Skip to content

Navigation Menu

Sign in
Sign up

fix(compose): support object dtype in ColumnTransformer + SimpleImputer on cuDF #8317

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
nethum529 wants to merge 2 commits into NVIDIA:main
base: main
Choose a base branch
Loading
from nethum529:fix/issue-6183-columntransformer-object-dtype
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
View file Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@
import cuml
from cuml.internals.global_settings import _global_settings_data
from cuml.internals.mixins import DeprecatedGetFeatureNamesMixin
from cuml.internals.outputs import _is_object_dtype
from cuml.internals.validation import (
check_is_fitted,
check_features,
Expand Down Expand Up @@ -300,7 +301,8 @@ def _list_indexing(X, key, key_dtype):


def _transform_one(transformer, X, y, weight, **fit_params):
with cuml.using_output_type("cupy"):
output_type = "numpy" if _is_object_dtype(X) else "cupy"
with cuml.using_output_type(output_type):
res = transformer.transform(X)

# if we have a weight for this transformer, multiply output
Expand All @@ -322,7 +324,8 @@ def _fit_transform_one(transformer,
be multiplied by ``weight``.
"""
with _print_elapsed_time(message_clsname, message):
with cuml.using_output_type("cupy"):
output_type = "numpy" if _is_object_dtype(X) else "cupy"
with cuml.using_output_type(output_type):
transformer.accept_sparse = True
if hasattr(transformer, 'fit_transform'):
res = transformer.fit_transform(X, y, **fit_params)
Expand Down Expand Up @@ -1014,6 +1017,12 @@ def _hstack(self, Xs):
return cu_sparse.hstack(converted_Xs).tocsr()
else:
Xs = [f.toarray() if issparse(f) else f for f in Xs]
if any(_is_object_dtype(X) for X in Xs):
# Object dtype (e.g. string columns from a categorical
# SimpleImputer) has no device representation - cupy has no
# way to store it. Stack on host instead.
Xs = [X.get() if isinstance(X, np.ndarray) else X for X in Xs]
return cpu_np.hstack(Xs)
return np.hstack(Xs)


Expand Down
80 changes: 61 additions & 19 deletions python/cuml/cuml/_thirdparty/sklearn/preprocessing/_imputation.py
View file Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@

import cupy as np
import numpy as cpu_np
import pandas as pd
from cupyx.scipy import sparse

import cuml
Expand All @@ -29,11 +30,11 @@
StringInputTagMixin,
_ensure_transformer_tags,
)
from cuml.internals.outputs import mlfunc, ReflectedAttr
from cuml.internals.outputs import ReflectedAttr, _is_object_dtype, mlfunc
from cuml.internals.validation import (
check_is_fitted,
check_inputs,
check_input_features,
check_inputs,
check_is_fitted,
)

from ....thirdparty_adapters import (
Expand Down Expand Up @@ -144,15 +145,24 @@ def _concatenate_indicator(self, X_imputed, X_indicator):
if not self.add_indicator:
return X_imputed

hstack = sparse.hstack if sparse.issparse(X_imputed) else np.hstack
if X_indicator is None:
raise ValueError(
"Data from the missing indicator are not provided. Call "
"_fit_indicator and _transform_indicator in the imputer "
"implementation."
)

return hstack((X_imputed, X_indicator))
if sparse.issparse(X_imputed):
return sparse.hstack((X_imputed, X_indicator))

if _is_object_dtype(X_imputed) or _is_object_dtype(X_indicator):
arrays = [
array.get() if isinstance(array, np.ndarray) else array
for array in (X_imputed, X_indicator)
]
return cpu_np.hstack(arrays)

return np.hstack((X_imputed, X_indicator))

def __sklearn_tags__(self):
tags = super().__sklearn_tags__()
Expand Down Expand Up @@ -264,10 +274,12 @@ def __init__(self, *, missing_values=np.nan, strategy="mean",
@classmethod
def _get_param_names(cls):
return super()._get_param_names() + [
"missing_values",
"strategy",
"fill_value",
"verbose",
"copy"
"copy",
"add_indicator",

@viclafargue viclafargue Jul 6, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

add_indicator=True still goes through the dense _concatenate_indicator path, which unconditionally uses cupy.hstack because np is CuPy in this file. For object-dtype imputed data, that sends the host object array back to CuPy and reproduces the same failure this PR is trying to avoid.

