def kmeans_select_best(features,
ks,
repeats=1,
method='AIC',
R=None,
**kwargs):
'''
assignments_centroids = kmeans_select_best(features, ks, repeats=1, method='AIC', R=None, **kwargs)
Perform ``repeats`` calls to ``kmeans`` for each ``k`` in ``ks``, select
the best one according to ``method.``
Note that, unlike a raw ``kmeans`` call, this is *always deterministic*
even if ``R=None`` (which is interpreted as being equivalent to setting it
to a fixed value). Otherwise, the jug paradigm would be broken as different
runs would give different results.
Parameters
----------
features : array-like
2D array
ks : sequence of integers
These will be the values of ``k`` to try
repeats : integer, optional
How many times to attempt each k (default: 1).
method : str, optional
Which method to use. Must be one of 'AIC' (default) or 'BIC'.
R : random number source, optional
Even you do not pass a value, the result will be deterministic. This is
different from the typical behaviour of ``R``, but, when using jug,
reproducibility is often but, when using jug, reproducibility is often
a desired feature.
kwargs : other options
These are passed transparently to ``kmeans``
Returns
-------
assignments_centroids : jug.Task
jug.Task which is the result of the best (as measured by ``method``)
kmeans clustering.
'''
from milk import kmeans
from milk.utils import get_pyrandom
kmeans = TaskGenerator(kmeans)
if R is not None:
start = get_pyrandom(R).randint(0, 1024 * 1024)
else:
start = 7
results = []
for ki, k in enumerate(ks):
for i in xrange(repeats):
results.append(
kmeans(features, k, R=(start + 7 * repeats * ki + i),
**kwargs))
return _select_best(features, results, method)[1]
def kmeans_select_best(features, ks, repeats=1, method='AIC', R=None, **kwargs):
'''
assignments_centroids = kmeans_select_best(features, ks, repeats=1, method='AIC', R=None, **kwargs)
Perform ``repeats`` calls to ``kmeans`` for each ``k`` in ``ks``, select
the best one according to ``method.``
Note that, unlike a raw ``kmeans`` call, this is *always deterministic*
even if ``R=None`` (which is interpreted as being equivalent to setting it
to a fixed value). Otherwise, the jug paradigm would be broken as different
runs would give different results.
Parameters
----------
features : array-like
2D array
ks : sequence of integers
These will be the values of ``k`` to try
repeats : integer, optional
How many times to attempt each k (default: 1).
method : str, optional
Which method to use. Must be one of 'AIC' (default) or 'BIC'.
R : random number source, optional
Even you do not pass a value, the result will be deterministic. This is
different from the typical behaviour of ``R``, but, when using jug,
reproducibility is often but, when using jug, reproducibility is often
a desired feature.
kwargs : other options
These are passed transparently to ``kmeans``
Returns
-------
assignments_centroids : jug.Task
jug.Task which is the result of the best (as measured by ``method``)
kmeans clustering.
'''
from milk import kmeans
from milk.utils import get_pyrandom
kmeans = TaskGenerator(kmeans)
if R is not None:
start = get_pyrandom(R).randint(0,1024*1024)
else:
start = 7
results = []
for ki,k in enumerate(ks):
for i in xrange(repeats):
results.append(kmeans(features, k, R=(start+7*repeats*ki+i), **kwargs))
return _select_best(features, results, method)[1]
def kmeans_select_best(features, ks, repeats=1, method='AIC', R=None, **kwargs):
'''
assignments_centroids = kmeans_select_best(features, ks, repeats=1, method='AIC', R=None, **kwargs)
Perform ``repeats`` calls to ``kmeans`` for each ``k`` in ``ks``, select
the best one according to ``method.``
Note that, unlike a raw ``kmeans`` call, this is *always deterministic*
even if ``R=None``.
Parameters
----------
features : array-like
2D array
ks : sequence of integers
These will be the values of ``k`` to try
repeats : integer, optional
How many times to attempt each k (default: 1).
method : str, optional
Which method to use. Must be one of 'AIC' (default) or 'BIC'.
R : random number source, optional
If you do not pass a value, the result will be deterministic
kwargs : other options
These are passed transparently to ``kmeans``
Returns
-------
assignments_centroids : jug.Task
jug.Task which is the result of the best (as measured by ``method``)
kmeans clustering.
'''
from milk import kmeans
from milk.utils import get_pyrandom
kmeans = TaskGenerator(kmeans)
if R is not None:
start = get_pyrandom(R).randint(0,1024*1024)
else:
start = 7
results = []
for ki,k in enumerate(ks):
for i in xrange(repeats):
results.append(kmeans(features, k, R=(start+7*repeats*ki+i), **kwargs))
return _select_best(features, results, method)
