def mols_having_best_feat(penalty='l1', c=1, num_folds=10):
df_t3 = task3_res()
coefs = []
for cv_seed, group in df_t3.groupby(['cv_seed']):
print(cv_seed, len(group))
# Iterate over the 5 cv seeds for the same num_cv_folds:
for _, gr in df_t3.result.items():
# average over the different folds
# print df_t3.C
# print df_t3.num_cv_folds
# print df_t3.cv_seed
coefs.append(np.mean(np.array([gr.logreg_coefs(i).ravel() for i in range(num_folds)]), axis=0))
av_coefs = np.mean(np.array(coefs), axis=0)
index_of_best = np.argmax(av_coefs)
mfm = MalariaFingerprintsManager(dset='lab')
feat = mfm.i2s(index_of_best)
print(feat)
# feat = 'n1c(S(C)(=O)=O)sc(N)c1S(c)(=O)=O'
molids = mfm.mols_with_feature(feat)
mc = MalariaCatalog()
mols = mc.molids2mols(molids)
labels = mc.molids2labels(molids, as01=True)
print(len(mols))
draw_in_a_grid_aligned_according_to_pattern(mols, feat,
op.join(MALARIA_EXPS_ROOT, 'logregs', 'Mols_having_best_fpt.png'),
legends=molids, classes=labels)
def from_feat_back_to_mols_faster(dset, smi):
"""
Retrieves the list of molecules that contain the given feature in the given dataset.
"""
# The non-folded version is easy
mfm = MalariaFingerprintsManager(dset=dset)
X = mfm.X()
col = mfm.s2i(smi) # the column where we have to look for in the X matrix
cooX = X.tocoo()
indices_mols = cooX.row[cooX.col == col]
molids = [mfm.i2m(i) for i in indices_mols]
mc = MalariaCatalog()
activities = [mc.label(molid, as01=True) for molid in molids]
mols = mc.molids2mols(molids)
return zip(mols, molids, indices_mols, activities)
