def test_sample_kmeans_density_estimation(data, density_exponent,
cluster_balance_threshold):
X, y = data
smote = KMeansSMOTE(random_state=42,
density_exponent=density_exponent,
cluster_balance_threshold=cluster_balance_threshold)
smote.fit_sample(X, y)
def test_sample_kmeans_not_enough_clusters():
rng = np.random.RandomState(42)
X = rng.randn(30, 2)
y = np.array([1] * 20 + [0] * 10)
smote = KMeansSMOTE(random_state=42, kmeans_estimator=30, k_neighbors=2)
with pytest.raises(RuntimeError):
smote.fit_sample(X, y)
def test_sample_kmeans_custom(data, k_neighbors, kmeans_estimator):
X, y = data
kmeans_smote = KMeansSMOTE(random_state=42,
kmeans_estimator=kmeans_estimator,
k_neighbors=k_neighbors)
X_resampled, y_resampled = kmeans_smote.fit_sample(X, y)
assert X_resampled.shape == (24, 2)
assert y_resampled.shape == (24, )
assert kmeans_smote.nn_k_.n_neighbors == 3
assert kmeans_smote.kmeans_estimator_.n_clusters == 3
def test_kmeans_smote(data):
X, y = data
kmeans_smote = KMeansSMOTE(kmeans_estimator=1,
random_state=42,
cluster_balance_threshold=0.0,
k_neighbors=5)
smote = SMOTE(random_state=42)
X_res_1, y_res_1 = kmeans_smote.fit_sample(X, y)
X_res_2, y_res_2 = smote.fit_sample(X, y)
assert_allclose(X_res_1, X_res_2)
assert_array_equal(y_res_1, y_res_2)
assert kmeans_smote.nn_k_.n_neighbors == 6
assert kmeans_smote.kmeans_estimator_.n_clusters == 1
assert 'batch_size' in kmeans_smote.kmeans_estimator_.get_params()
X_train = imp.fit_transform(X_train) # 训练集插补
X_test = imp.transform(X_test) # 测试集插补
prep = StandardScaler()
X_train = prep.fit_transform(X_train)
X_test = prep.transform(X_test)
ops_ada = ADASYN(random_state=10)
ops_bsmote = BorderlineSMOTE(random_state=10)
ops_ksmote = KMeansSMOTE(random_state=10)
ops_rs = RandomOverSampler(random_state=10)
ops_s = SMOTE(random_state=10)
X_train_ada, y_train_ada = ops_ada.fit_sample(X_train, y_train)
X_train_bsmote, y_train_bsmote = ops_bsmote.fit_sample(X_train, y_train)
X_train_ksmote, y_train_ksmote = ops_ksmote.fit_sample(X_train, y_train)
X_train_rs, y_train_rs = ops_rs.fit_sample(X_train, y_train)
X_train_s, y_train_s = ops_s.fit_sample(X_train, y_train)
dic_ = {
'ADASYN': [X_train_ada, y_train_ada],
'BorderlineSMOTE': [X_train_bsmote, y_train_bsmote],
'RandomOverSampler': [X_train_rs, y_train_rs],
'SMOTE': [X_train_s, y_train_s]
}
for t in dic_.keys():
print('over sampler: %s \n' % t)
X_ = dic_[t][0]
y_ = dic_[t][1]
X_t = X_test
res = adaBoost.predict(features[test_index])
bl_smote_scores['AB'] += metrics.f1_score(res, target[test_index])
bl_smote_con_mat['AB'] += confusion_matrix(y_true=target[test_index],
y_pred=res)
# Gradient Boost Classifier
gradBoost = GradientBoostingClassifier(random_state=0)
gradBoost.fit(X_train, y_train)
res = gradBoost.predict(features[test_index])
bl_smote_scores['GB'] += metrics.f1_score(res, target[test_index])
bl_smote_con_mat['GB'] += confusion_matrix(y_true=target[test_index],
y_pred=res)
# K-Means Smote
km_smote = KMeansSMOTE(random_state=0)
X_train, y_train = km_smote.fit_sample(features[train_index],
target[train_index])
# unique, counts = np.unique(y_train, return_counts=True)
# print("Kmeans uni, count:",np.asarray((unique, counts)).T)
# Logistic Regression
logistic = LogisticRegression(random_state=0)
logistic.fit(X_train, y_train)
res = logistic.predict(features[test_index])
km_scores['LR'] += metrics.f1_score(res, target[test_index])
km_con_mat['LR'] += confusion_matrix(y_true=target[test_index], y_pred=res)
#
# Ada Boost Classifier
adaBoost = AdaBoostClassifier(random_state=0)
adaBoost.fit(X_train, y_train)
res = adaBoost.predict(features[test_index])
km_scores['AB'] += metrics.f1_score(res, target[test_index])
y = np.ravel(y)
print(y.shape)
X_train, X_test, y_train, y_test = train_test_split(x,
y,
test_size=0.2,
stratify=y,
random_state=42)
# forest.fit(X_train, y_train)
# print("Original set\n{}".format(classification_report(y_test, forest.predict(X_test))))
pca = PCA(n_components=2)
# Fit and transform x to visualise inside a 2D feature space
X_vis = pca.fit_transform(X_train)
# Apply the random over-sampling
ada = KMeansSMOTE(random_state=42)
X_resampled, y_resampled = ada.fit_sample(X_train, y_train)
y_resampled = np.ravel(y_resampled)
forest.fit(X_resampled, y_resampled)
print(Counter(y_resampled))
print(y_resampled.shape)
X_res_vis = pca.transform(X_resampled)
print("KMeansSMOTE\n{}".format(
classification_report(y_test, forest.predict(X_test))))
f, (ax1, ax2) = plt.subplots(1, 2)
c0 = ax1.scatter(X_vis[y_train == 0, 0],
X_vis[y_train == 0, 1],
label="Class #0",
alpha=0.5)
def kmeans_smote(x, y):
print("----KMeans SMOTE----")
sampler = KMeansSMOTE(random_state=42)
X, y = sampler.fit_sample(x, y)
return X, y