def main(args):
"""
@param args: from argparse
"""
# get some state that will not change between k-means restarts
with open(args.table_filename) as fin:
rtable = RUtil.RTable(fin)
points = get_rtable_info(rtable, args.annotation, args.axes)
init_strategy = kmeans.InitStrategy().string_to_function(args.kmeans_init)
gs = GlobalState(rtable, points, args.annotation, args.k, init_strategy)
# go until iteration is stopped for some reason
print combobreaker.run_callable(
ClusterState(gs), args.nseconds, args.nrestarts)
def get_form():
"""
@return: the body of a form
"""
form_objects = [
Form.MultiLine('table', 'R table', g_default),
Form.Sequence('axes', 'column labels of Euclidean axes',
('pc1', 'pc2', 'pc3')),
Form.Integer('k', 'maximum number of clusters',
2, low=2),
Form.SingleLine('annotation', 'header of added column',
'cluster'),
kmeans.InitStrategy()]
return form_objects
def get_form():
"""
@return: the body of a form
"""
form_objects = [
Form.MultiLine('table', 'R table', g_default),
Form.Sequence('axes', 'column labels of Euclidean axes',
('pc1', 'pc2', 'pc3')),
kmeans.InitStrategy(),
Form.CheckGroup(
'options', 'more options',
[Form.CheckItem('verbose', 'show calinski index values', True)])
]
return form_objects
def get_response_content(fs):
rtable = RUtil.RTable(fs.table.splitlines())
header_row = rtable.headers
data_rows = rtable.data
points = get_rtable_info(rtable, fs.annotation, fs.axes)
# do the clustering
nrestarts = 10
init_strategy = kmeans.InitStrategy().string_to_function(fs.kmeans_init)
wcss, labels = kmeans.lloyd_with_restarts(
points, fs.k, nrestarts, init_strategy)
# get the response
lines = ['\t'.join(header_row + [fs.annotation])]
for i, (label, data_row) in enumerate(zip(labels, data_rows)):
row = data_row + [str(label)]
lines.append('\t'.join(row))
# return the response
return '\n'.join(lines) + '\n'
@param args: from argparse
"""
# get some state that will not change between k-means restarts
with open(args.table_filename) as fin:
rtable = RUtil.RTable(fin)
points = get_rtable_info(rtable, args.annotation, args.axes)
init_strategy = kmeans.InitStrategy().string_to_function(args.kmeans_init)
gs = GlobalState(rtable, points, args.annotation, args.k, init_strategy)
# go until iteration is stopped for some reason
print combobreaker.run_callable(
ClusterState(gs), args.nseconds, args.nrestarts)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument('--table_filename', required=True,
help='R table filename')
parser.add_argument('--axes', required=True,
type=moretypes.whitespace_separated_sequence,
help='column labels of Euclidean axes')
parser.add_argument('--k', type=moretypes.int_ge(2), required=True,
help='target number of clusters')
parser.add_argument('--annotation', default='cluster',
help='header of added column')
parser.add_argument('--nrestarts', type=moretypes.positive_integer,
help='restart the k-means iterative refinement this many times')
parser.add_argument('--nseconds', type=moretypes.positive_float,
help='run for this many seconds')
kmeans.InitStrategy().add_argument(parser)
main(parser.parse_args())
def get_response_content(fs):
# get the initialization strategy
init_strategy = kmeans.InitStrategy().string_to_function(fs.kmeans_init)
# read the table
rtable = RUtil.RTable(fs.table.splitlines())
header_row = rtable.headers
data_rows = rtable.data
Carbone.validate_headers(header_row)
# get the numpy array of conformant points
h_to_i = dict((h, i + 1) for i, h in enumerate(header_row))
axis_headers = fs.axes
if not axis_headers:
raise ValueError('no Euclidean axes were provided')
axis_set = set(axis_headers)
header_set = set(header_row)
bad_axes = axis_set - header_set
if bad_axes:
raise ValueError('invalid axes: ' + ', '.join(bad_axes))
axis_lists = []
for h in axis_headers:
index = h_to_i[h]
try:
axis_list = Carbone.get_numeric_column(data_rows, index)
except Carbone.NumericError:
msg_a = 'expected the axis column %s ' % h
msg_b = 'to be numeric'
raise ValueError(msg_a + msg_b)
axis_lists.append(axis_list)
points = np.array(zip(*axis_lists))
# precompute some stuff
allmeandist = kmeans.get_allmeandist(points)
nrestarts = 10
nseconds = 2
tm = time.time()
n = len(points)
wgss_list = []
# neg because both items in the pair are used for sorting
neg_calinski_k_pairs = []
# look for the best calinski index in a small amount of time
k = 2
while True:
wgss, labels = kmeans.lloyd_with_restarts(points, k, nrestarts,
init_strategy)
bgss = allmeandist - wgss
calinski = kmeans.get_calinski_index(bgss, wgss, k, n)
k_unique = len(set(labels))
neg_calinski_k_pairs.append((-calinski, k_unique))
wgss_list.append(wgss)
if time.time() - tm > nseconds:
break
if k == n - 1:
break
k += 1
max_k = k
best_neg_calinski, best_k = min(neg_calinski_k_pairs)
best_calinski = -best_neg_calinski
# create the response
out = StringIO()
print >> out, 'best cluster count: k = %d' % best_k
print >> out, 'searched 2 <= k <= %d clusters' % max_k
print >> out, '%.2f seconds' % (time.time() - tm)
if fs.verbose:
print >> out
print >> out, '(k_unique, wgss, calinski):'
for wgss, neg_calinski_k_pair in zip(wgss_list, neg_calinski_k_pairs):
neg_calinski, k_unique = neg_calinski_k_pair
calinski = -neg_calinski
row = [k_unique, wgss, calinski]
print >> out, '\t'.join(str(x) for x in row)
# return the response
return out.getvalue()