[mlpack-git] [mlpack/mlpack] Spill trees (#747)

[Ryan Curtin]

> +  }
> +
> +  std::vector<size_t> leftPoints, rightPoints;
> +  // Split the node.
> +  overlappingNode = SplitPoints(tau, rho, points, leftPoints, rightPoints);
> +
> +  // We don't need the information in points, so lets clean it.
> +  std::vector<size_t>().swap(points);
> +
> +  // Now we will recursively split the children by calling their constructors
> +  // (which perform this splitting process).
> +  left = new SpillTree(this, leftPoints, tau, maxLeafSize, rho);
> +  right = new SpillTree(this, rightPoints, tau, maxLeafSize, rho);
> +
> +  // Update count number, to represent the number of descendant points.
> +  count = left->NumDescendants() + right->NumDescendants();

I have a concern about this.  This means that `NumDescendants()` of the root can actually be greater than `dataset.n_cols`, but I think this can cause problems.  If we refactor so that `NumDescendants()` of the root returns `dataset.n_cols`, then `Descendant()` will be a little more complex: you'll just have to rearrange the point indices so that the first `n` elements are the non-shared elements, and possibly hold another member to indicate how many non-shared elements the node has. 

---
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/747/files/a71b57caa90311f5542180bc0553449c3691395d#r73718848
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20160805/77ae3381/attachment.html>