def ted_cv_w2v():
maxlen = 20
folds = range(1,11)
trains = ['data/TED/train'+str(fold)+'.csv' for fold in folds]
tests = ['data/TED/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,
0, maxlen, embd_type='w2v')
acc = cnn1d_w2vembd(X_train, Y_train, X_test, Y_test, nb_classes,
maxlen,
100, 5, 50, 20, 'rmsprop')
accs.append(acc)
acc_cv = np.mean(accs)
print('after 10-fold cv:' + str(acc_cv))
def asap_cv_w2v():
maxlen = 40
folds = range(1,11)
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)
w2v = load_w2v('data/Google_w2v.bin')
print("loaded Google word2vec")
kappas = []
for (train, test) in pairs:
print(train + '=>' + test)
X_train, Y_train, X_test, Y_test, nb_classes = load_csvs(train, test,
0, maxlen, embd_type='w2v', w2v=w2v)
kappa = cnn1d_w2vembd(X_train, Y_train, X_test, Y_test, nb_classes,
maxlen,
100, 3, 50, 20, 'rmsprop')
kappas.append(kappa)
kappa_cv = np.mean(kappas)
print('after 10-fold cv:' + str(kappa_cv))
def pun_cv_w2v():
maxlen = 20
folds = range(1,11)
trains = ['data/pun_of_day/train'+str(fold)+'.csv' for fold in folds]
tests = ['data/pun_of_day/test'+str(fold)+'.csv' for fold in folds]
pairs = zip(trains, tests)
w2v = load_w2v('data/Google_w2v.bin')
print("loaded Google word2vec")
accs = []
for (train, test) in pairs:
print(train + '=>' + test)
X_train, Y_train, X_test, Y_test, nb_classes = load_csvs(train, test,
0, maxlen, embd_type='w2v', w2v=w2v)
acc = cnn1d_w2vembd(X_train, Y_train, X_test, Y_test, nb_classes,
maxlen,
100, 5, 50, 20, 'rmsprop')
accs.append(acc)
acc_cv = np.mean(accs)
print('after 10-fold cv:' + str(acc_cv))
def test_ted_w2v():
maxlen = 20
X_train, Y_train, X_test, Y_test, nb_classes = load_ted(0, maxlen, 'w2v')
cnn1d_w2vembd(X_train, Y_train, X_test, Y_test, nb_classes,
maxlen,
100, 5, 50, 20, 'rmsprop')
def test_sg15_w2v():
maxlen = 120
X_train, Y_train, X_test, Y_test, nb_classes = load_sg15(0, maxlen, 'w2v')
cnn1d_w2vembd(X_train, Y_train, X_test, Y_test, nb_classes,
maxlen,
100, 10, 64, 20, 'rmsprop')
