srefdf = pickle.load(f)
### II. Set the split to use
with open('../../Preproc/PreProcOut/saiapr_90-10_splits.json', 'r') as f:
ssplit90 = json.load(f)
srefdf_t = filter_by_filelist(srefdf, ssplit90['train'])
### III. Preprocess: remove relational expressions from training
srefdf_tr = filter_relational_expr(srefdf_t)
### IV. Set list of words to train
wordlist = wordlist_by_criterion(srefdf_tr, model['wrdl'], model['wprm'])
### V. Get the region features
X = np.load('../../ExtractFeats/ExtrFeatsOut/saiapr.npz')
X = X['arr_0']
### VI. And... train away!
clsf = train_model(srefdf_tr, X, wordlist,
(linear_model.LogisticRegression, {'penalty':'l1'}),
nneg=model['nneg'], nsrc=model['nsrc'])
with gzip.open('../TrainedModels/' + basename + '.pklz', 'w') as f:
pickle.dump(clsf, f)
with open('../../Preproc/PreProcOut/saiapr_90-10_splits.json', 'r') as f:
ssplit90 = json.load(f)
tlist_a = ssplit90['train']
tlist_b = splits['train']
tlist = tlist_a + tlist_b
refdf_t = filter_by_filelist(refdf, tlist)
### III. Preprocess: remove relational expressions from training
refdf_tr = filter_relational_expr(refdf_t)
### IV. Set list of words to train
wordlist = wordlist_by_criterion(refdf_tr, model['wrdl'], model['wprm'])
### V. Get the region features
X_a = np.load('../../ExtractFeats/ExtrFeatsOut/saiapr.npz')
X_a = X_a['arr_0']
X_b = np.load('../../ExtractFeats/ExtrFeatsOut/mscoco.npz')
X_b = X_b['arr_0']
X = np.concatenate([X_a, X_b])
### VI. And... train away!
clsf = train_model(refdf_tr,
X,