@nethum529 nethum529 Jul 18, 2026

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Fixed. _concatenate_indicator now detects object-dtype imputed or indicator data and stacks on host with numpy.hstack (moving any cupy operands to host via .get()), instead of routing the host object array through cupy.hstack. The sparse path and the numeric device hstack fast path are unchanged. Added a regression test with add_indicator=True on string columns comparing cuML against scikit-learn.

]

def _validate_input(self, X, in_fit):
Expand All @@ -288,13 +300,15 @@ def _validate_input(self, X, in_fit):
ensure_all_finite = "allow-nan"

try:
mem_type = "host" if _is_object_dtype(X) else "device"
X = check_inputs(
self,
X,
accept_sparse="csc",
dtype=dtype,
ensure_all_finite=ensure_all_finite,
copy=self.copy,
mem_type=mem_type,
reset=in_fit,
)
except ValueError as ve:
Expand All @@ -305,6 +319,18 @@ def _validate_input(self, X, in_fit):
else:
raise ve

# Object nulls reach this host path as NaN. Restore pd.NA for its
# identity-based path, but reject NaN when None was requested,
# matching scikit-learn's validation semantics.
if _is_object_dtype(X):
if hasattr(X, "flags") and not X.flags.writeable:
X = X.copy()
nan_mask = _get_mask(X, np.nan)
if self.missing_values is pd.NA:
X[nan_mask] = pd.NA
elif self.missing_values is None and nan_mask.any():
raise ValueError("Input contains NaN")

_check_inputs_dtype(X, self.missing_values)
if X.dtype.kind not in ("i", "u", "f", "O"):
raise ValueError("SimpleImputer does not support data with dtype "
Expand Down Expand Up @@ -427,7 +453,8 @@ def _dense_fit(self, X, strategy, missing_values, fill_value):

# Constant
elif strategy == "constant":
return np.full(X.shape[1], fill_value, dtype=X.dtype)
xp = np.get_array_module(X)
return xp.full(X.shape[1], fill_value, dtype=X.dtype)

@mlfunc
def transform(self, X):
Expand All @@ -443,24 +470,27 @@ def transform(self, X):
X = self._validate_input(X, in_fit=False)
X_indicator = super()._transform_indicator(X)

statistics = self.statistics_
# Use the stored value for internal computation. ColumnTransformer
# may request cupy output, which cannot reflect object statistics.
statistics = type(self).statistics_.get_raw(self)

if X.shape[1] != statistics.shape[0]:
raise ValueError("X has %d features per sample, expected %d"
% (X.shape[1], self.statistics_.shape[0]))
% (X.shape[1], statistics.shape[0]))

# Delete the invalid columns if strategy is not constant
if self.strategy == "constant":
valid_statistics = statistics
else:
xp = np.get_array_module(statistics)
# same as np.isnan but also works for object dtypes
invalid_mask = _get_mask(statistics, np.nan)
valid_mask = np.logical_not(invalid_mask)
valid_mask = xp.logical_not(invalid_mask)
valid_statistics = statistics[valid_mask]
valid_statistics_indexes = np.flatnonzero(valid_mask)
valid_statistics_indexes = xp.flatnonzero(valid_mask)

if invalid_mask.any():
missing = np.arange(X.shape[1])[invalid_mask]
missing = xp.arange(X.shape[1])[invalid_mask]
if self.verbose:
warnings.warn("Deleting features without "
"observed values: %s" % missing)
Expand All @@ -485,9 +515,10 @@ def transform(self, X):
if self.strategy == "constant":
X[mask] = valid_statistics[0]
else:
for i, vi in enumerate(valid_statistics_indexes):
feature_idxs = np.flatnonzero(mask[:, vi])
X[feature_idxs, vi] = valid_statistics[i]
xp = np.get_array_module(mask)
for i in range(valid_statistics.shape[0]):
feature_idxs = xp.flatnonzero(mask[:, i])
X[feature_idxs, i] = valid_statistics[i]

X = super()._concatenate_indicator(X, X_indicator)
return X
Expand All @@ -508,7 +539,11 @@ def get_feature_names_out(self, input_features=None):
"""
check_is_fitted(self)
input_features = check_input_features(self, input_features)
non_missing_mask = np.logical_not(_get_mask(self.statistics_, np.nan)).get()
statistics = type(self).statistics_.get_raw(self)
xp = np.get_array_module(statistics)
non_missing_mask = xp.logical_not(_get_mask(statistics, np.nan))
if isinstance(non_missing_mask, np.ndarray):
non_missing_mask = non_missing_mask.get()
names = input_features[non_missing_mask]
if self.add_indicator:
indicator_names = self.indicator_.get_feature_names_out(input_features)
Expand Down Expand Up @@ -657,9 +692,11 @@ def _get_missing_features_info(self, X):
imputer_mask = sparse.csc_matrix(imputer_mask)

if self.features == 'all':
features_indices = np.arange(X.shape[1])
xp = np.get_array_module(imputer_mask)
features_indices = xp.arange(X.shape[1])
else:
features_indices = np.flatnonzero(n_missing)
xp = np.get_array_module(n_missing)
features_indices = xp.flatnonzero(n_missing)

return imputer_mask, features_indices

Expand All @@ -668,11 +705,13 @@ def _validate_input(self, X, in_fit):
ensure_all_finite = True
else:
ensure_all_finite = "allow-nan"
mem_type = "host" if _is_object_dtype(X) else "device"
X = check_inputs(
self,
X,
accept_sparse=('csc', 'csr'),
ensure_all_finite=ensure_all_finite,
mem_type=mem_type,
reset=in_fit,
)
_check_inputs_dtype(X, self.missing_values)
Expand Down Expand Up @@ -802,10 +841,13 @@ def get_feature_names_out(self, input_features=None):
check_is_fitted(self)
input_features = check_input_features(self, input_features)
prefix = self.__class__.__name__.lower()
features = type(self).features_.get_raw(self)
if isinstance(features, np.ndarray):
features = features.get()
return cpu_np.asarray(
[
f"{prefix}_{feature_name}"
for feature_name in input_features[self.features_.get()]
for feature_name in input_features[features]
],
dtype=object,
)
Expand Down
69 changes: 69 additions & 0 deletions python/cuml/cuml/internals/outputs.py
View file Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -284,6 +284,31 @@ def infer_output_type(array, array_like="numpy"):
return None


def _is_object_dtype(res):
"""Check for object or string dtype on an array/dataframe-like."""

def is_object_or_string(dtype):
try:
if np.dtype(dtype).kind == "O":
return True
except TypeError:
pass
return pd.api.types.is_string_dtype(dtype)

dtype = getattr(res, "dtype", None)
if dtype is not None:
return is_object_or_string(dtype)

dtypes = getattr(res, "dtypes", None)
if dtypes is not None:
try:
return any(is_object_or_string(dt) for dt in dtypes)
except TypeError:
return False

return False


class ArrayIndexPair:
"""An array paired with an aligned index.

Expand Down Expand Up @@ -521,6 +546,40 @@ def convert_arrays(
return pd.Series(obj.flatten(), index=index)
return pd.DataFrame(obj, index=index)
return pd.Series(obj, index=index)
elif _is_object_dtype(obj):
# NumPy object arrays have no device representation. Preserve
# host arrays for internal outputs, or wrap them in a
# dataframe-like type.
if output_type == "cuml":
return obj
elif output_type == "cupy":
raise TypeError(
f"{output_type=!r} doesn't support outputs of dtype "
f"object and shape {obj.shape}"
)

if hasattr(index, "to_pandas"):
index = index.to_pandas()

if obj.ndim == 2:
if one_col_2d_as_series and obj.shape[1] == 1:
host_df = pd.Series(
obj.flatten(), index=index
).infer_objects()
else:
host_df = pd.DataFrame(obj, index=index).infer_objects()
else:
host_df = pd.Series(obj, index=index).infer_objects()

try:
return cudf.from_pandas(host_df)
except (TypeError, ValueError, NotImplementedError) as exc:
raise TypeError(
"Cannot convert an object-dtype output with shape "
f"{obj.shape} to output_type='cudf'. Use "
"output_type='pandas' or output_type='numpy' for this "
"object layout."
) from exc
else:
# Other output types use device memory, coerce to cupy and take
# cupy code path.
Expand Down Expand Up @@ -639,6 +698,16 @@ def __reduce__(self):
def __set_name__(self, owner, name):
self.name = name

def get_raw(self, instance):
"""Return the value so internal work can dispatch on its stored type."""
cache = instance.__dict__.get(self.name)
if cache is None:
raise AttributeError(
f"{type(instance).__name__!r} object has no attribute "
f"{self.name!r}"
)
return cache.value

def __get__(self, instance, owner):
if instance is None:
return self
Expand Down
Loading
Loading

AltStyle によって変換されたページ (->オリジナル) /