Настройка базового c конвейера для Titani c Kaggle data, но я получаю сообщение об ошибке: ValueError: not enough values to unpack (expected 3, got 2).
Несмотря на то, что есть несколько сообщений SO по этой ошибке, они не t выстроиться в линию или предоставить solid метод для диагностики этой проблемы, не говоря уже о решении. К сожалению, трассировка ошибки неясна. Я закомментировал большинство строк и повторно запустил код, чтобы посмотреть, смогу ли я сузить, какой
Вот пример данных:
PassengerId Pclass Sex Age SibSp Parch Fare Embarked Title
892 3 male 34.5 0 0 7.8292 Q Mr
893 3 female 47.0 1 0 7.0000 S Mrs
894 2 male 62.0 0 0 9.6875 Q Mr
895 3 male 27.0 0 0 8.6625 S Mr
896 3 female 22.0 1 1 12.2875 S Mrs
Вот код конвейера, с которым я работаю :
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OneHotEncoder
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV
#Create a column transformer to impute missing values and one-hot encode specific columns
col_transform = ColumnTransformer(transformers=[
('one_hot', OneHotEncoder(categories='auto', sparse=False), ['Sex', 'Embarked', 'Title']),
('imputer', SimpleImputer(strategy='median'))],
remainder='passthrough')
#Create a pipeline for the column transformer and logistic regressor
pipe = Pipeline(steps=[('encoding', col_transform),
('logistic_reg', LogisticRegression(max_iter=10000, tol=0.1))])
param_grid = {
# 'logistic_reg__class_weight':[None, 'balanced'],
# 'logistic_reg__solver':['lbfgs', 'liblinear', 'newton-cg']
}
clf = GridSearchCV(pipe, param_grid=param_grid, cv=5, verbose=True, n_jobs=-1)
best_clf=clf.fit(X_train, y_train)
Вопрос: Есть идеи, почему я получаю ошибку, упомянутую выше?
РЕДАКТИРОВАТЬ: Вот полная ошибка
_RemoteTraceback Traceback (most recent call last)
_RemoteTraceback:
"""
Traceback (most recent call last):
File "C:\Users\Lofgran\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\externals\loky\process_executor.py", line 418, in _process_worker
r = call_item()
File "C:\Users\Lofgran\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\externals\loky\process_executor.py", line 272, in __call__
return self.fn(*self.args, **self.kwargs)
File "C:\Users\Lofgran\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\_parallel_backends.py", line 567, in __call__
return self.func(*args, **kwargs)
File "C:\Users\Lofgran\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py", line 225, in __call__
for func, args, kwargs in self.items]
File "C:\Users\Lofgran\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py", line 225, in <listcomp>
for func, args, kwargs in self.items]
File "C:\Users\Lofgran\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\model_selection\_validation.py", line 516, in _fit_and_score
estimator.fit(X_train, y_train, **fit_params)
File "C:\Users\Lofgran\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\pipeline.py", line 352, in fit
Xt, fit_params = self._fit(X, y, **fit_params)
File "C:\Users\Lofgran\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\pipeline.py", line 317, in _fit
**fit_params_steps[name])
File "C:\Users\Lofgran\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\memory.py", line 355, in __call__
return self.func(*args, **kwargs)
File "C:\Users\Lofgran\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\pipeline.py", line 716, in _fit_transform_one
res = transformer.fit_transform(X, y, **fit_params)
File "C:\Users\Lofgran\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\compose\_column_transformer.py", line 472, in fit_transform
self._validate_transformers()
File "C:\Users\Lofgran\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\compose\_column_transformer.py", line 265, in _validate_transformers
names, transformers, _ = zip(*self.transformers)
ValueError: not enough values to unpack (expected 3, got 2)
"""
The above exception was the direct cause of the following exception:
ValueError Traceback (most recent call last)
<ipython-input-17-6a051cf930ab> in <module>
25 clf = GridSearchCV(pipe, param_grid=param_grid, cv=5, verbose=True, n_jobs=-1) #5 fold cross-validation; n_jobs=use all processors
26
---> 27 best_clf=clf.fit(X_train, y_train)
~\AppData\Local\Continuum\anaconda3\lib\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
~\AppData\Local\Continuum\anaconda3\lib\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
~\AppData\Local\Continuum\anaconda3\lib\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:
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in __call__(self, iterable)
932
933 with self._backend.retrieval_context():
--> 934 self.retrieve()
935 # Make sure that we get a last message telling us we are done
936 elapsed_time = time.time() - self._start_time
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in retrieve(self)
831 try:
832 if getattr(self._backend, 'supports_timeout', False):
--> 833 self._output.extend(job.get(timeout=self.timeout))
834 else:
835 self._output.extend(job.get())
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\_parallel_backends.py in wrap_future_result(future, timeout)
519 AsyncResults.get from multiprocessing."""
520 try:
--> 521 return future.result(timeout=timeout)
522 except LokyTimeoutError:
523 raise TimeoutError()
~\AppData\Local\Continuum\anaconda3\lib\concurrent\futures\_base.py in result(self, timeout)
433 raise CancelledError()
434 elif self._state == FINISHED:
--> 435 return self.__get_result()
436 else:
437 raise TimeoutError()
~\AppData\Local\Continuum\anaconda3\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: not enough values to unpack (expected 3, got 2)
Редактировать 2:
col_transform = ColumnTransformer(transformers=[
('imputer', SimpleImputer(missing_values=np.nan, strategy='median')),
('one_hot', OneHotEncoder(categories='auto', sparse=False))],
remainder='passthrough')