_, f1 = model.predict(testX, batch_size=1024)
testX = np.concatenate([f1, testX], axis=1)
Y = clf.predict(testX)
utils.submit(Y)
else:
testX = utils.load_test_data(submit)
Y = np.array(
list(
map(
idx2word.get,
np.argmax(model.predict(testX, batch_size=1024)[0],
axis=-1))))
utils.submit(Y)
elif svm:
X, Y = utils.load_train_data(data_path)
Y = Y.astype(int)
trainX = np.delete(X, [1, 6, 11], axis=1)
_, f1 = model.predict(trainX, batch_size=1024)
X[:, 0] = f1.ravel()
clf_svm(X, Y, save_model=svm)
else:
model.load_weights(model_path)
#print(f'\n\033[32;1mTraining score: {model.evaluate(trainX, trainY, verbose=0)}')
#print(f'Validation Score: {model.evaluate(validX, validY, verbose=0)}\033[0m')
print(
f'\n\033[32;1mTraining score: {model.evaluate(trainX, [trainY, missing_col], verbose=0, batch_size=1024)}'
)
print(
f'Validation Score: {model.evaluate(validX, [validY, valid_missing_col], verbose=0, batch_size=1024)}\033[0m'
)
testX[:, 0:1], f2, testX[:, 1:5], f7, testX[:, 5:9], f12, testX[:,
9:]
],
axis=1)
Y = clf.predict(testX)
utils.submit(Y)
else:
out = tf.cast(out * 2, tf.int32)
submit_model = Model(I, out)
utils.submit(submit_model, submit)
elif svm:
X, Y = utils.load_train_data(data_path)
Y = Y.astype(int)
trainX = np.delete(X, [1, 6, 11], axis=1)
_, f2, f7, f12 = model.predict(trainX, batch_size=1024)
X[:, 1] = f2.ravel()
X[:, 6] = f7.ravel()
X[:, 11] = f12.ravel()
clf_svm(X, Y, seed, save_model=svm)
else:
trainX, trainY = utils.load_train_data(data_path)
trainY = trainY.astype(int)
trainX, validX, trainY, validY = utils.train_test_split(trainX,
trainY,
seed=seed)
missing_col, valid_missing_col = trainX[:, [1, 6, 11]], validX[:,
[1, 6, 11]]
trainX = np.delete(trainX, [1, 6, 11], axis=1)
validX = np.delete(validX, [1, 6, 11], axis=1)
print(
f'\n\033[32;1mTraining score: {model.evaluate(trainX, [trainY, missing_col[:, 0], missing_col[:, 1], missing_col[:, 2]], verbose=0)}'