ValueError: Invalid parameter n_estimators for estimator LogisticRegression(random_state=42) - pandas

Question

I already looked at the other similar questions, but they did not help me. I'm attempting to use GridSearchCV. I'm using three pipelines to predict nfl play data. It works pretty well until the grid search part.
Here is my code.
pipe_nfl1_1 = Pipeline([
('ssc', StandardScaler()),
('lr', LogisticRegression(random_state=42))
])
pipe_nfl1_2 = Pipeline([
('mms', MinMaxScaler()),
('rfc', RandomForestClassifier(random_state=42))
])
pipe_nfl1_3 = Pipeline([
('mms', MinMaxScaler()),
('svc', svm.SVC(random_state=42))
])
pipelines1 = [pipe_nfl1_1, pipe_nfl1_2, pipe_nfl1_3]
pipe_dict1 = {0: 'Logistic Regression', 1: 'Random Forest', 2: 'SVC'}
for pipe in pipelines1:
pipe.fit(X_train1, y_train1)
print('Pipeline test accuracy for predicting 1st downs:')
for idx, val in enumerate(pipelines1):
print(' %s: %.4f' % (pipe_dict1[idx], val.score(X_test1, y_test1)))
best_acc1 = 0.0
best_clf1 = 0
best_pipe1 = ''
for idx, val in enumerate(pipelines1):
if val.score(X_test1, y_test1) > best_acc1:
best_acc1 = val.score(X_test1, y_test1)
best_pipe1 = val
best_clf1 = idx
best_acc1 *= 100
print('Classifier with best accuracy for predicting 1st downs is %s with %.2f' % (pipe_dict1[best_clf1], best_acc1) + '%')
param_grid1 = {
'lr__n_estimators': [2, 4, 6]
}
grid_search1 = GridSearchCV(pipe_nfl1_1, param_grid1, cv=2)
# fine-tune the hyperparameters
grid_search1.fit(X_train1, y_train1)
# get the best model
final_model1 = grid_search1.best_estimator_
grid_search.best_score_
But I'm getting an error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-33-6b0007d9b8f1> in <module>
2
3 # fine-tune the hyperparameters
----> 4 grid_search1.fit(X_train1, y_train1)
5
6 # get the best model
~\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\utils\validation.py in inner_f(*args, **kwargs)
70 FutureWarning)
71 kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 72 return f(**kwargs)
73 return inner_f
74
~\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\model_selection\_search.py in fit(self, X, y, groups, **fit_params)
734 return results
735
--> 736 self._run_search(evaluate_candidates)
737
738 # For multi-metric evaluation, store the best_index_, best_params_ and
~\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\model_selection\_search.py in _run_search(self, evaluate_candidates)
1186 def _run_search(self, evaluate_candidates):
1187 """Search all candidates in param_grid"""
-> 1188 evaluate_candidates(ParameterGrid(self.param_grid))
1189
1190
~\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\model_selection\_search.py in evaluate_candidates(candidate_params)
706 n_splits, n_candidates, n_candidates * n_splits))
707
--> 708 out = parallel(delayed(_fit_and_score)(clone(base_estimator),
709 X, y,
710 train=train, test=test,
~\AppData\Local\Programs\Python\Python38\lib\site-packages\joblib\parallel.py in __call__(self, iterable)
1027 # remaining jobs.
1028 self._iterating = False
-> 1029 if self.dispatch_one_batch(iterator):
1030 self._iterating = self._original_iterator is not None
1031
~\AppData\Local\Programs\Python\Python38\lib\site-packages\joblib\parallel.py in dispatch_one_batch(self, iterator)
845 return False
846 else:
--> 847 self._dispatch(tasks)
848 return True
849
~\AppData\Local\Programs\Python\Python38\lib\site-packages\joblib\parallel.py in _dispatch(self, batch)
763 with self._lock:
764 job_idx = len(self._jobs)
--> 765 job = self._backend.apply_async(batch, callback=cb)
766 # A job can complete so quickly than its callback is
767 # called before we get here, causing self._jobs to
~\AppData\Local\Programs\Python\Python38\lib\site-packages\joblib\_parallel_backends.py in apply_async(self, func, callback)
206 def apply_async(self, func, callback=None):
207 """Schedule a func to be run"""
--> 208 result = ImmediateResult(func)
209 if callback:
210 callback(result)
~\AppData\Local\Programs\Python\Python38\lib\site-packages\joblib\_parallel_backends.py in __init__(self, batch)
570 # Don't delay the application, to avoid keeping the input
571 # arguments in memory
--> 572 self.results = batch()
573
574 def get(self):
~\AppData\Local\Programs\Python\Python38\lib\site-packages\joblib\parallel.py in __call__(self)
250 # change the default number of processes to -1
251 with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 252 return [func(*args, **kwargs)
253 for func, args, kwargs in self.items]
254
~\AppData\Local\Programs\Python\Python38\lib\site-packages\joblib\parallel.py in <listcomp>(.0)
250 # change the default number of processes to -1
251 with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 252 return [func(*args, **kwargs)
253 for func, args, kwargs in self.items]
254
~\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\model_selection\_validation.py in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, return_estimator, error_score)
518 cloned_parameters[k] = clone(v, safe=False)
519
--> 520 estimator = estimator.set_params(**cloned_parameters)
521
522 start_time = time.time()
~\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\pipeline.py in set_params(self, **kwargs)
139 self
140 """
--> 141 self._set_params('steps', **kwargs)
142 return self
143
~\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\utils\metaestimators.py in _set_params(self, attr, **params)
51 self._replace_estimator(attr, name, params.pop(name))
52 # 3. Step parameters and other initialisation arguments
---> 53 super().set_params(**params)
54 return self
55
~\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\base.py in set_params(self, **params)
259
260 for key, sub_params in nested_params.items():
--> 261 valid_params[key].set_params(**sub_params)
262
263 return self
~\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\base.py in set_params(self, **params)
247 key, delim, sub_key = key.partition('__')
248 if key not in valid_params:
--> 249 raise ValueError('Invalid parameter %s for estimator %s. '
250 'Check the list of available parameters '
251 'with `estimator.get_params().keys()`.' %
ValueError: Invalid parameter n_estimators for estimator LogisticRegression(random_state=42). Check the list of available parameters with `estimator.get_params().keys()`.
I've done LogisticRegression.get_params().keys() to get the keys, but it returns get_params() missing 1 required positional argument: 'self'.

Answer 1

You shouldn't have the leading underscores in the parameter names. You want your param_grid1 dict to consist of keys that are actually parameters accepted by the model you're using. That would be n_estimators for RandomForest, and C for LogisticRegression. With that said, n_estimators is a parameter for the model RandomForest, but it's not a parameter for LogisticRegression. C is a parameter for LogisticRegression.
I think what you want to do is a grid search over the parameter space of the model that performs best, right? In that case, your param_grid1 variable should be updated to the model that performs best. The parameters accepted by the models you're testing vary from model to model.