I am trying to do K- means clustering with scipy following this tutorial: http://glowingpython.blogspot.no/2012/04/k-means-clustering-with-scipy.html
The problem is that he uses vstack to make the arbitrary datapoints, which in turn returns an ndarray. I have two lists: lengths and breadths. How do I combine them to an ndarray so I can use his example?
lengths = [300.0, 300.0, 300.0, 300.0, 303.0, 300.0]
breadths = [9.6, 9.7, 9.8, 10.3, 6.8, 9.4]
Numpy's vstack will just accept these as lists fine:
In [23]: np.vstack((lengths, breadths))
Out[23]:
array([[ 300. , 300. , 300. , 300. , 303. , 300. ],
[ 9.6, 9.7, 9.8, 10.3, 6.8, 9.4]])
If you want to explicitely convert it to an array, you can do:
In [24]: np.array(lengths)
Out[24]: array([ 300., 300., 300., 300., 303., 300.])
However, I think in the case of this example kmeans expects the observations as different rows, so you need the transpose: np.vstack((lengths, breadths)).T
