I'm trying to use custom cross-validation sets for a very specific dataset and scikit-optimize using BayesSearchCV. I've been able to replicate the error with scikit-learn using GridSearchCV.
Straight from the documentation:
cv : int, cross-validation generator or an iterable, optional
Determines the cross-validation splitting strategy. Possible inputs for cv are:
None, to use the default 3-fold cross validation, integer, to specify the number of folds in a (Stratified)KFold, An object to be used as a cross-validation generator. An iterable yielding train, test splits. For integer/None inputs, if the estimator is a classifier and y is either binary or multiclass, StratifiedKFold is used. In all other cases, KFold is used.
Refer User Guide for the various cross-validation strategies that can be used here.
I can't use cv=10 in my specific dataset. This is only to illustrate the error.
I would like to use a list of lists for the cross-validation training-testing splits as it says in the documentation. How can I format my cross-validation lists correctly?
# Generate data
def iris_data(noise=None, palette="hls", desat=1):
# Iris dataset
X = pd.DataFrame(load_iris().data,
index = [*map(lambda x:f"iris_{x}", range(150))],
columns = [*map(lambda x: x.split(" (cm)")[0].replace(" ","_"), load_iris().feature_names)])
y = pd.Series(load_iris().target,
index = X.index,
name = "Species")
cmap = map_colors(y, mode=1, palette=palette, desat=desat)#y.map(lambda x:{0:"red",1:"green",2:"blue"}[x])
if noise is not None:
X_noise = pd.DataFrame(
np.random.RandomState(0).normal(size=(X.shape[0], noise)),
index=X_iris.index,
columns=[*map(lambda x:f"noise_{x}", range(noise))]
)
X = pd.concat([X, X_noise], axis=1)
return (X, y, cmap)
X, y, c = iris_data(noise=50)
# Get cross-validations
cv = list()
for i in range(10):
idx_tr = np.random.choice(np.arange(X.shape[0]),size=100, replace=False)
idx_te = set(range(X.shape[0])) - set(idx_tr)
tr_te_splits = [idx_tr.tolist(), list(idx_te)]
cv.append(tr_te_splits)
# Get hyperparameter searchspace
search_spaces = {
"n_estimators": [1,10,50],
"criterion": ["gini", "entropy"],
"max_features": ["sqrt", "log2", None],
"min_samples_leaf": [1,2,3,5,8,13],
}
opt = GridSearchCV(RandomForestClassifier(random_state=0), search_spaces, scoring="accuracy", n_jobs=1, cv=cv)
opt.fit(X,y)
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-26-d1117d10dfa6> in <module>()
59 }
60 opt = GridSearchCV(RandomForestClassifier(random_state=0), search_spaces, scoring="accuracy", n_jobs=1, cv=cv)
---> 61 opt.fit(X,y)
~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/model_selection/_search.py in fit(self, X, y, groups, **fit_params)
637 error_score=self.error_score)
638 for parameters, (train, test) in product(candidate_params,
--> 639 cv.split(X, y, groups)))
640
641 # if one choose to see train score, "out" will contain train score info
~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self, iterable)
777 # was dispatched. In particular this covers the edge
778 # case of Parallel used with an exhausted iterator.
--> 779 while self.dispatch_one_batch(iterator):
780 self._iterating = True
781 else:
~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in dispatch_one_batch(self, iterator)
623 return False
624 else:
--> 625 self._dispatch(tasks)
626 return True
627
~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in _dispatch(self, batch)
586 dispatch_timestamp = time.time()
587 cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 588 job = self._backend.apply_async(batch, callback=cb)
589 self._jobs.append(job)
590
~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in apply_async(self, func, callback)
109 def apply_async(self, func, callback=None):
110 """Schedule a func to be run"""
--> 111 result = ImmediateResult(func)
112 if callback:
113 callback(result)
~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in __init__(self, batch)
330 # Don't delay the application, to avoid keeping the input
331 # arguments in memory
--> 332 self.results = batch()
333
334 def get(self):
~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
132
133 def __len__(self):
~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in <listcomp>(.0)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
132
133 def __len__(self):
~/anaconda/envs/python3/lib/python3.6/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, error_score)
446 start_time = time.time()
447
--> 448 X_train, y_train = _safe_split(estimator, X, y, train)
449 X_test, y_test = _safe_split(estimator, X, y, test, train)
450
~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/utils/metaestimators.py in _safe_split(estimator, X, y, indices, train_indices)
198 X_subset = X[np.ix_(indices, train_indices)]
199 else:
--> 200 X_subset = safe_indexing(X, indices)
201
202 if y is not None:
~/anaconda/envs/python3/lib/python3.6/site-packages/sklearn/utils/__init__.py in safe_indexing(X, indices)
144 if hasattr(X, "iloc"):
145 # Work-around for indexing with read-only indices in pandas
--> 146 indices = indices if indices.flags.writeable else indices.copy()
147 # Pandas Dataframes and Series
148 try:
AttributeError: 'list' object has no attribute 'flags'
)
