def test_monotonic_validate_invert_labels(arr_type, dtype, copy):
arr = np.array([0, 15, 10, 50, 20, 50], dtype=dtype)
original = arr.copy()
if arr_type == "cp":
arr = cp.asarray(arr, dtype=dtype)
arr_orig = arr.copy()
monotonic, mapped_classes = make_monotonic(arr, copy=copy)
cp.cuda.Stream.null.synchronize()
assert array_equal(monotonic.get(), np.array([0, 2, 1, 4, 3, 4]))
# We only care about in-place updating if data is on device
if arr_type == "cp":
if copy:
assert array_equal(arr_orig.get(), arr.get())
else:
assert array_equal(arr.get(), monotonic.get())
wrong_classes = cp.asarray([0, 1, 2], dtype=dtype)
val_labels = check_labels(monotonic.get(), classes=wrong_classes)
cp.cuda.Stream.null.synchronize()
assert not val_labels
correct_classes = cp.asarray([0, 1, 2, 3, 4], dtype=dtype)
val_labels = check_labels(monotonic.get(), classes=correct_classes)
cp.cuda.Stream.null.synchronize()
assert val_labels
if arr_type == "cp":
monotonic_copy = monotonic.copy()
inverted = invert_labels(monotonic,
classes=cp.asarray([0, 10, 15, 20, 50],
dtype=dtype),
copy=copy)
cp.cuda.Stream.null.synchronize()
if arr_type == "cp":
if copy:
assert array_equal(monotonic_copy.get(), monotonic.get())
else:
assert array_equal(monotonic.get(), arr_orig.get())
assert array_equal(inverted.get(), original)
def _local_cm(inputs, labels, use_sample_weight):
if use_sample_weight:
y_true, y_pred, sample_weight = inputs
else:
y_true, y_pred = inputs
sample_weight = cp.ones(y_true.shape[0], dtype=y_true.dtype)
y_true, _ = make_monotonic(y_true, labels, copy=True)
y_pred, _ = make_monotonic(y_pred, labels, copy=True)
n_labels = labels.size
# intersect y_pred, y_true with labels, eliminate items not in labels
ind = cp.logical_and(y_pred < n_labels, y_true < n_labels)
y_pred = y_pred[ind]
y_true = y_true[ind]
sample_weight = sample_weight[ind]
cm = cupyx.scipy.sparse.coo_matrix((sample_weight, (y_true, y_pred)),
shape=(n_labels, n_labels),
dtype=cp.float64).toarray()
return cp.nan_to_num(cm)
def _partial_fit(self,
X,
y,
sample_weight=None,
_classes=None) -> "MultinomialNB":
if has_scipy():
from scipy.sparse import isspmatrix as scipy_sparse_isspmatrix
else:
from cuml.common.import_utils import dummy_function_always_false \
as scipy_sparse_isspmatrix
# todo: use a sparse CumlArray style approach when ready
# https://github.com/rapidsai/cuml/issues/2216
if scipy_sparse_isspmatrix(X) or cupyx.scipy.sparse.isspmatrix(X):
X = X.tocoo()
rows = cp.asarray(X.row, dtype=X.row.dtype)
cols = cp.asarray(X.col, dtype=X.col.dtype)
data = cp.asarray(X.data, dtype=X.data.dtype)
X = cupyx.scipy.sparse.coo_matrix((data, (rows, cols)),
shape=X.shape)
else:
X = input_to_cupy_array(X, order='K').array
y = input_to_cupy_array(y).array
Y, label_classes = make_monotonic(y, copy=True)
if not self.fit_called_:
self.fit_called_ = True
if _classes is not None:
_classes, *_ = input_to_cuml_array(_classes, order='K')
check_labels(Y, _classes)
self.classes_ = _classes
else:
self.classes_ = label_classes
self._n_classes_ = self.classes_.shape[0]
self._n_features_ = X.shape[1]
self._init_counters(self._n_classes_, self._n_features_, X.dtype)
else:
check_labels(Y, self.classes_)
self._count(X, Y)
self._update_feature_log_prob(self.alpha)
self._update_class_log_prior(class_prior=self._class_prior_)
return self
def label_binarize(y,
classes,
neg_label=0,
pos_label=1,
sparse_output=False) -> SparseCumlArray:
"""
A stateless helper function to dummy encode multi-class labels.
