def single_features():
train = get_train_dev_data()
test = get_test_data()
for i_bal, balanced in enumerate([False, True]):
for classifier in classifier_names:
if balanced and classifier in classifiers_not_supporting_balancing:
continue
for feature_name in all_feature_names:
print(feature_name)
accuracies = []
for i in range(15):
params = SingleBaseParams(feature_name,
classifier,
dirname=sklearn_master_name,
params={'balanced': balanced},
pca=False)
a = generate_probabilities(train,
test,
params,
test_only=True)
print('\t', i, feature_name, classifier, a)
accuracies.append(a * 100)
l, r = confidence_intervals(accuracies)
m = float(np.mean([l, r]))
balanced_str = "balanced" if balanced else "not_balanced"
results = "%s & %s & %s & %.3f & %.1f-%.1f" % (
balanced_str, feature_name, classifier, m, l, r)
print(results)
with open("out/conf_int/base/" + feature_name + ".txt",
'a') as f:
f.write("%s\n" % results)
def multiple_features(dirname):
train = get_train_dev_data()
test = get_test_data()
all_subsets = get_feature_name_sets_with_highest_probable_accuracy(dirname)
n_features = len(all_subsets)
n_classifiers = len(classifier_names)
print(n_features)
max_a = 0.
for i_bal, balanced in enumerate([False]):
for ic, classifier in enumerate(classifier_names):
if balanced and classifier in classifiers_not_supporting_balancing:
continue
for ifnl, feature_names_list in enumerate(all_subsets):
print('Balanced', balanced)
print('Classifier: ', ic, ' out of ', n_classifiers,
classifier)
print('Features ', ifnl, ' out of ', n_features)
print('Progress ',
(((((i_bal)) * 2 + ic) * n_features) + ifnl) /
(n_classifiers * n_features * 2 * 2) * 100., '%')
accs = []
for i in range(10):
params = MultiBaseParams(features=feature_names_list,
classifier=classifier,
dirname=dirname,
pca=False,
params={'balanced': balanced})
a = generate_probabilities(train,
test,
params,
test_only=True)
accs.append(a * 100)
l, r = confidence_intervals(accs)
m = float(np.mean([l, r]))
balanced_str = "balanced" if balanced else "not_balanced"
results = "%s & %s & %s & %.3f & %.1f-%.1f" % (
balanced_str, ' '.join(feature_names_list), classifier, m,
l, r)
print(results)
with open("out/conf_int/" + dirname + "/all.txt", 'a') as f:
f.write("%s\n" % results)
max_a = max(max_a, m)
print("max accuracy: %0.4f current accuracy %0.4f\n" %
(max_a, m))
def multiple_features(test_only=False):
train = get_train_dev_data()
test = get_test_data()
all_subsets = get_all_feature_subsets()
for classifier in classifier_names:
for subset in all_subsets:
print(subset)
params = MultiBaseParams(features=subset,
classifier=classifier,
dirname="new",
params={},
pca=False)
generate_probabilities(train, test, params, test_only=test_only)
params.serialize()
def single_features():
train = get_train_dev_data()
test = get_test_data()
for classifier in classifiers.keys():
for feature in all_feature_names:
print(feature)
params = SingleBaseParams(feature_name=feature,
classifier=classifier,
dirname="new",
params={},
pca=False)
run_grid_search(train=train,
test=test,
params=params,
parameters=classifiers[classifier])
def single_features(test_only=False):
train = get_train_dev_data()
test = get_test_data()
for classifier in classifier_names:
for feature in [publication_type_key]:
print(feature)
params = SingleBaseParams(feature_name=feature,
classifier=classifier,
dirname="new",
params={},
pca=False)
generate_probabilities(train=train,
test=test,
params=params,
test_only=test_only)
params.serialize()
def multiple_features():
train = get_train_dev_data()
test = get_test_data()
# all_subsets = get_all_feature_subsets()
all_subsets = [[publication_type_key, publication_year_key]]
for classifier in classifiers.keys():
for subset in all_subsets:
print(subset)
params = MultiBaseParams(features=subset,
classifier=classifier,
dirname="new",
params={},
pca=False)
run_grid_search(train,
test,
params,
parameters=classifiers[classifier])