"ValueError: max_features must be in (0, n_features] " in scikit when using random forest
I have a dataset of 20 features and 840 rows. I have already optimized the classifier (random forest). My parameters are n_estimators=100 and max_features=5. I want to do a classification for each feature. I mean with each of the features I want to know the prediction accuracy. But when I use my code I get an error. I am using scikit ver. 18.
How can I fix the problem?
for name in ["AWA"]:
x=sio.loadmat('/home/TrainVal/{}_Fp1.mat'.format(name))['x']
s_y=sio.loadmat('/home/TrainVal/{}_Fp1.mat'.format(name))['y']
y=np.ravel(s_y)
print(name, x.shape, y.shape)
print("")
clf = make_pipeline(preprocessing.RobustScaler(), RandomForestClassifier(n_estimators = 100,
max_features=5, n_jobs=-1))
#########10x10 SSS##############
print("10x10")
for i in range(x.shape[1]):
xA=x[:, i].reshape(-1,1)
xSSSmean = []
for j in range(10):
sss = StratifiedShuffleSplit(n_splits=10, test_size=0.1, random_state=j)
scoresSSS = cross_val_score(clf, xA, y, cv=sss)
xSSSmean.append(scoresSSS.mean())
result_list.append(np.mean(xSSSmean))
plt.bar(i, np.mean(xSSSmean)*100, align = 'center')
plt.ylabel('Accuracy')
plt.xlabel('Features')
plt.title('Accuracy per feature: {}_RF_Fp1(20)'.format(name))
xticks=np.arange(i+1)
plt.xticks(xticks, rotation = 'vertical')
plt.show()
#THE ERROR
ValueError Traceback (most recent call last)
<ipython-input-2-a5faae7f83a2> in <module>()
24
25 sss = StratifiedShuffleSplit(n_splits=10, test_size=0.1, random_state=j)#ver18
---> 26 scoresSSS = cross_val_score(clf, xA, y, cv=sss)
27 xSSSmean.append(scoresSSS.mean())
28 #print(scoresSSS)
/home/karim/anaconda2/envs/scikit18/lib/python3.5/site-packages/sklearn/model_selection/_validation.py in cross_val_score(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch)
138 train, test, verbose, None,
139 fit_params)
--> 140 for train, test in cv_iter)
141 return np.array(scores)[:, 0]
142
/home/karim/anaconda2/envs/scikit18/lib/python3.5/site-packages/sklearn/externals/joblib/parallel.py in __call__(self, iterable)
756 # was dispatched. In particular this covers the edge
757 # case of Parallel used with an exhausted iterator.
--> 758 while self.dispatch_one_batch(iterator):
759 self._iterating = True
760 else:
/home/karim/anaconda2/envs/scikit18/lib/python3.5/site-packages/sklearn/externals/joblib/parallel.py in dispatch_one_batch(self, iterator)
606 return False
607 else:
--> 608 self._dispatch(tasks)
609 return True
610
/home/karim/anaconda2/envs/scikit18/lib/python3.5/site-packages/sklearn/externals/joblib/parallel.py in _dispatch(self, batch)
569 dispatch_timestamp = time.time()
570 cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 571 job = self._backend.apply_async(batch, callback=cb)
572 self._jobs.append(job)
573
/home/karim/anaconda2/envs/scikit18/lib/python3.5/site-packages/sklearn/externals/joblib/_parallel_backends.py in apply_async(self, func, callback)
107 def apply_async(self, func, callback=None):
108 """Schedule a func to be run"""
--> 109 result = ImmediateResult(func)
110 if callback:
111 callback(result)
/home/karim/anaconda2/envs/scikit18/lib/python3.5/site-packages/sklearn/externals/joblib/_parallel_backends.py in __init__(self, batch)
324 # Don't delay the application, to avoid keeping the input
325 # arguments in memory
--> 326 self.results = batch()
327
328 def get(self):
/home/karim/anaconda2/envs/scikit18/lib/python3.5/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):
/home/karim/anaconda2/envs/scikit18/lib/python3.5/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):
/home/karim/anaconda2/envs/scikit18/lib/python3.5/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)
236 estimator.fit(X_train, **fit_params)
237 else:
--> 238 estimator.fit(X_train, y_train, **fit_params)
239
240 except Exception as e:
/home/karim/anaconda2/envs/scikit18/lib/python3.5/site-packages/sklearn/pipeline.py in fit(self, X, y, **fit_params)
268 Xt, fit_params = self._fit(X, y, **fit_params)
269 if self._final_estimator is not None:
--> 270 self._final_estimator.fit(Xt, y, **fit_params)
271 return self
272
/home/karim/anaconda2/envs/scikit18/lib/python3.5/site-packages/sklearn/ensemble/forest.py in fit(self, X, y, sample_weight)
324 t, self, X, y, sample_weight, i, len(trees),
325 verbose=self.verbose, class_weight=self.class_weight)
--> 326 for i, t in enumerate(trees))
327
328 # Collect newly grown trees
/home/karim/anaconda2/envs/scikit18/lib/python3.5/site-packages/sklearn/externals/joblib/parallel.py in __call__(self, iterable)
756 # was dispatched. In particular this covers the edge
757 # case of Parallel used with an exhausted iterator.
