from mlxtend.regressor import StackingRegressor
from sklearn.ensemble.forest import RandomForestRegressor as RFR
from sklearn.ensemble import GradientBoostingRegressor as GBR
import xgboost as xgb
rfr = RFR(n_estimators=500, n_jobs=cc.ncpu, random_state=0)
gbr = GBR(n_estimators=1000, random_state=0)
xgr = xgb.XGBRegressor()
mtr = RFR() # meta regressor
regressors = [rfr, gbr, xgr]
model = StackingRegressor(regressors=regressors, meta_regressor=mtr)
param_grid = {
'fs__threshold': ['median'],
'fs__estimator__max_features': ['log2'],
'clf__rfr__max_features': ['auto', 'log2'],
'clf__gbr__learning_rate': [0.05, 0.02, 0.01],
'clf__gbr__max_depth': [4, 5, 6, 7],
'clf__gbr__max_features': ['auto', 'log2'],
'clf__gbr__n_estimators': [500, 1000, 2000],
'clf__xgr__learning_rate': [0.001, 0.05, 0.1, 0.2],
'clf__xgr__max_depth': [2, 4, 6],
'clf__xgr__min_child_weight': [1, 3, 5],
'clf__xgr__n_estimators': [500, 1000],
'clf__meta-mtr__n_estimators': [750, 1500]
}
rf_feature_imp = RFR(250, n_jobs=cc.ncpu)
feat_selection = SelectFromModel(rf_feature_imp)
pipeline = Pipeline([('fs', feat_selection), ('clf', model), ])
gs = GridSearchCV(pipeline, param_grid=param_grid, verbose=1, n_jobs=-1, error_score=np.nan)
In the code above, I want to use the mlxtend voting regressor and also use a random forest to select relevant features. However, this code is not working and I get an error
ValueError: Invalid parameter xgr for estimator StackingRegressor(meta_regressor=RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=None,
max_features='auto', max_leaf_nodes=None,
min_impurity_split=1e-07, min_samples_leaf=1,
min_samples_split=2, min_weight_fraction_leaf=0.0,
n_estimators=10, n_jobs=1, oob_score=False, random_state=None,
verbose=0, warm_start=False),
regressors=[RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=None,
max_features='auto', max_leaf_nodes=None,
min_impurity_split=1e-07, min_samples_leaf=1,
min_samples_split=2, min_weight_fraction_leaf=0.0,
n_estimators=500, n_jobs=5, oob_sc...eg:linear', reg_alpha=0, reg_lambda=1,
scale_pos_weight=1, seed=0, silent=True, subsample=1)],
verbose=0). Check the list of available parameters with `estimator.get_params().keys()`.
How to fix this?
