I'm testing a simple prediction program with Python 2.7, sklearn 0.17.1, numpy 1.11.0. I got matrix with propabilities from LDA model, and now I want create RandomForestClassifier to predict results by propabilities.
My code is:
maxlen = 40
props = []
for doc in corpus:
topics = model.get_document_topics(doc)
tprops = [0] * maxlen
for topic in topics:
tprops[topics[0]] = topics[1]
props.append(tprops)
ntheta = np.array(props)
ny = np.array(y)
clf = RandomForestClassifier(n_estimators=100)
accuracy = cross_val_score(clf, ntheta, ny, scoring = 'accuracy')
print accuracy
ValueError Traceback (most recent call last)
<ipython-input-65-a7d276df43e9> in <module>()
1 # clf.fit(nteta, ny)
2 print nteta.shape, ny.shape
----> 3 accuracy = cross_val_score(clf, nteta, ny, scoring = 'accuracy')
4 print accuracy
/home/egor/anaconda2/lib/python2.7/site-packages/sklearn/cross_validation.pyc in cross_val_score(estimator, X, y, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch)
1431 train, test, verbose, None,
1432 fit_params)
-> 1433 for train, test in cv)
1434 return np.array(scores)[:, 0]
1435
/home/egor/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __call__(self, iterable)
798 # was dispatched. In particular this covers the edge
799 # case of Parallel used with an exhausted iterator.
--> 800 while self.dispatch_one_batch(iterator):
801 self._iterating = True
802 else:
/home/egor/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in dispatch_one_batch(self, iterator)
656 return False
657 else:
--> 658 self._dispatch(tasks)
659 return True
660
/home/egor/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in _dispatch(self, batch)
564
565 if self._pool is None:
--> 566 job = ImmediateComputeBatch(batch)
567 self._jobs.append(job)
568 self.n_dispatched_batches += 1
/home/egor/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __init__(self, batch)
178 # Don't delay the application, to avoid keeping the input
179 # arguments in memory
--> 180 self.results = batch()
181
182 def get(self):
/home/egor/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __call__(self)
70
71 def __call__(self):
---> 72 return [func(*args, **kwargs) for func, args, kwargs in self.items]
73
74 def __len__(self):
/home/egor/anaconda2/lib/python2.7/site-packages/sklearn/cross_validation.pyc in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, error_score)
1529 estimator.fit(X_train, **fit_params)
1530 else:
-> 1531 estimator.fit(X_train, y_train, **fit_params)
1532
1533 except Exception as e:
/home/egor/anaconda2/lib/python2.7/site-packages/sklearn/ensemble/forest.pyc in fit(self, X, y, sample_weight)
210 """
211 # Validate or convert input data
--> 212 X = check_array(X, dtype=DTYPE, accept_sparse="csc")
213 if issparse(X):
214 # Pre-sort indices to avoid that each individual tree of the
/home/egor/anaconda2/lib/python2.7/site-packages/sklearn/utils/validation.pyc in check_array(array, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)
405 " minimum of %d is required%s."
406 % (n_samples, shape_repr, ensure_min_samples,
--> 407 context))
408
409 if ensure_min_features > 0 and array.ndim == 2:
ValueError: Found array with 0 sample(s) (shape=(0, 40)) while a minimum of 1 is required.
UPD
For what I got 2 minus? Let critic be constructive.
UPD
cotique found that y was filled incorrect (must be other classes). And if y fills correct then the problem doesn't happens. In my case classes were wrong and their count were 39774. But in theory it's not an answer, why the error happens when we have 39774 classes and have to predict them.
See Question&Answers more detail:
os