def test_aggregation():
test_decisions = np.array([0, 0, 1, 1, 0, 1, 0, 1, 1, 0, 0, 1])
given_p = np.array([[1 / 3, 2 / 5, 3 / 7], [1 / 3, 3 / 5, 4 / 7],
[1, 3 / 5, 5 / 7]])
fuzzy_sets = np.zeros((3, 2))
f = KNNAlgorithmF(aggregation=A1Aggregation())
uncertainty_intervals = np.zeros(shape=(3, 2))
expected_uncertainty_intervals = np.array([[0.3873, 0.3873],
[0.5015, 0.5015],
[0.7714, 0.7714]])
expected_final_ps = np.array([0.3873, 0.5015, 0.7714])
for i in range(3):
k = 0
for j in range(len((3, 5, 7))):
fuzzy_sets[k] = np.array([given_p[i, j], given_p[i, j]])
k += 1
uncertainty_interval = f.aggregation.aggregate(fuzzy_sets)
uncertainty_intervals[i] = uncertainty_interval
print(uncertainty_interval)
final_p = uncertainty_interval.sum() / 2
print(final_p)
assert_array_equal(uncertainty_intervals, expected_uncertainty_intervals)
y = LabelEncoder().fit_transform(y)
X = MinMaxScaler().fit_transform(X)
missing = (0.0, 0.01, 0.05, 0.1, 0.2, 0.3, 0.4, 0.5)
dfs = []
ind = 0
ks = [(2, 4), (3, 5)]
for miss in missing:
for agg in (A1Aggregation(), A2Aggregation(), A3Aggregation(), A4Aggregation(p=3), A5Aggregation(), A6Aggregation(),
A7Aggregation(), A8Aggregation(), A9Aggregation(), A10Aggregation()):
for r in (2, 5, 10):
for k in ks:
X_missing = MissingValuesInserterColumnsIndependent(columns=range(X.shape[1]), nan_representation=-1, percentage=miss)\
.fit_transform(X)
multiclassF = OneVsRestClassifierForRandomBinaryClassifier(KNNAlgorithmF(missing_representation=-1, r=r, aggregation=agg, k_neighbours=k))
f_result = cross_validate(multiclassF, X_missing, y, scoring='roc_auc_ovo', return_estimator=True, cv=10)
w = pd.DataFrame({'algorithm': 'f', 'k': str(k), 'r': f_result['estimator'][0].estimator.r,
'agg': Aggregation.change_aggregation_to_name(f_result['estimator'][0].estimator.aggregation), 'missing': miss,
'auc': np.mean(f_result['test_score']), 'stddev': stdev(f_result['test_score'])}, index=[ind])
print(w)
dfs.append(w)
ind += 1
concatenated = pd.concat(dfs)
concatenated = pd.concat(dfs)
concatenated.to_excel('concatenated_vertebral.xlsx')
for miss in missing:
for k in ks:
X_missing = MissingValuesInserterColumnsIndependent(columns=range(X.shape[1]), nan_representation=-1, percentage=miss) \
missing = (0.0, 0.01, 0.05, 0.1, 0.2, 0.3, 0.4, 0.5)
dfs = []
ind = 0
ks = [(3, 5), (2, 4)]
for miss in missing:
for agg in (A1Aggregation(), A2Aggregation(), A3Aggregation(),
A4Aggregation(p=3), A5Aggregation(), A6Aggregation(),
A7Aggregation(), A8Aggregation(), A9Aggregation(),
A10Aggregation()):
for r in (2, 5, 10):
for k in ks:
X_missing = MissingValuesInserterColumnsIndependent(columns=range(X.shape[1]), nan_representation=-1, percentage=miss)\
.fit_transform(X)
multiclassF = OneVsRestClassifierForRandomBinaryClassifier(
KNNAlgorithmF(missing_representation=-1,
r=r,
aggregation=agg,
k_neighbours=k))
f_result = cross_validate(multiclassF,
X_missing,
y,
scoring='roc_auc_ovo',
return_estimator=True,
cv=10)
w = pd.DataFrame(
{
'algorithm':
'f',
'k':
str(k),
'r':
f_result['estimator'][0].estimator.r,
def test_compute_final_p():
X, y = load_iris(True)
f = KNNAlgorithmF()
f.fit(X, y)
assert_array_equal(f.compute_final_p(X), f.compute_final_p_opt(X))