I'm trying to get randomized hyperparameter search to work with the voting classifier from sklearn by adapting the example given in the sklearn documentation.
I've seen this minimal working example, but it breaks in many ways using my version of sklearn.
Here is a stripped-down example:
import numpy as np
from sklearn import __version__ as skv
from sklearn.ensemble import RandomForestClassifier as RFClassi
from sklearn.ensemble import HistGradientBoostingClassifier as HGBClassi
from sklearn.tree import DecisionTreeClassifier as DTClassi
from sklearn.model_selection import RandomizedSearchCV
from sklearn.ensemble import VotingClassifier
from sklearn.datasets import load_iris
print(f"sklearn version: {skv}")
df_X, target = load_iris(return_X_y=True, as_frame=True)
ensemble = ['rf','dtree','hgb']
hy_pa_grid = {
'hgb': dict(learning_rate = list(np.linspace(0.01,0.5,10).round(3))),
'rf':dict(criterion = ['gini', 'entropy']),
'dtree':dict(criterion = ['gini', 'entropy']),
}
clfs = {'hgb' : HGBClassi(), 'rf': RFClassi(), 'dtree' : DTClassi()}
vc = VotingClassifier(estimators = clfs.items(), voting = 'soft')
params = {
f"{c}__{p}" : hy_pa_grid[c][p]
for c in ensemble
for p in hy_pa_grid[c].keys()
}
print("\n".join(map(str,params.items())))
clf = RandomizedSearchCV(estimator = vc, param_distributions = params)
clf.fit(df_X,target)
The output I get is this:
sklearn version: 1.1.3
{'rf__criterion': ['gini', 'entropy'], 'dtree__criterion': ['gini', 'entropy'], 'hgb__learning_rate': [0.01, 0.064, 0.119, 0.173, 0.228, 0.282, 0.337, 0.391, 0.446, 0.5]}
Traceback (most recent call last):
File "vc.py", line 34, in <module>
clf.fit(df_X,target)
File "/home/USER/.local/lib/python3.8/site-packages/sklearn/model_selection/_search.py", line 789, in fit
base_estimator = clone(self.estimator)
File "/home/USER/.local/lib/python3.8/site-packages/sklearn/base.py", line 87, in clone
new_object_params[name] = clone(param, safe=False)
File "/home/USER/.local/lib/python3.8/site-packages/sklearn/base.py", line 68, in clone
return copy.deepcopy(estimator)
File "/usr/lib/python3.8/copy.py", line 161, in deepcopy
rv = reductor(4)
TypeError: cannot pickle 'dict_items' object
Any ideas for getting round this? I also tried doing it with GridSearchCV, as in the example, but I get the same error.
