signaturization.md

@@ -17,7 +17,6 @@ Besides, there are other (auxiliary) types of data that may be of interest. The
 * `clus*` [Clusters](#clusters): Centroids and labels of a k-means clustering.
 * `proj*` [2D Projections](#2d-projections): t-SNE 2D projections of the data.
 
-
 I consider the numbering `0`-`3` to be conceptually closed. However, further auxiliary data types may be introduced in the future. Note that all names have a 4-character code followed by a digit. Future data should stick to this nomenclature.
 
 ## Commonalities
@@ -30,29 +29,49 @@ Every CC data will have the following methods:
 * `predict()`: Uses the fitted models to go from input to output.
 * `validate()`: Performs a validation across external data such as MoA and ATC codes.
 
-## Signatures type 0
+Also, data are always sorted by a certain key (and InChIKey, typically). These keys should be accessible and iterable without having to load the whole dataset into memory.
+
+* `keys`
+* `__iter__`
+* `__getattr__`
+
+I think that it may be interesting to keep cognizance of the folder where persistency models are stored:
+
+* `PATH`
+
+### Signature commonalities
+
+All signatures type 0-3 contain a numerical data matrix:
+
+* `V`: Typically, a dense matrix (it can be sparse in the case of signatures type 0).
+
+All 
+
+## Peculiarities
+
+### Signatures type 0
 
 * From: standard input
 * To: `sign0.h5`
 
-## Signatures type 1
+### Signatures type 1
 
 * From: `sign0.h5`
 * To: `sign1`.h5`
 
-## Signatures type 2
+### Signatures type 2
 
-## Signatures type 3
+### Signatures type 3
 
-## Similarity vectors
+### Similarity vectors
 
-## Nearest neighbors
+### Nearest neighbors
 
-## Predicted nearest neighbors
+### Predicted nearest neighbors
 
-## Clusters
+### Clusters
 
-## 2D projections
+### 2D projections
 
 Below, I list an schematic proposal of the classes: