Evalml: Dataset Titanic dengan kolom teks gagal dalam ensembling

Dibuat pada 20 Mei 2021 · 5Komentar · Sumber: alteryx/evalml

Reproduksi:

import pandas as pd
import woodwork as ww
data_set = pd.read_csv("titanic_alan.csv")
y = data_set['Survived']
X = data_set.drop(['Survived',], axis=1)
automl = AutoMLSearch(X, y, problem_type="binary", error_callback=raise_error_callback, max_batches=10, ensembling=True)
automl.search()

Kesalahan dengan:


---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-9-7e028fe6ad03> in <module>
      1 automl = AutoMLSearch(X, y, problem_type="binary", error_callback=raise_error_callback, max_batches=10, ensembling=True)
----> 2 automl.search()

~/Desktop/evalml/evalml/automl/automl_search.py in search(self, show_iteration_plot)
    598                     computation = computations[current_computation_index]
    599                     if computation.done():
--> 600                         evaluation = computation.get_result()
    601                         data, pipeline, job_log = evaluation.get('scores'), evaluation.get("pipeline"), evaluation.get("logger")
    602                         pipeline_id = self._post_evaluation_callback(pipeline, data, job_log)

~/Desktop/evalml/evalml/automl/engine/sequential_engine.py in get_result(self)
     33         Raises Exception: If computation fails. Returns traceback.
     34         """
---> 35         return self.work(**self.kwargs)
     36 
     37     def cancel(self):

~/Desktop/evalml/evalml/automl/engine/engine_base.py in evaluate_pipeline(pipeline, automl_config, X, y, logger)
    216     return train_and_score_pipeline(pipeline, automl_config=automl_config,
    217                                     full_X_train=X, full_y_train=y,
--> 218                                     logger=logger)
    219 
    220 

~/Desktop/evalml/evalml/automl/engine/engine_base.py in train_and_score_pipeline(pipeline, automl_config, full_X_train, full_y_train, logger)
    171             if automl_config.error_callback is not None:
    172                 automl_config.error_callback(exception=e, traceback=traceback.format_tb(sys.exc_info()[2]), automl=automl_config,
--> 173                                              fold_num=i, pipeline=pipeline)
    174             if isinstance(e, PipelineScoreError):
    175                 nan_scores = {objective: np.nan for objective in e.exceptions}

~/Desktop/evalml/evalml/automl/callbacks.py in raise_error_callback(exception, traceback, automl, **kwargs)
     13     logger.error(f'AutoML search raised a fatal exception: {str(exception)}')
     14     logger.error("\n".join(traceback))
---> 15     raise exception
     16 
     17 

~/Desktop/evalml/evalml/automl/engine/engine_base.py in train_and_score_pipeline(pipeline, automl_config, full_X_train, full_y_train, logger)
    160         try:
    161             logger.debug(f"\t\t\tFold {i}: starting training")
--> 162             cv_pipeline = train_pipeline(pipeline, X_train, y_train, automl_config.optimize_thresholds, automl_config.objective)
    163             logger.debug(f"\t\t\tFold {i}: finished training")
    164             if automl_config.optimize_thresholds and pipeline.can_tune_threshold_with_objective(automl_config.objective):

~/Desktop/evalml/evalml/automl/engine/engine_base.py in train_pipeline(pipeline, X, y, optimize_thresholds, objective)
    111                                                                   test_size=0.2, random_seed=pipeline.random_seed)
    112     cv_pipeline = pipeline.clone()
--> 113     cv_pipeline.fit(X, y)
    114     tune_binary_threshold(cv_pipeline, objective, cv_pipeline.problem_type,
    115                           X_threshold_tuning, y_threshold_tuning)

~/Desktop/evalml/evalml/utils/base_meta.py in _set_fit(self, X, y)
     16         @wraps(method)
     17         def _set_fit(self, X, y=None):
---> 18             return_value = method(self, X, y)
     19             self._is_fitted = True
     20             return return_value

~/Desktop/evalml/evalml/pipelines/classification_pipeline.py in fit(self, X, y)
     35         self._encoder.fit(y)
     36         y = self._encode_targets(y)
---> 37         self._fit(X, y)
     38         return self
     39 

~/Desktop/evalml/evalml/pipelines/pipeline_base.py in _fit(self, X, y)
    217     def _fit(self, X, y):
    218         self.input_target_name = y.name
--> 219         self._component_graph.fit(X, y)
    220         self.input_feature_names = self._component_graph.input_feature_names
    221 

~/Desktop/evalml/evalml/pipelines/component_graph.py in fit(self, X, y)
    122         X = infer_feature_types(X)
    123         X = _convert_woodwork_types_wrapper(X.to_dataframe())
--> 124         self._compute_features(self.compute_order, X, y, fit=True)
    125         self._feature_provenance = self._get_feature_provenance(X.columns)
    126         return self

~/Desktop/evalml/evalml/pipelines/component_graph.py in _compute_features(self, component_list, X, y, fit)
    249             else:
    250                 if fit:
--> 251                     component_instance.fit(input_x, input_y)
    252                 if not (fit and component_name == self.compute_order[-1]):  # Don't call predict on the final component during fit
    253                     output = component_instance.predict(input_x)

~/Desktop/evalml/evalml/utils/base_meta.py in _set_fit(self, X, y)
     16         @wraps(method)
     17         def _set_fit(self, X, y=None):
---> 18             return_value = method(self, X, y)
     19             self._is_fitted = True
     20             return return_value

~/Desktop/evalml/evalml/pipelines/components/estimators/estimator.py in fit(self, X, y)
     45         X, y = self._manage_woodwork(X, y)
     46         self.input_feature_names = list(X.columns)
---> 47         self._component_obj.fit(X, y)
     48         return self
     49 

~/Desktop/evalml_venv/lib/python3.7/site-packages/sklearn/ensemble/_stacking.py in fit(self, X, y, sample_weight)
    439         self._le = LabelEncoder().fit(y)
    440         self.classes_ = self._le.classes_
--> 441         return super().fit(X, self._le.transform(y), sample_weight)
    442 
    443     @if_delegate_has_method(delegate='final_estimator_')

~/Desktop/evalml_venv/lib/python3.7/site-packages/sklearn/ensemble/_stacking.py in fit(self, X, y, sample_weight)
    182                                        fit_params=fit_params,
    183                                        verbose=self.verbose)
--> 184             for est, meth in zip(all_estimators, self.stack_method_)
    185             if est != 'drop'
    186         )

~/Desktop/evalml_venv/lib/python3.7/site-packages/joblib/parallel.py in __call__(self, iterable)
   1052 
   1053             with self._backend.retrieval_context():
-> 1054                 self.retrieve()
   1055             # Make sure that we get a last message telling us we are done
   1056             elapsed_time = time.time() - self._start_time

~/Desktop/evalml_venv/lib/python3.7/site-packages/joblib/parallel.py in retrieve(self)
    931             try:
    932                 if getattr(self._backend, 'supports_timeout', False):
--> 933                     self._output.extend(job.get(timeout=self.timeout))
    934                 else:
    935                     self._output.extend(job.get())

~/Desktop/evalml_venv/lib/python3.7/site-packages/joblib/_parallel_backends.py in wrap_future_result(future, timeout)
    540         AsyncResults.get from multiprocessing."""
    541         try:
--> 542             return future.result(timeout=timeout)
    543         except CfTimeoutError as e:
    544             raise TimeoutError from e

~/.pyenv/versions/3.7.9/lib/python3.7/concurrent/futures/_base.py in result(self, timeout)
    433                 raise CancelledError()
    434             elif self._state == FINISHED:
--> 435                 return self.__get_result()
    436             else:
    437                 raise TimeoutError()

~/.pyenv/versions/3.7.9/lib/python3.7/concurrent/futures/_base.py in __get_result(self)
    382     def __get_result(self):
    383         if self._exception:
--> 384             raise self._exception
    385         else:
    386             return self._result

AttributeError: 'WordListCorpusReader' object has no attribute '_LazyCorpusLoader__args'

Menjatuhkan semua kolom teks memungkinkan ansambel berjalan hingga selesai:

import pandas as pd
import woodwork as ww
data_set = pd.read_csv("titanic_alan.csv")
y = data_set['Survived']
X = data_set.drop(['Survived', 'Name', 'Embarked'], axis=1)
automl = AutoMLSearch(X, y, problem_type="binary", error_callback=raise_error_callback, max_batches=10, ensembling=True)
automl.search()

Ini berpotensi relevan: https://github.com/nltk/nltk/issues/1576

bug

Sumber

angela97lin

Komentar yang paling membantu

Untuk siapa pun yang mengambil ini, menyetel n_jobs=1 hanya untuk ensembler di automl membuat jejak tumpukan asli hilang. Itu bisa menjadi tambalan cepat tetapi masih ada ruang untuk menemukan akar masalahnya dan mengidentifikasi perbaikan yang lebih baik.

from evalml.pipelines import BinaryClassificationPipeline
from evalml.pipelines import StackedEnsembleClassifier
from evalml.pipelines.components.utils import WrappedSKClassifier
import pandas as pd
import pytest

X = pd.read_csv("/Users/freddy.boulton/Downloads/titanic_text.csv")
y = X.pop('Survived')
X = X.drop(["Embarked"], axis=1)

components = ["Imputer", "Text Featurization Component", "One Hot Encoder"]
estimators = ["Random Forest Classifier", "CatBoost Classifier", "Extra Trees Classifier"]
pipelines = [BinaryClassificationPipeline(component_graph=components + [est]) for est in estimators]

ensemble = StackedEnsembleClassifier(pipelines, n_jobs=1)
ensemble.fit(X, y)

Juga, seseorang memeriksa saya tetapi saya dapat mengulangi masalah asli dengan evalml 0.23.0 jadi saya tidak yakin apakah perlu menyelidiki perbedaan antara 0.24.1 dan 0.23.0.

freddyaboulton pada 20 Mei 2021

👍2

Semua 5 komentar

Saya pikir kita dapat melakukan repro tanpa menjalankan pencarian - hanya menekan fit pada StackedEnsemblerClassifier menimbulkan kesalahan. Saya tidak yakin apakah ini sepenuhnya karena multiprosesor, menggunakan Parallel(n_jobs=-1) dengan pipa vanilla berfungsi. Saya pikir itu sesuatu yang terjadi dalam StackedEnsemblerClassifier :

from evalml.pipelines import BinaryClassificationPipeline
from evalml.pipelines import StackedEnsembleClassifier
from evalml.pipelines.components.utils import WrappedSKClassifier
import pandas as pd
from joblib import Parallel, delayed
import pytest

X = pd.read_csv("/Users/freddy.boulton/Downloads/titanic_text.csv")
y = X.pop('Survived')

components = ["Imputer", "Text Featurization Component", "One Hot Encoder"]
estimators = ["Random Forest Classifier", "CatBoost Classifier", "Extra Trees Classifier"]
pipelines = [BinaryClassificationPipeline(component_graph=components + [est]) for est in estimators]

# Fitting each pipeline individually works
for pl in pipelines:
    pl.fit(X, y)

# Wrapping each pipeline in sklearn works
for pl in pipelines:
    WrappedSKClassifier(pl).fit(X, y)


def fit_pipeline(pipeline, X, y):
    return pipeline.fit(X, y)

# Fitting pipelines in parallel works too
fit_pipelines = Parallel(n_jobs=-1)(delayed(fit_pipeline)(pl, X, y) for pl in pipelines)
fit_sklearn_wrapped = Parallel(n_jobs=-1)(delayed(fit_pipeline)(WrappedSKClassifier(pl), X, y) for pl in pipelines)


# Using ensemble does not work
ensemble = StackedEnsembleClassifier(pipelines)
with pytest.raises(AttributeError,
                   match="'WordListCorpusReader' object has no attribute '_LazyCorpusLoader__args'"):
    ensemble.fit(X, y)

freddyaboulton pada 20 Mei 2021

👍1

@freddyaboulton luar biasa! Ya saya melihat itu juga.

Saya tahu kumpulan data yang kami berikan telah diacak relatif terhadap data titanic standar. Aku ingin tahu apakah itu ada hubungannya dengan penyebabnya di sini.

dsherry pada 20 Mei 2021

from evalml.pipelines import BinaryClassificationPipeline
from evalml.pipelines import StackedEnsembleClassifier
from evalml.pipelines.components.utils import WrappedSKClassifier
import pandas as pd
import pytest

X = pd.read_csv("/Users/freddy.boulton/Downloads/titanic_text.csv")
y = X.pop('Survived')
X = X.drop(["Embarked"], axis=1)

components = ["Imputer", "Text Featurization Component", "One Hot Encoder"]
estimators = ["Random Forest Classifier", "CatBoost Classifier", "Extra Trees Classifier"]
pipelines = [BinaryClassificationPipeline(component_graph=components + [est]) for est in estimators]

ensemble = StackedEnsembleClassifier(pipelines, n_jobs=1)
ensemble.fit(X, y)

Juga, seseorang memeriksa saya tetapi saya dapat mengulangi masalah asli dengan evalml 0.23.0 jadi saya tidak yakin apakah perlu menyelidiki perbedaan antara 0.24.1 dan 0.23.0.

freddyaboulton pada 20 Mei 2021

👍2

@freddyaboulton Saya pikir ini masuk akal mengingat https://github.com/nltk/nltk/issues/1576 , tidak yakin mereka pernah menyelesaikan ini tetapi saya juga dapat melakukan repro dengan 0.23.0 :')

angela97lin pada 20 Mei 2021

Ini sepertinya sudah mendekati titik

ParthivNaresh pada 20 Mei 2021

Apakah halaman ini membantu?

0 / 5 - 0 peringkat

Masalah terkait

API Pemeriksaan Data

kmax12 · 11Komentar

Penjelasan prediksi

dsherry · 8Komentar

Ansambel bertumpuk berkinerja buruk

dancuarini · 11Komentar

Jatuhkan dukungan untuk python 3.5

dsherry · 8Komentar

Dokumen membutuhkan waktu lama untuk dibuat

freddyaboulton · 8Komentar