def test_fit_resample_half():
# Define the sampling_strategy parameter
sampling_strategy = {0: 2, 1: 3, 2: 3}
# Create the sampling object
ee = EasyEnsemble(
sampling_strategy=sampling_strategy,
random_state=RND_SEED,
n_subsets=3)
# Get the different subset
X_resampled, y_resampled = ee.fit_resample(X, Y)
X_gt = np.array([[[-0.58539673, 0.62515052], [0.85117925, 1.0185556],
[1.35269503, 0.44812421], [-1.23195149, 0.15427291],
[0.5220963, 0.11349303], [1.10915364, 0.05718352],
[0.59091459, 0.40692742], [0.22039505, 0.26469445]],
[[0.85117925, 1.0185556], [-0.58539673, 0.62515052],
[1.35269503, 0.44812421], [-2.10724436, 0.70263997],
[-1.23195149, 0.15427291], [0.59091459, 0.40692742],
[0.22039505, 0.26469445], [1.10915364, 0.05718352]],
[[0.85117925, 1.0185556], [-0.58539673, 0.62515052],
[-1.23195149, 0.15427291], [0.5220963, 0.11349303],
[1.35269503, 0.44812421], [1.10915364, 0.05718352],
[0.59091459, 0.40692742], [0.22039505, 0.26469445]]])
y_gt = np.array([[0, 0, 1, 1, 1, 2, 2, 2], [0, 0, 1, 1, 1, 2, 2, 2],
[0, 0, 1, 1, 1, 2, 2, 2]])
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_fit_resample_half():
# Define the sampling_strategy parameter
sampling_strategy = {0: 2, 1: 3, 2: 3}
# Create the sampling object
ee = EasyEnsemble(sampling_strategy=sampling_strategy,
random_state=RND_SEED,
n_subsets=3)
# Get the different subset
X_resampled, y_resampled = ee.fit_resample(X, Y)
X_gt = np.array([[[-0.58539673, 0.62515052], [0.85117925, 1.0185556],
[1.35269503, 0.44812421], [-1.23195149, 0.15427291],
[0.5220963, 0.11349303], [1.10915364, 0.05718352],
[0.59091459, 0.40692742], [0.22039505, 0.26469445]],
[[0.85117925, 1.0185556], [-0.58539673, 0.62515052],
[1.35269503, 0.44812421], [-2.10724436, 0.70263997],
[-1.23195149, 0.15427291], [0.59091459, 0.40692742],
[0.22039505, 0.26469445], [1.10915364, 0.05718352]],
[[0.85117925, 1.0185556], [-0.58539673, 0.62515052],
[-1.23195149, 0.15427291], [0.5220963, 0.11349303],
[1.35269503, 0.44812421], [1.10915364, 0.05718352],
[0.59091459, 0.40692742], [0.22039505, 0.26469445]]])
y_gt = np.array([[0, 0, 1, 1, 1, 2, 2, 2], [0, 0, 1, 1, 1, 2, 2, 2],
[0, 0, 1, 1, 1, 2, 2, 2]])
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_random_state_none():
# Define the sampling_strategy parameter
sampling_strategy = 'auto'
# Create the sampling object
ee = EasyEnsemble(sampling_strategy=sampling_strategy, random_state=None)
# Get the different subset
X_resampled, y_resampled = ee.fit_resample(X, Y)
def test_random_state_none():
# Define the sampling_strategy parameter
sampling_strategy = 'auto'
# Create the sampling object
ee = EasyEnsemble(sampling_strategy=sampling_strategy, random_state=None)
# Get the different subset
X_resampled, y_resampled = ee.fit_resample(X, Y)
def ensemble_sample(self,
method="BalanceCascade",
sampling_strategy="majority",
random_state=42,
replacement=True):
"""
下采样方法
:param method: str, option:'EasyEnsemble','BalanceCascade'
:param sampling_strategy: 采样策略, str, dict, 'majority','not minority','not majority','all','auto'
:param random_state:int
:param replacement: bool
:return:df
"""
feature_name = self._df.columns.difference(["id",
self._target]).tolist()
X = self._df[feature_name].values
y = self._df[self._target].values
print("Original label shape {}".format(Counter(y)))
if method == "EasyEnsemble":
enS = EasyEnsemble(sampling_strategy=sampling_strategy,
random_state=random_state,
replacement=replacement)
elif method == "BalanceCascade":
enS = BalanceCascade(sampling_strategy=sampling_strategy,
random_state=random_state)
else:
print("不支持{}该抽样方法".format(method))
return self._df
X_res, y_res = enS.fit_resample(X, y)
print("enSample label shape {}".format(Counter(y_res)))
_data = np.concatenate([X_res, y_res.reshape(len(X_res), 1)], axis=1)
df_new = pd.DataFrame(data=_data,
columns=feature_name + [self._target])
return df_new
n_informative=3,
n_redundant=1,
flip_y=0,
n_features=20,
n_clusters_per_class=1,
n_samples=100,
random_state=10)
# Instanciate a PCA object for the sake of easy visualisation
pca = PCA(n_components=2)
# Fit and transform x to visualise inside a 2D feature space
X_vis = pca.fit_transform(X)
# Apply Easy Ensemble
ee = EasyEnsemble(n_subsets=3)
X_resampled, y_resampled = ee.fit_resample(X, y)
X_res_vis = []
for X_res in X_resampled:
X_res_vis.append(pca.transform(X_res))
# Two subplots, unpack the axes array immediately
f, (ax1, ax2) = plt.subplots(1, 2)
ax1.scatter(X_vis[y == 0, 0], X_vis[y == 0, 1], label="Class #0", alpha=0.5)
ax1.scatter(X_vis[y == 1, 0], X_vis[y == 1, 1], label="Class #1", alpha=0.5)
ax1.set_title('Original set')
ax2.scatter(X_vis[y == 0, 0], X_vis[y == 0, 1], label="Class #0", alpha=0.5)
for iy, e in enumerate(X_res_vis):
ax2.scatter(e[y_resampled[iy] == 1, 0],
e[y_resampled[iy] == 1, 1],
print(__doc__)
# Generate the dataset
X, y = make_classification(n_classes=2, class_sep=2, weights=[0.3, 0.7],
n_informative=3, n_redundant=1, flip_y=0,
n_features=20, n_clusters_per_class=1,
n_samples=100, random_state=10)
# Instanciate a PCA object for the sake of easy visualisation
pca = PCA(n_components=2)
# Fit and transform x to visualise inside a 2D feature space
X_vis = pca.fit_transform(X)
# Apply Easy Ensemble
ee = EasyEnsemble(n_subsets=3)
X_resampled, y_resampled = ee.fit_resample(X, y)
X_res_vis = []
for X_res in X_resampled:
X_res_vis.append(pca.transform(X_res))
# Two subplots, unpack the axes array immediately
f, (ax1, ax2) = plt.subplots(1, 2)
ax1.scatter(X_vis[y == 0, 0], X_vis[y == 0, 1], label="Class #0", alpha=0.5)
ax1.scatter(X_vis[y == 1, 0], X_vis[y == 1, 1], label="Class #1", alpha=0.5)
ax1.set_title('Original set')
ax2.scatter(X_vis[y == 0, 0], X_vis[y == 0, 1], label="Class #0", alpha=0.5)
for iy, e in enumerate(X_res_vis):
ax2.scatter(e[y_resampled[iy] == 1, 0], e[y_resampled[iy] == 1, 1],
label="Class #1 - set #{}".format(iy), alpha=0.5)
