def __init__(
self,
collection,
nclusters,
metric='euc',
tmpdir=None,
):
if not isinstance(nclusters, int) or nclusters <= 1:
raise Exception('Need appropriate value for number of clusters.')
self.nclusters = nclusters
self.scorer = Scorer(collection.records,
collection.analysis) # Could check for entries
self.datatype = collection.datatype
self.metric = metric
try:
self.tmpdir
except:
self.tmpdir = collection.tmpdir
def __init__(self, nclusters, collection, tmpdir=TMPDIR,
analysis='nj', initial_assignment=None, scorer=None):
optioncheck(analysis, ANALYSES + ['tc', 'TreeCollection'])
if self.analysis == 'tc':
self.analysis = 'TreeCollection'
else:
self.analysis = analysis
self.Collection = collection
if not self.Collection.records[0].tree:
print('Calculating {} trees for collection...'.format(analysis))
self.Collection.calc_NJ_trees()
self.datatype = collection.datatype
if scorer is not None and isinstance(scorer, Scorer):
self.scorer = scorer
else:
self.scorer = Scorer(self.Collection)
self.nclusters = nclusters
self.tmpdir = tmpdir
print('Calculating initial scores...')
if initial_assignment is None:
initial_assignment = Partition(tuple([0] * len(collection)))
# initial_assignment = self.random_partition(nclusters)
self.global_best_scores = {}
self.global_best_assignments = {}
self.global_best_scores[self.nclusters] = self.scorer.score(
initial_assignment, history=True)
self.global_best_assignments[self.nclusters] = initial_assignment
self.done_worse = 0
self.stayed_put = 0
self.i = 0
self.resets = 0
self.merges = 0
def __init__(self, members, records, analysis):
self.members = tuple(members)
self.records = [records[i] for i in self.members]
self.scorer = Scorer(records, analysis)
self.tree = self.scorer.add(self.members)
#!/usr/bin/env python
from collection import Collection, Scorer
from clustering import Partition
from random import randint
from anneal import *
import pickle
c = Collection(input_dir='/homes/mgperry/treeCl_data/easy_case/', compression='gz', file_format='phylip', datatype='protein')
scorer = Scorer(c.records, 'nj')
k = 4
partition = [randint(1, k) for rec in scorer.records]
def likelihood(partition, scorer):
score = scorer.score(Partition(partition))
return(score)
print type(partition)
opts = {'func': likelihood,
'x0': partition,
'args': [scorer],
'schedule': 'cluster',
'full_output': 1,
'T0': 100000,
'Tf': 1,
'maxeval': None,
