def optimize_model_params(self, X: pd.DataFrame, y: pd.Series) -> None:
"""
Optimize params of LightGBM regressor
:param X: Data
:param y: Target
:return: Saves best model in self
"""
param_grid = ParameterGrid({
"learning_rate": [0.05],
"n_estimators": [1000],
"num_leaves": [15, 31, 63, 127, 255],
"min_child_samples": [3, 20, 50, 150],
"subsample_freq": [1, 5, 25, 50],
"colsample_bytree": [1.0, 0.8, 0.6],
"subsample": [1.0, 0.8, 0.6],
"lambda_l2": [0, 0.1, 1, 10],
"random_state": [2020]
})
param_grid = list(param_grid)
random.shuffle(param_grid)
print(f"Number of grid points: {len(param_grid)}")
# optimize params
while (self.training_time_left >
self.worst_training_time) & (len(param_grid) > 0):
params = param_grid.pop()
self.validate_fit(X, y, {
"model_params": params,
"params": self.best_params["params"]
})
def optimize_params(self, X: pd.DataFrame, y: pd.Series):
"""
Optimize main parameters of pipeline
:param X: Data
:param y: Target
:return: Saves best model in self
"""
param_grid = ParameterGrid({
"id_columns": [self.dtype_cols['idd']],
"cat_columns": [self.dtype_cols['cat']],
"encode_type": ["catboost"],
"target_process": ["diff", "none"],
"prev_target_col": [f"{self.label}__shift-1"],
"apply_weights": ["none"],
"use_features": ["all"]
})
param_grid = list(param_grid)
param_grid = [
params for params in param_grid
if params != self.best_params["params"]
]
random.shuffle(param_grid)
print(f"Number of grid points: {len(param_grid)}")
pprint(param_grid)
# optimize params
while (self.training_time_left >
self.worst_training_time) & (len(param_grid) > 0):
params = param_grid.pop()
self.validate_fit(X, y, {"params": params})