def triple_venn_consv():
hints = co.load_havug_ints()
ppi_cxs, clean_cxs, corconsv = ppi.load_training_complexes("Hs", "Dm")
cints = co.pairs_from_complexes(ut.i1(ppi_cxs)) # exclude huge ones
ints23 = ut.loadpy(ut.bigd("../23_collapsenodes/Hs_filtorth025_withsc_2sp_refilt2sp_cxs_cxppis_clust27_532cxs"))[1]
ints3 = [cp.consv_pairs(i, h2d) for i in ints23, hints, cints]
cp.triple_venn(ints3, ["map23", "havug", "corum"])
def compact(d, scoref, precision=3):
sys.path.append(d+'/..')
import utils as ut
compactf = '%s.p%s.txt.gz' % (scoref, precision)
print compactf, precision
ascores = (ut.loadpy(scoref) if scoref.endswith('.py') else
np.loadtxt(scoref))
formatstring = '%' + '0.%se' % precision
np.savetxt(compactf, ascores, fmt=formatstring, delimiter='\t')
def precalc_scores(scoref, dtype='f2'):
"""
Also zero out the diagonal to more efficiently remove all self-interactions
up-front.
"""
# NOTE to change dtype you must change it in loadtxt below!!
save_compact = ut.config()['save_compact_corrs']
compactf = '%s.%s.pyd' % (scoref, dtype)
if os.path.exists(compactf):
mat = ut.loadpy(compactf)
inds = range(mat.shape[0]) # always square score matrix
mat[inds, inds] = 0
return mat
else:
ascores = np.loadtxt(scoref, dtype='f2')
if save_compact:
print 'saving compact', compactf
ut.savepy(ascores, compactf)
return ascores
def precalc_scores(scoref, dtype='f2'):
"""
Also zero out the diagonal to more efficiently remove all self-interactions
up-front.
"""
# NOTE to change dtype you must change it in loadtxt below!!
save_compact = ut.config()['save_compact_corrs']
compactf = '%s.%s.pyd' % (scoref, dtype)
if os.path.exists(compactf):
mat = ut.loadpy(compactf)
inds = range(mat.shape[0]) # always square score matrix
mat[inds, inds] = 0
return mat
else:
ascores = np.loadtxt(scoref, dtype='f2')
if save_compact:
print 'saving compact', compactf
ut.savepy(ascores, compactf)
return ascores
# Plot the feature importances of the trees and of the forest
if do_plot:
import pylab as pl
pl.figure()
pl.title("Feature importances")
for tree in forest.estimators_:
pl.plot(indnums, tree.feature_importances_[indices], "r")
pl.plot(indnums, importances[indices], "b")
pl.show()
feats, weights = zip(*ranked)
return list(feats), list(weights)
if __name__ == '__main__':
if len(sys.argv) < 4:
sys.exit("usage: python ml.py train_test feats_f clf_type \
donorm kwarg1_val1-kwarg2-val2")
ttf = sys.argv[1]
tt = np.load(ttf)
feats = ut.loadpy(sys.argv[2])
k = sys.argv[3]
do_norm = sys.argv[4]
kvs = sys.argv[5]
kwargs = dict([tuple(kv.split('_')) for kv in kvs.split('-')]) \
if kvs else {}
clf = tree(**kwargs) if k=='tree' else svm(kernel=k, **kwargs)
ts = [('%s features, %s kernel, norm: %s, %s' %(n,k,do_norm, kvs),
fit_and_test([fe.keep_cols(t, ut.i0(feats[:n])) for t in tt],
clf, norm=do_norm))
for n in 20,30,40,50]
ut.savepy(ts, 'ts_%s_%s_%s_%s' %(k,do_norm,kvs,ttf))
if len([1 for m in maxes[i] if m > cutoff]) >= nsp]
arrfilt = arr[exceed_inds]
if do_counts:
orig_sp_counts = [len([1 for m in maxes[i] if m > cutoff]) for i in
range(len(arr))]
sp_counts_filt = [c for c in orig_sp_counts if c >=nsp]
pd_spcounts = pd.PairDict([[arrfilt[i][0],arrfilt[i][1],
sp_counts_filt[i]]
for i in range(len(arrfilt))])
else:
pd_spcounts = None
return arrfilt, pd_spcounts
def filter_nsp_nocounts(arr, **kwargs):
return filter_nsp(arr, do_counts=False, **kwargs)[0]
if __name__ == '__main__':
nargs = len(sys.argv)
if nargs < 6:
sys.exit("usage: python myml.py f_examples f_classifier \
perslice islice path")
exs = np.load(sys.argv[1])
clf = ut.loadpy(sys.argv[2])
perslice = int(sys.argv[3])
i = int(sys.argv[4])
path = sys.argv[5]
exs_slice = exs[i*perslice:(i+1)*perslice]
del exs
classify_slice(clf, exs_slice, 100000, savef=(path+str(i)+'_'),
maintain=False, startslice=0)
