def tpo_cv_cnnvar():
maxlen = 200
nb_words = 6500
embd_dim = 100
folds = range(1, 11)
trains = ['data/tpov4/train_'+str(fold)+'.csv' for fold in folds]
tests = ['data/tpov4/test_'+str(fold)+'.csv' for fold in folds]
pairs = zip(trains, tests)
accs = []
for (train, test) in pairs:
print(train + '=>' + test)
X_train, Y_train, X_test, Y_test, nb_classes = load_csvs(train, test,
nb_words, maxlen, embd_type='self', w2v=None)
acc = cnn_var_selfembd(X_train, Y_train, X_test, Y_test, nb_classes,
maxlen, nb_words, embd_dim,
50, 32, 25, 'rmsprop')
accs.append(acc)
acc_cv = np.mean(accs)
print('after 10-fold cv:' + str(acc_cv))
def asap_cv_cnnvar():
maxlen = 75
nb_words = 4500
embd_dim = 50
folds = (1,2,3,4,5,6,7,8,9,10)
trains = ['data/asap2/train'+str(fold)+'.csv' for fold in folds]
tests = ['data/asap2/test'+str(fold)+'.csv' for fold in folds]
pairs = zip(trains, tests)
kappas = []
for (train, test) in pairs:
print(train + '=>' + test)
X_train, Y_train, X_test, Y_test, nb_classes = load_csvs(train, test,
nb_words, maxlen, embd_type='self', w2v=None)
kappa = cnn_var_selfembd(X_train, Y_train, X_test, Y_test, nb_classes,
maxlen, nb_words, embd_dim,
50, 32, 30, 'rmsprop')
kappas.append(kappa)
kappa_cv = metrics.mean_quadratic_weighted_kappa(kappas)
print('after 10-fold cv:' + str(kappa_cv))