I'm trying to use GridSearchCV with KMeans clustering to explore the optimal number to clusters to use in order to get the best results on a classification problem.
I've got the following code:
from sklearn.datasets import fetch_olivetti_faces
from sklearn.model_selection import StratifiedShuffleSplit, GridSearchCV
from sklearn.linear_model import LogisticRegression
from sklearn.cluster import KMeans
from sklearn.pipeline import Pipeline
faces = fetch_olivetti_faces()
X_data, y_data = faces.data, faces.target
log_reg = LogisticRegression()
split = StratifiedShuffleSplit(n_splits = 1, test_size=.2, random_state=42)
for train_index, test_index in split.split(X_train, y_train):
X_train_set , y_train_set = X_data[train_index,], y_data[train_index,]
X_test_set, y_test_set = X_data[test_index,], y_data[test_index, ]
pipeline = Pipeline([
('kmeans', KMeans(n_clusters = 30)),
('log_reg', LogisticRegression())
])
cluster_grid = dict(n_clusters=range(2,100))
grid = GridSearchCV(pipeline, cluster_grid)
grid.fit(X_train_set, y_train_set, cv=5, verbose=2)
Here's the entire traceback:
-------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-42-80e6a3932897> in <module>
----> 1 grid.fit(X_train_set, y_train_set, cv=5, verbose=2)
~/opt/anaconda3/lib/python3.7/site-packages/sklearn/model_selection/_search.py in fit(self, X, y, groups, **fit_params)
686 return results
687
--> 688 self._run_search(evaluate_candidates)
689
690 # For multi-metric evaluation, store the best_index_, best_params_ and
~/opt/anaconda3/lib/python3.7/site-packages/sklearn/model_selection/_search.py in _run_search(self, evaluate_candidates)
1147 def _run_search(self, evaluate_candidates):
1148 """Search all candidates in param_grid"""
-> 1149 evaluate_candidates(ParameterGrid(self.param_grid))
1150
1151
~/opt/anaconda3/lib/python3.7/site-packages/sklearn/model_selection/_search.py in evaluate_candidates(candidate_params)
665 for parameters, (train, test)
666 in product(candidate_params,
--> 667 cv.split(X, y, groups)))
668
669 if len(out) < 1:
~/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py in __call__(self, iterable)
919 # remaining jobs.
920 self._iterating = False
--> 921 if self.dispatch_one_batch(iterator):
922 self._iterating = self._original_iterator is not None
923
~/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py in dispatch_one_batch(self, iterator)
757 return False
758 else:
--> 759 self._dispatch(tasks)
760 return True
761
~/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py in _dispatch(self, batch)
714 with self._lock:
715 job_idx = len(self._jobs)
--> 716 job = self._backend.apply_async(batch, callback=cb)
717 # A job can complete so quickly than its callback is
718 # called before we get here, causing self._jobs to
~/opt/anaconda3/lib/python3.7/site-packages/joblib/_parallel_backends.py in apply_async(self, func, callback)
180 def apply_async(self, func, callback=None):
181 """Schedule a func to be run"""
--> 182 result = ImmediateResult(func)
183 if callback:
184 callback(result)
~/opt/anaconda3/lib/python3.7/site-packages/joblib/_parallel_backends.py in __init__(self, batch)
547 # Don't delay the application, to avoid keeping the input
548 # arguments in memory
--> 549 self.results = batch()
550
551 def get(self):
~/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py in __call__(self)
223 with parallel_backend(self._backend, n_jobs=self._n_jobs):
224 return [func(*args, **kwargs)
--> 225 for func, args, kwargs in self.items]
226
227 def __len__(self):
~/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py in <listcomp>(.0)
223 with parallel_backend(self._backend, n_jobs=self._n_jobs):
224 return [func(*args, **kwargs)
--> 225 for func, args, kwargs in self.items]
226
227 def __len__(self):
~/opt/anaconda3/lib/python3.7/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)
501 train_scores = {}
502 if parameters is not None:
--> 503 estimator.set_params(**parameters)
504
505 start_time = time.time()
~/opt/anaconda3/lib/python3.7/site-packages/sklearn/pipeline.py in set_params(self, **kwargs)
162 self
163 """
--> 164 self._set_params('steps', **kwargs)
165 return self
166
~/opt/anaconda3/lib/python3.7/site-packages/sklearn/utils/metaestimators.py in _set_params(self, attr, **params)
48 self._replace_estimator(attr, name, params.pop(name))
49 # 3. Step parameters and other initialisation arguments
---> 50 super().set_params(**params)
51 return self
52
~/opt/anaconda3/lib/python3.7/site-packages/sklearn/base.py in set_params(self, **params)
222 'Check the list of available parameters '
223 'with `estimator.get_params().keys()`.' %
--> 224 (key, self))
225
226 if delim:
ValueError: Invalid parameter n_clusters for estimator Pipeline(memory=None,
steps=[('kmeans',
KMeans(algorithm='auto', copy_x=True, init='k-means++',
max_iter=300, n_clusters=30, n_init=10, n_jobs=None,
precompute_distances='auto', random_state=None,
tol=0.0001, verbose=0)),
('log_reg',
LogisticRegression(C=1.0, class_weight=None, dual=False,
fit_intercept=True, intercept_scaling=1,
l1_ratio=None, max_iter=100,
multi_class='warn', n_jobs=None,
penalty='l2', random_state=None,
solver='warn', tol=0.0001, verbose=0,
warm_start=False))],
verbose=False). Check the list of available parameters with `estimator.get_params().keys()`.
I have no idea what the heck is going on...I'm not sure how to interpret this error message but my parameter grid doesn't seem to be out of wack. PLEASE HELP!
When you are using pipeline you need to give the parameters as following:
cluster_grid = {
'kmeans__n_clusters': range(2,100)
}
# adding n_jobs to run in parallel
grid = GridSearchCV(pipeline, cluster_grid, n_jobs=-1)
where kmeans is taken from ('kmeans', KMeans())
So, your code should look as the following:
pipeline = Pipeline([
('kmeans', KMeans(),
('log_reg', LogisticRegression())
])
cluster_grid = {
'kmeans__n_clusters': range(2,100)
}
# adding n_jobs to run in parallel
grid = GridSearchCV(pipeline, cluster_grid, n_jobs=-1)