def makeRank(self, rank = 'phylum', subtree = None):
#Get the subtree and db connections to build meta for
tree = subtree if subtree != None else self.t
dbi = cbdb.getName('taxdmp')
print 'Fetching taxonomic nodes from the db'
#Get the terminal nodes and corresponding ncbi taxa
terms = [t for t in tree.get_terminals() if t.m.has_key('taxid')]
nodes = [dbi.S.q(dbi.Node).filter_by(id = t.m['taxid']).scalar()
for t in terms]
#endpoints for parental iteratiion
taxa = ncbi.get_rank(rank)
root = ncbi.get_root()
print 'Computing terminal node mappings for taxon: {0}'.format(rank)
bar = pbar.simple(len(nodes)); bar.start()
node_taxa = list(nodes)
get_p_iter = lambda: \
node_taxa[idx] == None and True \
or node_taxa[idx] in taxa and True \
or node_taxa[idx] == root and True \
or node_taxa.__setitem__(idx,node_taxa[idx].parent) \
or node_taxa[idx]
for idx, v in enumerate(node_taxa):
bar.update(idx);
par = list(iter(get_p_iter, True))[-1] if v else None
terms[idx].m[rank] = par.id if par in taxa else None
bar.finish()
print 'Done!'
def testParams(self, model_class, prediction="test", res=10, dim=1):
# set up the grid of prediction parameters
if len(shape(res)) == 0:
res = (res,) * dim
test_vals = list(it.product(*[[(x, r) for x in arange(r)] for r in res]))
# shall we predict holdout or training set?
if prediction == "training":
xyfun = self.xyTrain
predictfun = self.predictTraining
else:
xyfun = self.xyTest
predictfun = self.predictTest
# set initial values for output variables
ntest = len(xyfun()[1][0])
rms = zeros(res)
pdicts = reshape(array([{} for i in range(product(res))]), res)
test_preds = reshape(array([zeros(ntest) for i in range(product(res))]), concatenate([res + (ntest,)]))
# test the learning method for each parameter
bar = pbar.simple(len(test_vals))
ct = 0
for t in test_vals:
ct += 1
bar.update(ct)
pdict = {}
idxs = zip(map(lambda x: x[0], t))
self.setModel(model_class(params=t, pdict=pdicts[idxs][0]))
self.learn()
xtest, ytest = xyfun()
ypred = predictfun()
rms[idxs] = std(ytest - ypred)
test_preds[idxs] = ypred
bar.finish()
# create a dictionary of all of the output variables
out = {}
out["pdicts"] = pdicts
out["test_rms"] = rms
out["test_preds"] = test_preds
out["actual_preds"] = ytest
print ytest
return out