diff --git a/MultiLabel/NOTES.txt b/MultiLabel/NOTES.txt
index b809537..fe45c97 100644
--- a/MultiLabel/NOTES.txt
+++ b/MultiLabel/NOTES.txt
@@ -1,5 +1,22 @@
+Classifiers
+
+- Classifiers binary, single-label, OneVsRest or MultiOutput:
+    - LR
+    - LinearSVC (?)
+
+- Classifiers natively multi-label:
+    - from scikit-multilearn (x11)
+    -
+
+Protocols:
+    - NPP
+    - APP (for each class)
+
+
+
 Things to test:
-- MultiChain for classification, MultiChain for regression?
+- MultiChain for classification, MultiChain for regression...
+- Reimplement stacking with sklearn.ensemble.StackingClassifier? No parece facil.
 
 - Independent classifiers + independent quantifiers
 - Stacking + independent quantifiers
@@ -12,3 +29,10 @@ Things to test:
 
 - Model Selection for specific protocols?
 
+TODO:
+- decide methods
+    - decide classifiers binary
+    - decide classifiers multi-label
+    - decide quantifiers naive
+    - decide quantifiers multi-label
+- decide datasets
diff --git a/MultiLabel/multi_label.py b/MultiLabel/main.py
similarity index 100%
rename from MultiLabel/multi_label.py
rename to MultiLabel/main.py
diff --git a/MultiLabel/mldata.py b/MultiLabel/mldata.py
index 562d4f4..d211c33 100644
--- a/MultiLabel/mldata.py
+++ b/MultiLabel/mldata.py
@@ -64,6 +64,7 @@ class MultilabelledCollection:
         return MultilabelledCollection(documents, labels)
 
     def train_test_split(self, train_prop=0.6, random_state=None):
+        raise ValueError('use the scikit-multilearn implementation')
         tr_docs, te_docs, tr_labels, te_labels = \
             train_test_split(self.instances, self.labels, train_size=train_prop, random_state=random_state)
         return MultilabelledCollection(tr_docs, tr_labels), MultilabelledCollection(te_docs, te_labels)