stacking_feat(load_sub())
x_test.columns = x_train.columns
x_train.drop(DROP, axis=1, inplace=True)
x_test.drop(DROP, axis=1, inplace=True)
pool_test = catboost.Pool(data=x_test,
label=None,
cat_features=None,
weight=None)
y_oof = pd.Series(0, index=x_train.index, name="oof_y")
y_pred = pd.Series(0, index=x_test.index, name="time_to_failure")
trees = []
scores = []
feat_importance = 0
for index_train, index_valid in K_FOLDS.split(x_train):
pool_train = catboost.Pool(data=x_train.iloc[index_train],
label=y_train.iloc[index_train],
cat_features=None,
weight=None)
pool_valid = catboost.Pool(data=x_train.iloc[index_valid],
label=y_train.iloc[index_valid],
cat_features=None,
weight=None)
clf = catboost.CatBoostRegressor(**CLF_PARAMS)
clf.fit(
X=pool_train,
eval_set=[pool_valid],
)
trees.append(clf.tree_count_)
scores.append(clf.best_score_['validation_0']['MAE'])
y_oof.iloc[index_valid] = clf.predict(pool_valid)
y_pred += clf.predict(pool_test) / K_FOLDS.get_n_splits()
feat_importance += pd.DataFrame(
clf.get_feature_importance(prettified=True),
columns=["name", "value"
]).set_index("name") / K_FOLDS.get_n_splits()
LOGGER.info(f"Количество деревьев: {sorted(trees)}")
LOGGER.info(
f"Среднее количество деревьев: {np.mean(trees):.0f} +/- {np.std(trees):.0f}"
)
LOGGER.info(f"MAE на кроссвалидации: " + str(np.round(sorted(scores), 5)))
LOGGER.info(
f"MAE среднее: {np.mean(scores):0.3f} +/- {np.std(scores):0.3f}")
stamp = (
f"{time.strftime('%Y-%m-%d_%H-%M')}_"
f"{np.mean(scores):0.3f}_"
f"{np.mean(scores) + np.std(scores) * 2 / len(scores) ** 0.5:0.3f}_stk"
)
y_oof.to_csv(conf.DATA_PROCESSED + f"oof_{stamp}.csv", header=True)
y_pred.to_csv(conf.DATA_PROCESSED + f"sub_{stamp}.csv", header=True)
print(feat_importance.sort_values("value", ascending=False))
def train_light_gbm():
"""Обучение LightGBM RF."""
x_train, y_train = processing.train_set()
x_test = processing.test_set()
x_train.drop(DROP, axis=1, inplace=True)
x_test.drop(DROP, axis=1, inplace=True)
y_oof = pd.Series(0, index=x_train.index, name="oof_lgbm")
y_pred = pd.Series(0, index=x_test.index, name="time_to_failure")
trees = []
scores = []
feat_importance = 0
for index_train, index_valid in K_FOLDS.split(x_train):
pool_train = lgb.Dataset(
x_train.iloc[index_train],
label=y_train.iloc[index_train],
)
pool_valid = lgb.Dataset(
x_train.iloc[index_valid],
label=y_train.iloc[index_valid],
)
clf = lgb.train(
CLF_PARAMS,
pool_train,
ITERATIONS,
valid_sets=[pool_train, pool_valid],
verbose_eval=ITERATIONS // 100,
early_stopping_rounds=ITERATIONS // 10
)
trees.append(clf.best_iteration)
scores.append(clf.best_score["valid_1"]["l1"])
y_oof.iloc[index_valid] = clf.predict(x_train.iloc[index_valid], num_iteration=clf.best_iteration)
y_pred += clf.predict(x_test, num_iteration=clf.best_iteration) / K_FOLDS.get_n_splits()
feat_importance += clf.feature_importance("gain") / K_FOLDS.get_n_splits()
print("\n")
LOGGER.info(f"Количество деревьев: {sorted(trees)}")
LOGGER.info(f"Среднее количество деревьев: {np.mean(trees):.0f} +/- {np.std(trees):.0f}")
LOGGER.info(f"MAE на кроссвалидации: " + str(np.round(sorted(scores), 5)))
LOGGER.info(f"MAE среднее: {np.mean(scores):0.3f} +/- {np.std(scores):0.3f}")
stamp = (
f"{time.strftime('%Y-%m-%d_%H-%M')}_"
f"{np.mean(scores):0.3f}_"
f"{np.mean(scores) + np.std(scores) * 2 / len(scores) ** 0.5:0.3f}_lgbm")
y_oof.to_csv(conf.DATA_PROCESSED + f"oof_{stamp}.csv", header=True)
y_pred.to_csv(conf.DATA_PROCESSED + f"sub_{stamp}.csv", header=True)
print(pd.DataFrame(feat_importance, index=x_train.columns, columns=["value"]).sort_values("value", ascending=False))
def train_ext():
"""Обучение LightGBM."""
x_train, y_train = processing.train_set()
x_test = processing.test_set()
x_train.drop(DROP, axis=1, inplace=True)
x_test.drop(DROP, axis=1, inplace=True)
y_oof = pd.Series(0, index=x_train.index, name="oof_ext")
y_pred = pd.Series(0, index=x_test.index, name="time_to_failure")
feat_importance = 0
scores = []
for index_train, index_valid in K_FOLDS.split(x_train):
clf = ensemble.ExtraTreesRegressor(**CLF_PARAMS)
clf.fit(x_train.iloc[index_train], y_train.iloc[index_train])
y_oof.iloc[index_valid] = clf.predict(x_train.iloc[index_valid])
scores.append(
metrics.mean_absolute_error(y_train.iloc[index_valid],
y_oof.iloc[index_valid]))
y_pred += clf.predict(x_test) / K_FOLDS.get_n_splits()
feat_importance += clf.feature_importances_ / K_FOLDS.get_n_splits()
print("\n")
LOGGER.info(f"MAE на кроссвалидации: " + str(np.round(sorted(scores), 5)))
LOGGER.info(
f"MAE среднее: {np.mean(scores):0.3f} +/- {np.std(scores):0.3f}")
stamp = (
f"{time.strftime('%Y-%m-%d_%H-%M')}_"
f"{np.mean(scores):0.3f}_"
f"{np.mean(scores) + np.std(scores) * 2 / len(scores) ** 0.5:0.3f}_ext"
)
y_oof.to_csv(conf.DATA_PROCESSED + f"oof_{stamp}.csv", header=True)
y_pred.to_csv(conf.DATA_PROCESSED + f"sub_{stamp}.csv", header=True)
print(
pd.DataFrame(feat_importance, index=x_train.columns,
columns=["value"]).sort_values("value", ascending=False))