Parameters
----------
y : array-like of size [n_samples,] or [n_samples, n_classes]
classes : the set of unique classes in the input
neg_label : integer the negative value for transformed output
pos_label : integer the positive value for transformed output
sparse_output : bool whether to return sparse array
"""
classes = cp.asarray(classes, dtype=classes.dtype)
labels = cp.asarray(y, dtype=y.dtype)
if not check_labels(labels, classes):
raise ValueError("Unseen classes encountered in input")
row_ind = cp.arange(0, labels.shape[0], 1, dtype=y.dtype)
col_ind, _ = make_monotonic(labels, classes, copy=True)
# Convert from CumlArray to cupy
col_ind = cp.asarray(col_ind)
val = cp.full(row_ind.shape[0], pos_label, dtype=y.dtype)
sp = cupyx.scipy.sparse.coo_matrix(
(val, (row_ind, col_ind)),
shape=(col_ind.shape[0], classes.shape[0]),
dtype=cp.float32)
cp.cuda.Stream.null.synchronize()
if sparse_output:
sp = sp.tocsr()
return sp
else:
arr = sp.toarray().astype(y.dtype)
arr[arr == 0] = neg_label
return arr
def _partial_fit(self, X, y, sample_weight=None, _classes=None):
if isinstance(X, np.ndarray) or isinstance(X, cp.ndarray):
X = cp.asarray(X, X.dtype)
elif scipy.sparse.isspmatrix(X) or cp.sparse.isspmatrix(X):
X = X.tocoo()
rows = cp.asarray(X.row, dtype=X.row.dtype)
cols = cp.asarray(X.col, dtype=X.col.dtype)
data = cp.asarray(X.data, dtype=X.data.dtype)
X = cp.sparse.coo_matrix((data, (rows, cols)), shape=X.shape)
if isinstance(y, np.ndarray) or isinstance(y, cp.ndarray):
y = cp.asarray(y, y.dtype)
Y, label_classes = make_monotonic(y, copy=True)
if not self.fit_called_:
self.fit_called_ = True
if _classes is not None:
check_labels(Y, _classes)
self.classes_ = _classes
else:
self.classes_ = label_classes
self.n_classes_ = self.classes_.shape[0]
self.n_features_ = X.shape[1]
self._init_counters(self.n_classes_, self.n_features_, X.dtype)
else:
check_labels(Y, self.classes_)
self._count(X, Y)
self._update_feature_log_prob(self.alpha)
self._update_class_log_prior(class_prior=self.class_prior)
return self
def confusion_matrix(y_true,
y_pred,
labels=None,
sample_weight=None,
normalize=None) -> CumlArray:
"""Compute confusion matrix to evaluate the accuracy of a classification.
Parameters
----------
y_true : array-like (device or host) shape = (n_samples,)
or (n_samples, n_outputs)
Ground truth (correct) target values.
y_pred : array-like (device or host) shape = (n_samples,)
or (n_samples, n_outputs)
Estimated target values.
labels : array-like (device or host) shape = (n_classes,), optional
List of labels to index the matrix. This may be used to reorder or
select a subset of labels. If None is given, those that appear at least
once in y_true or y_pred are used in sorted order.
sample_weight : array-like (device or host) shape = (n_samples,), optional
Sample weights.
normalize : string in [‘true’, ‘pred’, ‘all’]
Normalizes confusion matrix over the true (rows), predicted (columns)
conditions or all the population. If None, confusion matrix will not be
normalized.
Returns
-------
C : array-like (device or host) shape = (n_classes, n_classes)
Confusion matrix.
