def Qc(train_set, test_set, laplace=False):
"""Handles the tasks of question c
Arguments:
train_set
test_set
Keyword Arguments:
laplace {bool} -- are we to use Laplace smoothing or not (default: {False})
"""
gen_error_vec = []
known_error_vec = []
unknown_error_vec = []
viterbi_results = []
train_set = clean_POS(train_set)
test_set = clean_POS(test_set)
S = initialize_S(train_set)
probs = Probabilities(S, train_set=train_set, test_set=test_set)
for xy_tup in test_set:
x = [t[0] for t in xy_tup]
y = [t[1] for t in xy_tup]
viterbi_tags = viterbi(x, probs, laplace)
viterbi_results.append(viterbi_tags)
err_vec, known_0, unknonwn_0 = (calculate_error(
viterbi_tags, y, x, probs))
gen_error_vec.append(err_vec[0])
if not known_0: known_error_vec.append(err_vec[1])
if not unknonwn_0: unknown_error_vec.append(err_vec[2])
gen_error = statistics.mean(gen_error_vec)
known_error = statistics.mean(known_error_vec)
unknown_error = statistics.mean(unknown_error_vec)
return [gen_error, known_error, unknown_error]
def Qe(train_set, test_set, laplace=False):
"""Handles tasks of question e
Arguments:
train_set
test_set
Keyword Arguments:
laplace {bool} -- (default: {False})
"""
# initializations
viterbi_results = []
gen_error_vec = []
known_error_vec = []
unknown_error_vec = []
# "clean" the train and test sets from complex tags
train_set = clean_POS(train_set)
test_set = clean_POS(test_set)
S = initialize_S(train_set)
probs = Probabilities(S, train_set, test_set)
# Generate pseudo train and test sets and probability object
pseudo_train = probs.generate_pseudo_set(train_set)
pseudo_test = probs.generate_pseudo_set(test_set)
pseudo_probs = Probabilities(S, pseudo_train, pseudo_test)
for xy_tup in pseudo_test:
x = [t[0] for t in xy_tup]
y = [t[1] for t in xy_tup]
viterbi_tags = viterbi(x, pseudo_probs, laplace)
viterbi_results.append(viterbi_tags)
err_vec, _, _ = (calculate_error(viterbi_tags, y, x, probs, True))
gen_error_vec.append(err_vec[0])
# update confusion values
pseudo_probs.update_confusion_matrix(y, viterbi_tags)
gen_error = statistics.mean(gen_error_vec)
print(gen_error)
# print results and statistics
if laplace:
print(DataFrame(confusion_matrix(S, pseudo_probs)))
return gen_error
