TypeError: Issue with GridSearchCV - python-3.x

Question

I am trying to use GridSearchCV and Pipeline to check parameters of SVM. The code is as follows.
parameter={'svm_C':(0.1, 1, 10, 100), 'svm_gamma':(0.001, 0.01, 0.1, 10)}
pipe=Pipeline([("scaler", StandardScaler), ("svm", SVC())])
print(parameter)
print(pipe)
print(xtrain.shape)
print(ytrain1.shape)
grid=GridSearchCV(pipe, parameter, cv=3, n_jobs=-1)
grid.fit(xtrain,ytrain1)
print("Best set score:{}".format(grid.best_score_))
print("Test set Score:{}".format(grid.score(xtest,ytest1)))
print("Best paameters:{}".format(grid.best_params_))
filename='finalized_svm.sav'
filename1='gridfinal_svm.sav'
joblib.dump(best_estimator_, filename)
joblib.dump(grid, filename1)
pred=grid.predict(xtest)
confusion=confusion_matrix(ytest1,pred), print(confusion)
I loaded some .mat files for xtrain and ytrain. The issue is generated in line "grid.fit(xtrain,ytrain1)".
The error generated is as follows
Traceback (most recent call last):
File "C:/code net/mysvm.py", line 44, in <module>
grid.fit(xtrain,ytrain1)
File "C:\Users\Manisha\AppData\Local\Programs\Python\Python36\lib\site-packages\sklearn\model_selection\_search.py", line 626, in fit
base_estimator = clone(self.estimator)
File "C:\Users\Manisha\AppData\Local\Programs\Python\Python36\lib\site-packages\sklearn\base.py", line 62, in clone
new_object_params[name] = clone(param, safe=False)
File "C:\Users\Manisha\AppData\Local\Programs\Python\Python36\lib\site-packages\sklearn\base.py", line 50, in clone
return estimator_type([clone(e, safe=safe) for e in estimator])
File "C:\Users\Manisha\AppData\Local\Programs\Python\Python36\lib\site-packages\sklearn\base.py", line 50, in <listcomp>
return estimator_type([clone(e, safe=safe) for e in estimator])
File "C:\Users\Manisha\AppData\Local\Programs\Python\Python36\lib\site-packages\sklearn\base.py", line 50, in clone
return estimator_type([clone(e, safe=safe) for e in estimator])
File "C:\Users\Manisha\AppData\Local\Programs\Python\Python36\lib\site-packages\sklearn\base.py", line 50, in <listcomp>
return estimator_type([clone(e, safe=safe) for e in estimator])
File "C:\Users\Manisha\AppData\Local\Programs\Python\Python36\lib\site-packages\sklearn\base.py", line 60, in clone
new_object_params = estimator.get_params(deep=False)
TypeError: get_params() missing 1 required positional argument: 'self'
By using parameter={'svm_C':(0.1, 1, 10, 100), 'svm_gamma':(0.001, 0.01, 0.1, 10)}
pipe=Pipeline([("scaler", StandardScaler()), the error comes out
Traceback (most recent call last):
File "C:\Users\Manisha\AppData\Local\conda\conda\envs\tfp36\lib\site-packages\sklearn\externals\joblib\externals\loky\process_executor.py", line 420, in _process_worker
r = call_item.fn(*call_item.args, **call_item.kwargs)
File "C:\Users\Manisha\AppData\Local\conda\conda\envs\tfp36\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py", line 563, in __call__
return self.func(*args, **kwargs)
File "C:\Users\Manisha\AppData\Local\conda\conda\envs\tfp36\lib\site-packages\sklearn\externals\joblib\parallel.py", line 261, in __call__
for func, args, kwargs in self.items]
File "C:\Users\Manisha\AppData\Local\conda\conda\envs\tfp36\lib\site-packages\sklearn\externals\joblib\parallel.py", line 261, in <listcomp>
for func, args, kwargs in self.items]
File "C:\Users\Manisha\AppData\Local\conda\conda\envs\tfp36\lib\site-packages\sklearn\model_selection\_validation.py", line 514, in _fit_and_score
estimator.set_params(**parameters)
File "C:\Users\Manisha\AppData\Local\conda\conda\envs\tfp36\lib\site-packages\sklearn\pipeline.py", line 147, in set_params
self._set_params('steps', **kwargs)
File "C:\Users\Manisha\AppData\Local\conda\conda\envs\tfp36\lib\site-packages\sklearn\utils\metaestimators.py", line 52, in _set_params
super(_BaseComposition, self).set_params(**params)
File "C:\Users\Manisha\AppData\Local\conda\conda\envs\tfp36\lib\site-packages\sklearn\base.py", line 213, in set_params
(key, self))
ValueError: Invalid parameter svm_C for estimator Pipeline(memory=None,
steps=[('scaler', StandardScaler(copy=True, with_mean=True, with_std=True)), ('svm', SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
decision_function_shape='ovr', degree=3, gamma='auto_deprecated',
kernel='rbf', max_iter=-1, probability=False, random_state=None,
shrinking=True, tol=0.001, verbose=False))]). Check the list of available parameters with `estimator.get_params().keys()`.
"""
The above exception was the direct cause of the following exception:
ValueError Traceback (most recent call last)
<ipython-input-7-83184f586b10> in <module>
2 print(ytrain1.shape)
3 grid1=GridSearchCV(pipe, parameter, cv=3, n_jobs=-1)
----> 4 grid1.fit(xtrain,ytrain1)
5 print("Best set score:{}".format(grid.best_score_))
6 print("Test set Score:{}".format(grid.score(xtest,ytest1)))
~\AppData\Local\conda\conda\envs\tfp36\lib\site-packages\sklearn\model_selection\_search.py in fit(self, X, y, groups, **fit_params)
720 return results_container[0]
721
--> 722 self._run_search(evaluate_candidates)
723
724 results = results_container[0]
~\AppData\Local\conda\conda\envs\tfp36\lib\site-packages\sklearn\model_selection\_search.py in _run_search(self, evaluate_candidates)
1189 def _run_search(self, evaluate_candidates):
1190 """Search all candidates in param_grid"""
-> 1191 evaluate_candidates(ParameterGrid(self.param_grid))
1192
1193
~\AppData\Local\conda\conda\envs\tfp36\lib\site-packages\sklearn\model_selection\_search.py in evaluate_candidates(candidate_params)
709 for parameters, (train, test)
710 in product(candidate_params,
--> 711 cv.split(X, y, groups)))
712
713 all_candidate_params.extend(candidate_params)
~\AppData\Local\conda\conda\envs\tfp36\lib\site-packages\sklearn\externals\joblib\parallel.py in __call__(self, iterable)
994
995 with self._backend.retrieval_context():
--> 996 self.retrieve()
997 # Make sure that we get a last message telling us we are done
998 elapsed_time = time.time() - self._start_time
~\AppData\Local\conda\conda\envs\tfp36\lib\site-packages\sklearn\externals\joblib\parallel.py in retrieve(self)
897 try:
898 if getattr(self._backend, 'supports_timeout', False):
--> 899 self._output.extend(job.get(timeout=self.timeout))
900 else:
901 self._output.extend(job.get())
~\AppData\Local\conda\conda\envs\tfp36\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py in wrap_future_result(future, timeout)
515 AsyncResults.get from multiprocessing."""
516 try:
--> 517 return future.result(timeout=timeout)
518 except LokyTimeoutError:
519 raise TimeoutError()
~\AppData\Local\conda\conda\envs\tfp36\lib\concurrent\futures\_base.py in result(self, timeout)
430 raise CancelledError()
431 elif self._state == FINISHED:
--> 432 return self.__get_result()
433 else:
434 raise TimeoutError()
~\AppData\Local\conda\conda\envs\tfp36\lib\concurrent\futures\_base.py in __get_result(self)
382 def __get_result(self):
383 if self._exception:
--> 384 raise self._exception
385 else:
386 return self._result
ValueError: Invalid parameter svm_C for estimator Pipeline(memory=None,
steps=[('scaler', StandardScaler(copy=True, with_mean=True, with_std=True)), ('svm', SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
decision_function_shape='ovr', degree=3, gamma='auto_deprecated',
kernel='rbf', max_iter=-1, probability=False, random_state=None,
shrinking=True, tol=0.001, verbose=False))]). Check the list of available parameters with `estimator.get_params().keys()`.

