def _encode_categorical(self, X, y):
"""TODO"""
# compute the median of the standard deviation of the minority class
target_stats = Counter(y)
class_minority = min(target_stats, key=target_stats.get)
# Separate categorical features from continuous features
X_continuous = X[:, self.continuous_features_]
X_continuous = check_array(X_continuous, accept_sparse=["csr", "csc"])
X_categorical = X[:, self.categorical_features_].copy()
X_minority = X_continuous[np.flatnonzero(y == class_minority)]
if sparse.issparse(X):
if X.format == "csr":
_, var = csr_mean_variance_axis0(X_minority)
else:
_, var = csc_mean_variance_axis0(X_minority)
else:
var = X_minority.var(axis=0)
self.median_std_ = np.median(np.sqrt(var))
if X_continuous.dtype.name != "object":
dtype_ohe = X_continuous.dtype
else:
dtype_ohe = np.float64
self.ohe_ = OneHotEncoder(sparse=True, handle_unknown="ignore", dtype=dtype_ohe)
# the input of the OneHotEncoder needs to be dense
X_ohe = self.ohe_.fit_transform(
X_categorical.toarray() if sparse.issparse(X_categorical) else X_categorical
)
# we can replace the 1 entries of the categorical features with the
# median of the standard deviation. It will ensure that whenever
# distance is computed between 2 samples, the difference will be equal
# to the median of the standard deviation as in the original paper.
# In the edge case where the median of the std is equal to 0, the 1s
# entries will be also nullified. In this case, we store the original
# categorical encoding which will be later used for inversing the OHE
if math.isclose(self.median_std_, 0):
self._X_categorical_encoded = X_ohe.toarray()
X_ohe.data = np.ones_like(X_ohe.data, dtype=X_ohe.dtype) * self.median_std_ / 2
if self._issparse:
X_encoded = np.hstack([X_continuous.toarray(), X_ohe.toarray()])
else:
X_encoded = np.hstack([X_continuous, X_ohe.toarray()])
return X_encoded
def _fit_resample(self, X, y):
self.n_features_ = X.shape[1]
self._validate_estimator()
# compute the median of the standard deviation of the minority class
target_stats = Counter(y)
class_minority = min(target_stats, key=target_stats.get)
X_continuous = X[:, self.continuous_features_]
X_continuous = check_array(X_continuous, accept_sparse=['csr', 'csc'])
X_minority = safe_indexing(X_continuous,
np.flatnonzero(y == class_minority))
if sparse.issparse(X):
if X.format == 'csr':
_, var = csr_mean_variance_axis0(X_minority)
else:
_, var = csc_mean_variance_axis0(X_minority)
else:
var = X_minority.var(axis=0)
self.median_std_ = np.median(np.sqrt(var))
X_categorical = X[:, self.categorical_features_]
if X_continuous.dtype.name != 'object':
dtype_ohe = X_continuous.dtype
else:
dtype_ohe = np.float64
self.ohe_ = OneHotEncoder(sparse=True, handle_unknown='ignore',
dtype=dtype_ohe)
# the input of the OneHotEncoder needs to be dense
X_ohe = self.ohe_.fit_transform(
X_categorical.toarray() if sparse.issparse(X_categorical)
else X_categorical)
