'min_child_weight': 10,
'min_data_in_leaf': 150,
'reg_lambda': 0.5, # L2 regularization term on weights.
'reg_alpha': 0.5, # L1 regularization term on weights.
'colsample_bytree': 0.9,
'subsample': 0.9,
# 'nthread': 32,
'nthread': cpu_count(),
'bagging_freq': 1,
'verbose':-1,
'seed': SEED
}
loader805 = utils_best.Loader('CV805_LB803')
loader804 = utils_best.Loader('LB804')
# =============================================================================
# load
# =============================================================================
X_805 = loader805.train()
X_804 = loader804.train()
col = X_804.columns.difference(X_805.columns)
X = pd.concat([X_805, X_804[col]], axis=1)
y = utils.read_pickles('../data/label').TARGET
#col = [c for c in X.columns if new_feature in c]
'min_child_weight': 10,
'min_data_in_leaf': 150,
'reg_lambda': 0.5, # L2 regularization term on weights.
'reg_alpha': 0.5, # L1 regularization term on weights.
'colsample_bytree': 0.9,
'subsample': 0.9,
# 'nthread': 32,
'nthread': cpu_count(),
'bagging_freq': 1,
'verbose': -1,
# 'seed': SEED
}
np.random.seed(SEED)
loader = utils_best.Loader('LB804')
# =============================================================================
# load
# =============================================================================
# train
X_train = loader.train()
y_train = utils.read_pickles('../data/label').TARGET
files_tr = utils.get_use_files(new_features, True)
X_ = pd.concat([pd.read_feather(f) for f in tqdm(files_tr, mininterval=60)],
axis=1)
X_train = pd.concat([X_train, X_], axis=1)
if X_train.columns.duplicated().sum() > 0:
'num_leaves': 63,
'max_bin': 255,
'min_child_weight': 10,
'min_data_in_leaf': 150,
'reg_lambda': 0.5, # L2 regularization term on weights.
'reg_alpha': 0.5, # L1 regularization term on weights.
'colsample_bytree': 0.9,
'subsample': 0.9,
# 'nthread': 32,
'nthread': cpu_count(),
'bagging_freq': 1,
'verbose': -1,
'seed': SEED
}
loader = utils_best.Loader('CV805_LB803')
# =============================================================================
# load
# =============================================================================
X = loader.train()
y = utils.read_pickles('../data/label').TARGET
if X.columns.duplicated().sum() > 0:
raise Exception(f'duplicated!: { X.columns[X.columns.duplicated()] }')
print('no dup :) ')
print(f'X.shape {X.shape}')
gc.collect()
CAT = list(set(X.columns) & set(loader.category()))