--> 758 while self.dispatch_one_batch(iterator):
759 self._iterating = True
760 else:
/home/karim/anaconda2/envs/scikit18/lib/python3.5/site-packages/sklearn/externals/joblib/parallel.py in dispatch_one_batch(self, iterator)
606 return False
607 else:
--> 608 self._dispatch(tasks)
609 return True
610
/home/karim/anaconda2/envs/scikit18/lib/python3.5/site-packages/sklearn/externals/joblib/parallel.py in _dispatch(self, batch)
569 dispatch_timestamp = time.time()
570 cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 571 job = self._backend.apply_async(batch, callback=cb)
572 self._jobs.append(job)
573
/home/karim/anaconda2/envs/scikit18/lib/python3.5/site-packages/sklearn/externals/joblib/_parallel_backends.py in apply_async(self, func, callback)
107 def apply_async(self, func, callback=None):
108 """Schedule a func to be run"""
--> 109 result = ImmediateResult(func)
110 if callback:
111 callback(result)
/home/karim/anaconda2/envs/scikit18/lib/python3.5/site-packages/sklearn/externals/joblib/_parallel_backends.py in __init__(self, batch)
324 # Don't delay the application, to avoid keeping the input
325 # arguments in memory
--> 326 self.results = batch()
327
328 def get(self):
/home/karim/anaconda2/envs/scikit18/lib/python3.5/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):
/home/karim/anaconda2/envs/scikit18/lib/python3.5/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):
/home/karim/anaconda2/envs/scikit18/lib/python3.5/site-packages/sklearn/ensemble/forest.py in _parallel_build_trees(tree, forest, X, y, sample_weight, tree_idx, n_trees, verbose, class_weight)
118 curr_sample_weight *= compute_sample_weight('balanced', y, indices)
119
--> 120 tree.fit(X, y, sample_weight=curr_sample_weight, check_input=False)
121 else:
122 tree.fit(X, y, sample_weight=sample_weight, check_input=False)
/home/karim/anaconda2/envs/scikit18/lib/python3.5/site-packages/sklearn/tree/tree.py in fit(self, X, y, sample_weight, check_input, X_idx_sorted)
737 sample_weight=sample_weight,
738 check_input=check_input,
--> 739 X_idx_sorted=X_idx_sorted)
740 return self
741
/home/karim/anaconda2/envs/scikit18/lib/python3.5/site-packages/sklearn/tree/tree.py in fit(self, X, y, sample_weight, check_input, X_idx_sorted)
244 raise ValueError("max_depth must be greater than zero. ")
245 if not (0 < max_features <= self.n_features_):
--> 246 raise ValueError("max_features must be in (0, n_features]")
247 if not isinstance(max_leaf_nodes, (numbers.Integral, np.integer)):
248 raise ValueError("max_leaf_nodes must be integral number but was "
ValueError: max_features must be in (0, n_features]
Answer
So I managed to solve the problem!!! :) In scikit page says:
*If float, then max_features is a percentage and int(max_features * n_features) features are considered at each split.*
My value:
- List item
n_features=20. This is in int. It is the number of features that I have in my dataset.
max_features: this is the number of features that I want to use. But they are in int so I have to turn them into float
To turn it into float I have to use the formula that is in scikit:
int(max_features * n_features)
int(x * 20)=2
x=0.1
We have to assume that I want to use only 2 features from the 20.
x is the percentage in float
I changed the value in max_features from int to float. Just like this:
max_features:
(int) (float)
20 = 1.0
15 = 0.75
10 = 0.5
5 = 0.25
2 = 0.1
EXAMPLE
#Instead of:
clf = make_pipeline(preprocessing.RobustScaler(), RandomForestClassifier(n_estimators = 100,
max_features=5, n_jobs=-1))
#I did:
clf = make_pipeline(preprocessing.RobustScaler(), RandomForestClassifier(n_estimators = 100,
max_features=0.25, n_jobs=-1))