# we can replace the 1 entries of the categorical features with the
# median of the standard deviation. It will ensure that whenever
# distance is computed between 2 samples, the difference will be equal
# to the median of the standard deviation as in the original paper.
X_ohe.data = (np.ones_like(X_ohe.data, dtype=X_ohe.dtype) *
self.median_std_ / 2)
X_encoded = sparse.hstack((X_continuous, X_ohe), format='csr')
X_resampled, y_resampled = super(SMOTENC, self)._fit_resample(
X_encoded, y)
# reverse the encoding of the categorical features
X_res_cat = X_resampled[:, self.continuous_features_.size:]
X_res_cat.data = np.ones_like(X_res_cat.data)
X_res_cat_dec = self.ohe_.inverse_transform(X_res_cat)
if sparse.issparse(X):
X_resampled = sparse.hstack(
(X_resampled[:, :self.continuous_features_.size],
X_res_cat_dec), format='csr'
)
else:
X_resampled = np.hstack(
(X_resampled[:, :self.continuous_features_.size].toarray(),
X_res_cat_dec)
)
indices_reordered = np.argsort(
np.hstack((self.continuous_features_, self.categorical_features_))
)
if sparse.issparse(X_resampled):
# the matrix is supposed to be in the CSR format after the stacking
col_indices = X_resampled.indices.copy()
for idx, col_idx in enumerate(indices_reordered):
mask = X_resampled.indices == col_idx
col_indices[mask] = idx
X_resampled.indices = col_indices
else:
X_resampled = X_resampled[:, indices_reordered]
return X_resampled, y_resampled
def _fit_resample(self, X, y):
# FIXME: to be removed in 0.12
if self.n_jobs is not None:
warnings.warn(
"The parameter `n_jobs` has been deprecated in 0.10 and will be "
"removed in 0.12. You can pass an nearest neighbors estimator where "
"`n_jobs` is already set instead.",
FutureWarning,
)
self.n_features_ = X.shape[1]
self._validate_estimator()
# compute the median of the standard deviation of the minority class
target_stats = Counter(y)
class_minority = min(target_stats, key=target_stats.get)
X_continuous = X[:, self.continuous_features_]
X_continuous = check_array(X_continuous, accept_sparse=["csr", "csc"])
X_minority = _safe_indexing(X_continuous,
np.flatnonzero(y == class_minority))
if sparse.issparse(X):
if X.format == "csr":
_, var = csr_mean_variance_axis0(X_minority)
else:
_, var = csc_mean_variance_axis0(X_minority)
else:
var = X_minority.var(axis=0)
self.median_std_ = np.median(np.sqrt(var))
X_categorical = X[:, self.categorical_features_]
if X_continuous.dtype.name != "object":
dtype_ohe = X_continuous.dtype
else:
dtype_ohe = np.float64
self.ohe_ = OneHotEncoder(sparse=True,
handle_unknown="ignore",
dtype=dtype_ohe)
# the input of the OneHotEncoder needs to be dense
X_ohe = self.ohe_.fit_transform(X_categorical.toarray(
) if sparse.issparse(X_categorical) else X_categorical)
# we can replace the 1 entries of the categorical features with the
# median of the standard deviation. It will ensure that whenever
# distance is computed between 2 samples, the difference will be equal
# to the median of the standard deviation as in the original paper.
# In the edge case where the median of the std is equal to 0, the 1s
# entries will be also nullified. In this case, we store the original
# categorical encoding which will be later used for inversing the OHE
if math.isclose(self.median_std_, 0):
self._X_categorical_minority_encoded = _safe_indexing(
X_ohe.toarray(), np.flatnonzero(y == class_minority))
X_ohe.data = np.ones_like(X_ohe.data,
dtype=X_ohe.dtype) * self.median_std_ / 2
X_encoded = sparse.hstack((X_continuous, X_ohe), format="csr")
X_resampled, y_resampled = super()._fit_resample(X_encoded, y)
# reverse the encoding of the categorical features
X_res_cat = X_resampled[:, self.continuous_features_.size:]
X_res_cat.data = np.ones_like(X_res_cat.data)
X_res_cat_dec = self.ohe_.inverse_transform(X_res_cat)
if sparse.issparse(X):
X_resampled = sparse.hstack(
(
X_resampled[:, :self.continuous_features_.size],
X_res_cat_dec,
),
format="csr",
)
else:
X_resampled = np.hstack((
X_resampled[:, :self.continuous_features_.size].toarray(),
X_res_cat_dec,
))
indices_reordered = np.argsort(
np.hstack((self.continuous_features_, self.categorical_features_)))
if sparse.issparse(X_resampled):
# the matrix is supposed to be in the CSR format after the stacking
col_indices = X_resampled.indices.copy()
for idx, col_idx in enumerate(indices_reordered):
mask = X_resampled.indices == col_idx
col_indices[mask] = idx
X_resampled.indices = col_indices
else:
X_resampled = X_resampled[:, indices_reordered]
return X_resampled, y_resampled