Answer 1

I have done what you want to do in this way, and it is working:
# Setup the pipeline
steps = [('scaler', StandardScaler()),
('SVM', SVC())]
pipeline = Pipeline(steps)
# Specify the hyperparameter space
parameters = {'SVM__C':[1, 10, 100],
'SVM__gamma':[0.1, 0.01]}
I see 2 differences respect to your code:
When defining the steps in the pipeline instantination you write StandardScaler, without parenthesis:
Your code is:
pipe=Pipeline([("scaler", StandardScaler), ("svm", SVC())])
In my code I write StandardScaler(), look:
steps = [('scaler', StandardScaler()),('SVM', SVC())]
pipeline = Pipeline(steps)
The second difference is that when you specify the keys for your parameters grid parameters. You provide the keys: 'svm_C', 'svm_gamma' instead of 'SVM__C' and 'SVM__gamma' respectively.
You need double-under_square _+_ , this is, __ , as the 1st person that answered your question said before.
So, instead to write :
parameter={'svm_C':(0.1, 1, 10, 100), 'svm_gamma':(0.001, 0.01, 0.1, 10)}
You should write
parameters = {'SVM__C':[1, 10, 100],'SVM__gamma':[0.1, 0.01]}
I even have gotten an error writting 'svm__c' instead of 'SVM__C' and 'svm__gamma' instead of 'SVM__gamma'.
This last I do not why.
I hope, it helps