"""
y_true, n_rows, n_cols, dtype = \
input_to_cuml_array(y_true, check_dtype=[cp.int32, cp.int64])
y_pred, _, _, _ = \
input_to_cuml_array(y_pred, check_dtype=dtype,
check_rows=n_rows, check_cols=n_cols)
if labels is None:
labels = sorted_unique_labels(y_true, y_pred)
n_labels = len(labels)
else:
labels, n_labels, _, _ = \
input_to_cupy_array(labels, check_dtype=dtype, check_cols=1)
if sample_weight is None:
sample_weight = cp.ones(n_rows, dtype=dtype)
else:
sample_weight, _, _, _ = \
input_to_cupy_array(sample_weight,
check_dtype=[cp.float32, cp.float64,
cp.int32, cp.int64],
check_rows=n_rows, check_cols=n_cols)
if normalize not in ['true', 'pred', 'all', None]:
msg = "normalize must be one of " \
f"{{'true', 'pred', 'all', None}}, got {normalize}."
raise ValueError(msg)
with using_output_type("cupy"):
y_true, _ = make_monotonic(y_true, labels, copy=True)
y_pred, _ = make_monotonic(y_pred, labels, copy=True)
# intersect y_pred, y_true with labels, eliminate items not in labels
ind = cp.logical_and(y_pred < n_labels, y_true < n_labels)
y_pred = y_pred[ind]
y_true = y_true[ind]
sample_weight = sample_weight[ind]
cm = cupyx.scipy.sparse.coo_matrix((sample_weight, (y_true, y_pred)),
shape=(n_labels, n_labels),
dtype=np.float64).toarray()
# Choose the accumulator dtype to always have high precision
if sample_weight.dtype.kind in {'i', 'u', 'b'}:
cm = cm.astype(np.int64)
with np.errstate(all='ignore'):
if normalize == 'true':
cm = cp.divide(cm, cm.sum(axis=1, keepdims=True))
elif normalize == 'pred':
cm = cp.divide(cm, cm.sum(axis=0, keepdims=True))
elif normalize == 'all':
cm = cp.divide(cm, cm.sum())
cm = cp.nan_to_num(cm)
return cm
def _partial_fit(self,
X,
y,
sample_weight=None,
_classes=None,
convert_dtype=True) -> "MultinomialNB":
if has_scipy():
from scipy.sparse import isspmatrix as scipy_sparse_isspmatrix
else:
from cuml.common.import_utils import dummy_function_always_false \
as scipy_sparse_isspmatrix
# todo: use a sparse CumlArray style approach when ready
# https://github.com/rapidsai/cuml/issues/2216
if scipy_sparse_isspmatrix(X) or cupyx.scipy.sparse.isspmatrix(X):
X = _convert_x_sparse(X)
# TODO: Expanded this since sparse kernel doesn't
# actually require the scipy sparse container format.
else:
X = input_to_cupy_array(
X, order='K', check_dtype=[cp.float32, cp.float64,
cp.int32]).array
expected_y_dtype = cp.int32 if X.dtype in [cp.float32, cp.int32
] else cp.int64
y = input_to_cupy_array(
y,
convert_to_dtype=(expected_y_dtype if convert_dtype else False),
check_dtype=expected_y_dtype).array
Y, label_classes = make_monotonic(y, copy=True)
if not self.fit_called_:
self.fit_called_ = True
if _classes is not None:
_classes, *_ = input_to_cuml_array(
_classes,
order='K',
convert_to_dtype=(expected_y_dtype
if convert_dtype else False))
check_labels(Y, _classes)
self.classes_ = _classes
else:
self.classes_ = label_classes
self._n_classes_ = self.classes_.shape[0]
self._n_features_ = X.shape[1]
self._init_counters(self._n_classes_, self._n_features_, X.dtype)
else:
check_labels(Y, self.classes_)
if cp.sparse.isspmatrix(X):
self._count_sparse(X.row, X.col, X.data, X.shape, Y)
else:
self._count(X, Y)
self._update_feature_log_prob(self.alpha)
self._update_class_log_prior(class_prior=self._class_prior_)
return self
