def process_line(packed_line):
line, i, X_test, y_test, verbose = packed_line
split = line.split()
params = np.array(split[1:]).astype(np.float)
w = matricize_W(params)
t = matricize_Tij(params)
predictions = decode_crf(X_test, w, t)
word_acc, char_acc = compute_word_char_accuracy_score(predictions, y_test)
if verbose:
print(str(i) + ": ", word_acc)
return (1. - word_acc)
def save_word_error(result_file, output_file, X_test, y_test):
f_vals = []
file = open(result_file, 'r')
lines = file.readlines()
file.close()
for i, line in enumerate(lines):
split = line.split()
print(i, ": ", end='')
params = np.array(split[1:]).astype(np.float)
w = matricize_W(params)
t = matricize_Tij(params)
predictions = decode_crf(X_test, w, t)
word_acc, char_acc = compute_word_char_accuracy_score(predictions, y_test)
print(word_acc)
# only word accuracy so just accuracy[0]
f_vals.append(str(1 - word_acc) + "\n")
file = open(output_file, 'w')
file.writelines(f_vals)
file.close()
if sum(abs(parameters - previous_params)) <= self.epsilon or iteration == self.iterations:
break
return parameters
if __name__ == '__main__':
LAMBDA = 1e-2
X_train, y_train = prepare_dataset("train_sgd.txt")
X_test, y_test = prepare_dataset("test_sgd.txt")
filepath = "%s_%s.txt" % ('GIBBS', LAMBDA)
callback = Callback(X_train, y_train, filepath, LAMBDA)
gibbs = SamplingOptimizer(LAMBDA, callback_fn=callback.callback_fn_return_vals)
opt_params = gibbs.train(X_train)
W = matricize_W(opt_params)
T = matricize_Tij(opt_params)
y_preds = decode_crf(X_train, W, T)
word_acc, char_acc = compute_word_char_accuracy_score(y_preds, y_train)
print("Final train accuracy :", "Word =", word_acc, "Char =", char_acc)
y_preds = decode_crf(X_test, W, T)
word_acc, char_acc = compute_word_char_accuracy_score(y_preds, y_test)
print("Final test accuracy :", "Word =", word_acc, "Char =", char_acc)
for lambd in LAMBDAS:
filepath = FILENAME_FMT % (OPTIMIZATION_NAME, lambd)
remove_file(filepath)
# maintain a callback to measure loss and average gradient every epoch
callback = Callback(X_train, y_train, filepath, lambd)
# train using BFGS
optimal_params = optimize(params, X_train, y_train, lambd,
callback.callback_fn)
w = matricize_W(optimal_params)
t = matricize_Tij(optimal_params)
y_pred = decode_crf(X_train, w, t)
word_acc, char_acc = compute_word_char_accuracy_score(y_pred, y_train)
print("Train accuracies")
print("Character accuracies :", char_acc)
print("Word Accuracies :", word_acc)
y_pred = decode_crf(X_test, w, t)
word_acc, char_acc = compute_word_char_accuracy_score(y_pred, y_test)
print("Test accuracies")
print("Character accuracies :", char_acc)
print("Word Accuracies :", word_acc)
print()