def _test_determenistic(distance, algorithm, weight, k):
x_train, x_test, y_train, y_test = \
train_test_split(IRIS.data, IRIS.target,
test_size=0.33, random_state=31)
alg_results = []
for _ in range(N_TRIES):
# models
scikit_model = ScikitKNeighborsClassifier(n_neighbors=k,
weights=weight,
algorithm=algorithm,
leaf_size=30,
p=2,
metric=distance)
daal_model = DaalKNeighborsClassifier(n_neighbors=k,
weights=weight,
algorithm=algorithm,
leaf_size=30,
p=2,
metric=distance)
# training
scikit_model.fit(x_train, y_train)
daal_model.fit(x_train, y_train)
# predict
scikit_predict = scikit_model.predict(x_test)
daal_predict = daal_model.predict(x_test)
distances, indices = daal_model.kneighbors(x_test)
alg_results.append((distances, indices, daal_predict))
# accuracy
scikit_accuracy = accuracy_score(y_test, scikit_predict)
daal_accuracy = accuracy_score(y_test, daal_predict)
ratio = daal_accuracy / scikit_accuracy
assert ratio >= ACCURACY_RATIO,\
f'kNN accuracy: scikit_accuracy={scikit_accuracy},daal_accuracy={daal_accuracy}, ratio={ratio}'
# predict proba
scikit_predict_proba = scikit_model.predict_proba(x_test)
daal_predict_proba = daal_model.predict_proba(x_test)
# log loss
scikit_log_loss = log_loss(y_test, scikit_predict_proba)
daal_log_loss = log_loss(y_test, daal_predict_proba)
ratio = daal_log_loss / scikit_log_loss
assert ratio <= LOG_LOSS_RATIO,\
f'kNN log_loss: scikit_log_loss={scikit_log_loss},daal_log_loss={daal_log_loss}, ratio={ratio}'
# ROC AUC
scikit_roc_auc = roc_auc_score(y_test,
scikit_predict_proba,
multi_class='ovr')
daal_roc_auc = roc_auc_score(y_test,
daal_predict_proba,
multi_class='ovr')
ratio = daal_roc_auc / scikit_roc_auc
assert ratio >= ROC_AUC_RATIO,\
f'kNN roc_auc: scikit_roc_auc={scikit_roc_auc},daal_roc_auc={daal_roc_auc}, ratio={ratio}'
for i in range(1, N_TRIES):
for j, res in enumerate(alg_results[i]):
assert (res == alg_results[0][j]).mean() == 1, \
f'Results are different between runs for {algorithm}, {weight}, {distance}, k={k}'
def kfold_function_template(self, data_transform_function):
tracemalloc.start()
x, y, data_memory_size = self.gen_clsf_data()
kf = KFold(n_splits=10)
x, y = data_transform_function(x, y)
mem_before, _ = tracemalloc.get_traced_memory()
for train_index, test_index in kf.split(x):
if isinstance(x, np.ndarray):
x_train, x_test = x[train_index], x[test_index]
y_train, y_test = y[train_index], y[test_index]
elif isinstance(x, pd.core.frame.DataFrame):
x_train, x_test = x.iloc[train_index], x.iloc[test_index]
y_train, y_test = y.iloc[train_index], y.iloc[test_index]
knn = KNeighborsClassifier()
knn.fit(x_train, y_train)
del knn, x_train, x_test, y_train, y_test
mem_after, _ = tracemalloc.get_traced_memory()
tracemalloc.stop()
self.assertTrue(
mem_after - mem_before < 0.25 * data_memory_size,
'Size of extra allocated memory is greater than 25% of input data')
def check_determenistic(distance, algorithm, weight, k):
x_train, x_test, y_train, y_test = make_dataset()
alg_results = []
for _ in range(N_TRIES):
alg = KNeighborsClassifier(n_neighbors=k,
weights=weight,
algorithm=algorithm,
leaf_size=30,
p=2,
metric=distance)
alg.fit(x_train, y_train)
distances, indices = alg.kneighbors(x_test)
labels = alg.predict(x_test)
alg_results.append((distances, indices, labels))
accuracy = accuracy_score(labels, y_test)
assert accuracy >= CHECK_RATIO_KNN,\
'kNN classifier:accuracy={}'.format(accuracy)
for i in range(1, N_TRIES):
for j, res in enumerate(alg_results[i]):
assert (res == alg_results[0][j]).mean() == 1, \
('Results are different between runs for %s, %s, %s, k=%d'\
% (algorithm, weight, distance, k))
def test_KNeighborsClassifier(self):
check_estimator(KNeighborsClassifier(algorithm='kd_tree'))
test_size=0.5,
shuffle=True):
x, y = make_classification(n_samples=n_samples,
n_features=n_features,
n_classes=n_classes,
random_state=777)
return train_test_split(x,
y,
random_state=777,
test_size=test_size,
shuffle=shuffle)
ESTIMATORS = {
'KNeighborsClassifier':
KNeighborsClassifier(n_neighbors=10),
'DaalRandomForestClassifier':
DaalRandomForestClassifier(n_estimators=10, random_state=777),
'DaalRandomForestRegressor':
DaalRandomForestRegressor(n_estimators=10, random_state=777),
}
ORDERS = ['C', 'F']
DATA_FORMATS = [pd.DataFrame, np.array]
def check_data_formats_diff(name):
x_train, x_test, y_train, y_test = make_dataset()
alg_results = []
for data_format in DATA_FORMATS:
for order in ORDERS: