AutoTabPFN giving an error: 'dict' object has no attribute 'name'

[RonghongJi]

Describe the bug

from sklearn.datasets import load_breast_cancer
from sklearn.metrics import accuracy_score, roc_auc_score
from sklearn.model_selection import train_test_split

from tabpfn_extensions.post_hoc_ensembles.sklearn_interface import AutoTabPFNClassifier

X, y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=42)
clf = AutoTabPFNClassifier() # 120 seconds tuning time
clf.fit(X_train, y_train)
predictions = clf.predict(X_test)

This paper and its corresponding model truly represent a remarkable leap forward in handling small tabular data.
I had a problem using it. Why do I get the following error when I run the sample code after installing the AutoTabPFNClassifier according to the instructions? I would really appreciate it if you could help me take a look at this.

---

AttributeError Traceback (most recent call last)
Cell In[3], line 10
8 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=42)
9 clf = AutoTabPFNClassifier() # 120 seconds tuning time
---> 10 clf.fit(X_train, y_train)
11 predictions = clf.predict(X_test)

File ~/tabpfn-extensions/src/tabpfn_extensions/post_hoc_ensembles/sklearn_interface.py:112, in AutoTabPFNClassifier.fit(self, X, y, categorical_feature_indices)
97 task_type = (
98 TaskType.MULTICLASS if len(unique_labels(y)) > 2 else TaskType.BINARY
99 )
100 self.predictor_ = AutoPostHocEnsemblePredictor(
101 preset=self.preset,
102 task_type=task_type,
(...)
109 **self.phe_init_args_,
110 )
--> 112 self.predictor_.fit(
113 X,
114 y,
115 categorical_feature_indices=self.categorical_feature_indices,
116 )
118 # -- Sklearn required values
119 self.classes_ = self.predictor_.label_encoder.classes

File ~/tabpfn-extensions/src/tabpfn_extensions/post_hoc_ensembles/pfn_phe.py:333, in AutoPostHocEnsemblePredictor.fit(self, X, y, categorical_feature_indices)
316 self._estimators, model_family_per_estimator = self._collect_base_models(
317 categorical_feature_indices=categorical_feature_indices,
318 )
320 self._ens_model = self._ens_model(
321 estimators=self._estimators,
322 seed=self.ges_random_state,
(...)
330 model_family_per_estimator=model_family_per_estimator,
331 )
--> 333 self._ens_model.fit(X, y)
335 return self

File ~/tabpfn-extensions/src/tabpfn_extensions/post_hoc_ensembles/greedy_weighted_ensemble.py:234, in GreedyWeightedEnsemble.fit(self, X, y)
233 def fit(self, X, y):
--> 234 weights = self.get_weights(X, y)
236 final_weights = []
237 base_models = []

File ~/tabpfn-extensions/src/tabpfn_extensions/post_hoc_ensembles/greedy_weighted_ensemble.py:173, in GreedyWeightedEnsemble.get_weights(self, X, y)
172 def get_weights(self, X, y):
--> 173 oof_proba = self.get_oof_per_estimator(X, y)
174 self.model_family_per_estimator = (
175 self.model_family_per_estimator
176 if self.model_family_per_estimator is not None
177 else ["X"] * len(self._estimators)
178 )
179 self._model_family_per_estimator = self.model_family_per_estimator[
180 : len(self._estimators)
181 ]

File ~/tabpfn-extensions/src/tabpfn_extensions/post_hoc_ensembles/abstract_validation_utils.py:372, in AbstractValidationUtils.get_oof_per_estimator(self, X, y, return_loss_per_estimator, impute_dropped_instances, _extra_processing)
369 to_pass_holdout_index_hits = holdout_index_hits
370 holdout_index_hit_counts = current_repeat
--> 372 self._fill_predictions_in_place(
373 model_i=model_i,
374 base_model=base_model,
375 oof_proba_list=oof_proba_list,
376 X=X,
377 y=y,
378 train_index=train_index,
379 test_index=test_index,
380 loss_per_estimator=loss_per_estimator,
381 holdout_index_hits=to_pass_holdout_index_hits,
382 split_i=split_i,
383 _extra_processing=_extra_processing,
384 )
386 if check_for_repeat_early_stopping: # True after every repeat.
387 ran_repeats = current_repeat

File ~/tabpfn-extensions/src/tabpfn_extensions/post_hoc_ensembles/abstract_validation_utils.py:127, in AbstractValidationUtils._fill_predictions_in_place(self, model_i, base_model, oof_proba_list, X, y, train_index, test_index, loss_per_estimator, holdout_index_hits, _extra_processing, split_i)
123 fold_y_train, fold_y_test = y[train_index], y[test_index]
124 # base_model = copy.deepcopy(base_model) # FIXME: think about adding this for safety but will likely slow down (due to having to load model again)
125
126 # Default base models case
--> 127 base_model.fit(fold_X_train, fold_y_train)
129 pred = self._predict_oof(base_model, fold_X_test)
131 oof_proba_list[model_i][test_index] += pred

File /opt/anaconda3/envs/tabpfn/lib/python3.13/site-packages/tabpfn/classifier.py:485, in TabPFNClassifier.fit(self, X, y)
482 assert len(ensemble_configs) == self.n_estimators
484 # Create the inference engine
--> 485 self.executor_ = create_inference_engine(
486 X_train=X,
487 y_train=y,
488 model=self.model_,
489 ensemble_configs=ensemble_configs,
490 cat_ix=self.inferred_categorical_indices_,
491 fit_mode=self.fit_mode,
492 device_=self.device_,
493 rng=rng,
494 n_jobs=self.n_jobs,
495 byte_size=byte_size,
496 forced_inference_dtype_=self.forced_inference_dtype_,
497 memory_saving_mode=self.memory_saving_mode,
498 use_autocast_=self.use_autocast_,
499 )
501 return self

File /opt/anaconda3/envs/tabpfn/lib/python3.13/site-packages/tabpfn/base.py:213, in create_inference_engine(X_train, y_train, model, ensemble_configs, cat_ix, fit_mode, device_, rng, n_jobs, byte_size, forced_inference_dtype_, memory_saving_mode, use_autocast_)
200 engine = InferenceEngineOnDemand.prepare(
201 X_train=X_train,
202 y_train=y_train,
(...)
210 save_peak_mem=memory_saving_mode,
211 )
212 elif fit_mode == "fit_preprocessors":
--> 213 engine = InferenceEngineCachePreprocessing.prepare(
214 X_train=X_train,
215 y_train=y_train,
216 cat_ix=cat_ix,
217 ensemble_configs=ensemble_configs,
218 n_workers=n_jobs,
219 model=model,
220 rng=rng,
221 dtype_byte_size=byte_size,
222 force_inference_dtype=forced_inference_dtype_,
223 save_peak_mem=memory_saving_mode,
224 )
225 elif fit_mode == "fit_with_cache":
226 engine = InferenceEngineCacheKV.prepare(
227 X_train=X_train,
228 y_train=y_train,
(...)
238 autocast=use_autocast_,
239 )

File /opt/anaconda3/envs/tabpfn/lib/python3.13/site-packages/tabpfn/inference.py:265, in InferenceEngineCachePreprocessing.prepare(cls, X_train, y_train, cat_ix, model, ensemble_configs, n_workers, rng, dtype_byte_size, force_inference_dtype, save_peak_mem)
239 """Prepare the inference engine.
240
241 Args:
(...)
254 The prepared inference engine.
255 """
256 itr = fit_preprocessing(
257 configs=ensemble_configs,
258 X_train=X_train,
(...)
263 parallel_mode="block",
264 )
--> 265 configs, preprocessors, X_trains, y_trains, cat_ixs = list(zip(*itr))
266 return InferenceEngineCachePreprocessing(
267 X_trains=X_trains,
268 y_trains=y_trains,
(...)
275 save_peak_mem=save_peak_mem,
276 )

File /opt/anaconda3/envs/tabpfn/lib/python3.13/site-packages/tabpfn/preprocessing.py:625, in fit_preprocessing(configs, X_train, y_train, random_state, cat_ix, n_workers, parallel_mode)
622 worker_func = joblib.delayed(func)
624 seeds = rng.integers(0, np.iinfo(np.int32).max, len(configs))
--> 625 yield from executor( # type: ignore
626 [
627 worker_func(config, X_train, y_train, seed)
628 for config, seed in zip(configs, seeds)
629 ],
630 )

File /opt/anaconda3/envs/tabpfn/lib/python3.13/site-packages/joblib/parallel.py:1918, in Parallel.call(self, iterable)
1916 output = self._get_sequential_output(iterable)
1917 next(output)
-> 1918 return output if self.return_generator else list(output)
1920 # Let's create an ID that uniquely identifies the current call. If the
1921 # call is interrupted early and that the same instance is immediately
1922 # re-used, this id will be used to prevent workers that were
1923 # concurrently finalizing a task from the previous call to run the
1924 # callback.
1925 with self._lock:

File /opt/anaconda3/envs/tabpfn/lib/python3.13/site-packages/joblib/parallel.py:1847, in Parallel._get_sequential_output(self, iterable)
1845 self.n_dispatched_batches += 1
1846 self.n_dispatched_tasks += 1
-> 1847 res = func(*args, **kwargs)
1848 self.n_completed_tasks += 1
1849 self.print_progress()

File /opt/anaconda3/envs/tabpfn/lib/python3.13/site-packages/tabpfn/preprocessing.py:537, in fit_preprocessing_one(config, X_train, y_train, random_state, cat_ix)
534 X_train = X_train.copy()
535 y_train = y_train.copy()
--> 537 preprocessor = config.to_pipeline(random_state=static_seed)
538 res = preprocessor.fit_transform(X_train, cat_ix)
540 # TODO(eddiebergman): Not a fan of this, wish it was more transparent, but we want
541 # to distuinguish what to do with the ys based on the ensemble config type

File /opt/anaconda3/envs/tabpfn/lib/python3.13/site-packages/tabpfn/preprocessing.py:452, in EnsembleConfig.to_pipeline(self, random_state)
440 if use_poly_features:
441 steps.append(
442 NanHandlingPolynomialFeaturesStep(
443 max_features=max_poly_features,
444 random_state=random_state,
445 ),
446 )
448 steps.extend(
449 [
450 RemoveConstantFeaturesStep(),
451 ReshapeFeatureDistributionsStep(
--> 452 transform_name=self.preprocess_config.name,
453 append_to_original=self.preprocess_config.append_original,
454 subsample_features=self.preprocess_config.subsample_features,
455 global_transformer_name=self.preprocess_config.global_transformer_name,
456 apply_to_categorical=(
457 self.preprocess_config.categorical_name == "numeric"
458 ),
459 random_state=random_state,
460 ),
461 EncodeCategoricalFeaturesStep(
462 self.preprocess_config.categorical_name,
463 random_state=random_state,
464 ),
465 ],
466 )
468 if self.add_fingerprint_feature:
469 steps.append(AddFingerprintFeaturesStep(random_state=random_state))

AttributeError: 'dict' object has no attribute 'name'

Steps/Code to Reproduce

No response

Expected Results

No response

Actual Results

No response

Versions

[noahho]

Thanks a lot for your kind words. I believe this is due to an outdated tabpfn version. Please check the newest version is installed: "pip install tabpfn --upgrade"

[lincj1994]

Thanks a lot for your kind words. I believe this is due to an outdated tabpfn version. Please check the newest version is installed: "pip install tabpfn --upgrade"

Hello, same issue persists even after upgrading TabPFN via pip install tabpfn --upgrade. Could you please provide further guidance?

[RonghongJi]

Thanks a lot for your kind words. I believe this is due to an outdated tabpfn version. Please check the newest version is installed: "pip install tabpfn --upgrade"

Hello, same issue persists even after upgrading TabPFN via pip install tabpfn --upgrade. Could you please provide further guidance?

I didn't solve the problem this way either, maybe it wasn't a version problem.

[mert-kurttutan]

@RonghongJi Can you show your result from running pip list ?

[RonghongJi]

@RonghongJi Can you show your result from running pip list ?

(tabpfn) rhji@RonadeMacBook-Pro ~ % pip list
Package Version Editable project location

---

appnope 0.1.3
asttokens 2.0.5
Bottleneck 1.4.2
certifi 2025.1.31
charset-normalizer 3.4.1
cloudpickle 3.1.1
colour 0.1.5
comm 0.2.1
contourpy 1.3.1
cycler 0.12.1
debugpy 1.8.11
decorator 5.1.1
einops 0.8.1
et_xmlfile 1.1.0
executing 0.8.3
filelock 3.17.0
fonttools 4.56.0
fsspec 2025.2.0
future 1.0.0
huggingface-hub 0.29.1
hyperopt 0.2.7
idna 3.10
ipykernel 6.29.5
ipython 8.30.0
jedi 0.19.2
Jinja2 3.1.5
joblib 1.4.2
jupyter_client 8.6.3
jupyter_core 5.7.2
kditransform 0.2.0
kiwisolver 1.4.8
llvmlite 0.44.0
MarkupSafe 3.0.2
matplotlib 3.10.0
matplotlib-inline 0.1.6
mpmath 1.3.0
nest_asyncio 1.6.0
networkx 3.4.2
numba 0.61.0
numexpr 2.10.1
numpy 2.1.3
openpyxl 3.1.5
packaging 24.2
pandas 2.2.3
parso 0.8.4
pexpect 4.8.0
pillow 11.1.0
pip 25.0
platformdirs 3.10.0
prompt_toolkit 3.0.43
psutil 5.9.0
ptyprocess 0.7.0
pure-eval 0.2.2
py4j 0.10.9.9
Pygments 2.15.1
pyparsing 3.2.1
python-dateutil 2.9.0.post0
pytz 2024.1
PyYAML 6.0.2
pyzmq 26.2.0
requests 2.32.3
scikit-learn 1.6.1
scipy 1.15.2
seaborn 0.12.2
setuptools 72.1.0
shap 0.46.0
shapiq 1.2.1
six 1.16.0
slicer 0.0.8
stack-data 0.2.0
sympy 1.13.1
tabpfn 2.0.1
tabpfn-extensions 0.0.4 /Users/rhji/tabpfn-extensions
threadpoolctl 3.5.0
torch 2.6.0
tornado 6.4.2
tqdm 4.67.1
traitlets 5.14.3
typing_extensions 4.12.2
tzdata 2023.3
urllib3 2.3.0
wcwidth 0.2.5
wheel 0.45.1

[mert-kurttutan]

@RonghongJi Indeed, something in your environment setting is preventing you from updating[1] to the lastest version, which is 2.0.6

I suggest you run the following:

pip install tabpfn==2.0.6

see if it runs successfully.

1: This might be because of version settings in requirements.txt or pyproject.toml file you have in your local setting.