Support-Vector-Machine | simple implementation of support vector machine classifier | Machine Learning library

The sentence refers to the sentence before that:

Note that if we comment out the drop id column part, accuracy goes back down into the 60s.

and the KNearestNeighbors tutorial where the change in model performance is investigated if 'useless' data (aka noise), like the indices of the data points, is fed to the model as input.

[...] let's show what happens when we do indeed include truly meaningless and misleading data by commenting out the dropping of the id column

The conclusion here is that SVMs handle meaningless features, noise or 'pointless data' in the input better than KNNs.

Altair features an image mark that can be used if you want to plot images that are available at a URL; for example:

"Two horizontal curves" is a set of data where you have two arrays y1 and y2 defined on a single support x.
Equally, "two vertical curves" would be a set of data where you have a single y support for two x arrays.

You can see the following link: https://cran.r-project.org/web/packages/e1071/vignettes/svmdoc.pdf

The link shows the dual problem formulation of the SVM algorithm this package uses (when one use one-class SVM, page 7 index (3)), easy transformation from the dual to the primal problem shows that this default implementation is the one Schölkopf suggested, see paper: https://www.stat.purdue.edu/~yuzhu/stat598m3/Papers/NewSVM.pdf

You can get the correct classified with diag:

If you're that strapped for space, you'll probably want to skip scikit and simply implement the math yourself. That way, you can cycle through the data in structures of your own choosing. Memory requirements depend on the class of SVM you're using; a two-class linear SVM can be done with a single pass through the data, considering only one observation at a time as you accumulate sum-of-products, so your command logic would take far more space than the data requirements.

If you need to keep the entire data set in memory for multiple passes, that's "only" 5000*10*8 bytes for floats, or 400k of your 1Mb, which might be enough room to do your manipulations. Also consider a slow training process, re-reading the data on each pass, as this reduces the 400k to a triviality at the cost of wall-clock time.

All of this is under your control if you look up a usable SVM implementation and alter the I/O portions as needed.

Does that help?

Here is a vectorized version. The non poly branch comes in two variants a direct one and a memory saving one in case the number of features is large: