def predict(name, sp, arrsource, arrfeats, nsp, clf_scaler_feats=None,
clf_factory=None, clffact_feats=None, clf_type='svm', norm=True, nfeats=100, balance_train=False):
"""
- arrfeats: labeled training examples array, from
ppi.feature_array.arrfeats, also stored in res.cvtest result as
result.exs.arrfeats.
- arrsource: array of data to classify, matching the training array
"""
if clf_scaler_feats:
clf, scaler, feats = clf_scaler_feats
else:
if balance_train:
arrfeats = fe.balance_train(arrfeats)
if clf_type in clf_factories and clf_factory is None:
clf_factory, clffact_feats = clf_factories[clf_type]
feats = feature_selection(arrfeats, nfeats, clffact_feats() if clffact_feats
else None)
arrfeats = fe.keep_cols(arrfeats, feats)
clf = clf_factory()
scaler = ml.fit_clf(arrfeats, clf, norm=norm)
print "Classifier:", clf
arrsource = fe.keep_cols(arrsource, feats)
ppis = ml.classify(clf, arrsource, scaler=scaler)
pres = Struct(ppis=ppis,name=name, species=sp, ppi_params=str(clf),
feats=feats, nsp=nsp, arrfeats=arrfeats,
balance_train=balance_train)
return pres
def fold_test(arrfeats, kfold, k, clf_factory, clffact_feats, nfeats, norm,
balance_train):
arrtrain, arrtest = fe.arr_kfold(arrfeats, kfold, k)
if balance_train:
arrtrain = fe.balance_train(arrtrain)
if nfeats:
clf_feats = clffact_feats()
feats = feature_selection(arrtrain, nfeats, clf_feats)
arrtrain,arrtest = [fe.keep_cols(a,feats) for a in arrtrain,arrtest]
else:
feats = None
clf = clf_factory()
if k==0: print "Classifier:", clf
scaler = ml.fit_clf(arrtrain, clf, norm=norm)
if ml.exist_pos_neg(arrtrain):
ppis = ml.classify(clf, arrtest, scaler=scaler, do_sort=False)
else:
ppis = []
return ppis,clf,scaler,feats