Tuto-GUDHI-representations.ipynb is failing with gudhi 3.7.0

[VincentRouvreau]

Since gudhi 3.7.0, Tuto-GUDHI-representations.ipynb is failing on the model = model.fit(train_dgms, train_labs) cell.

Seems to come from GUDHI/gudhi-devel#719

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Cell In[22], line 1
----> 1 model = model.fit(train_dgms, train_labs)

File ~/miniconda3/envs/test_notebooks/lib/python3.8/site-packages/sklearn/model_selection/_search.py:875, in BaseSearchCV.fit(self, X, y, groups, **fit_params)
    869     results = self._format_results(
    870         all_candidate_params, n_splits, all_out, all_more_results
    871     )
    873     return results
--> 875 self._run_search(evaluate_candidates)
    877 # multimetric is determined here because in the case of a callable
    878 # self.scoring the return type is only known after calling
    879 first_test_score = all_out[0]["test_scores"]

File ~/miniconda3/envs/test_notebooks/lib/python3.8/site-packages/sklearn/model_selection/_search.py:1389, in GridSearchCV._run_search(self, evaluate_candidates)
   1387 def _run_search(self, evaluate_candidates):
   1388     """Search all candidates in param_grid"""
-> 1389     evaluate_candidates(ParameterGrid(self.param_grid))

File ~/miniconda3/envs/test_notebooks/lib/python3.8/site-packages/sklearn/model_selection/_search.py:822, in BaseSearchCV.fit.<locals>.evaluate_candidates(candidate_params, cv, more_results)
    814 if self.verbose > 0:
    815     print(
    816         "Fitting {0} folds for each of {1} candidates,"
    817         " totalling {2} fits".format(
    818             n_splits, n_candidates, n_candidates * n_splits
    819         )
    820     )
--> 822 out = parallel(
    823     delayed(_fit_and_score)(
    824         clone(base_estimator),
    825         X,
    826         y,
    827         train=train,
    828         test=test,
    829         parameters=parameters,
    830         split_progress=(split_idx, n_splits),
    831         candidate_progress=(cand_idx, n_candidates),
    832         **fit_and_score_kwargs,
    833     )
    834     for (cand_idx, parameters), (split_idx, (train, test)) in product(
    835         enumerate(candidate_params), enumerate(cv.split(X, y, groups))
    836     )
    837 )
    839 if len(out) < 1:
    840     raise ValueError(
    841         "No fits were performed. "
    842         "Was the CV iterator empty? "
    843         "Were there no candidates?"
    844     )

File ~/miniconda3/envs/test_notebooks/lib/python3.8/site-packages/joblib/parallel.py:1088, in Parallel.__call__(self, iterable)
   1085 if self.dispatch_one_batch(iterator):
   1086     self._iterating = self._original_iterator is not None
-> 1088 while self.dispatch_one_batch(iterator):
   1089     pass
   1091 if pre_dispatch == "all" or n_jobs == 1:
   1092     # The iterable was consumed all at once by the above for loop.
   1093     # No need to wait for async callbacks to trigger to
   1094     # consumption.

File ~/miniconda3/envs/test_notebooks/lib/python3.8/site-packages/joblib/parallel.py:901, in Parallel.dispatch_one_batch(self, iterator)
    899     return False
    900 else:
--> 901     self._dispatch(tasks)
    902     return True

File ~/miniconda3/envs/test_notebooks/lib/python3.8/site-packages/joblib/parallel.py:819, in Parallel._dispatch(self, batch)
    817 with self._lock:
    818     job_idx = len(self._jobs)
--> 819     job = self._backend.apply_async(batch, callback=cb)
    820     # A job can complete so quickly than its callback is
    821     # called before we get here, causing self._jobs to
    822     # grow. To ensure correct results ordering, .insert is
    823     # used (rather than .append) in the following line
    824     self._jobs.insert(job_idx, job)

File ~/miniconda3/envs/test_notebooks/lib/python3.8/site-packages/joblib/_parallel_backends.py:208, in SequentialBackend.apply_async(self, func, callback)
    206 def apply_async(self, func, callback=None):
    207     """Schedule a func to be run"""
--> 208     result = ImmediateResult(func)
    209     if callback:
    210         callback(result)

File ~/miniconda3/envs/test_notebooks/lib/python3.8/site-packages/joblib/_parallel_backends.py:597, in ImmediateResult.__init__(self, batch)
    594 def __init__(self, batch):
    595     # Don't delay the application, to avoid keeping the input
    596     # arguments in memory
--> 597     self.results = batch()

File ~/miniconda3/envs/test_notebooks/lib/python3.8/site-packages/joblib/parallel.py:288, in BatchedCalls.__call__(self)
    284 def __call__(self):
    285     # Set the default nested backend to self._backend but do not set the
    286     # change the default number of processes to -1
    287     with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 288         return [func(*args, **kwargs)
    289                 for func, args, kwargs in self.items]

File ~/miniconda3/envs/test_notebooks/lib/python3.8/site-packages/joblib/parallel.py:288, in <listcomp>(.0)
    284 def __call__(self):
    285     # Set the default nested backend to self._backend but do not set the
    286     # change the default number of processes to -1
    287     with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 288         return [func(*args, **kwargs)
    289                 for func, args, kwargs in self.items]

File ~/miniconda3/envs/test_notebooks/lib/python3.8/site-packages/sklearn/utils/fixes.py:117, in _FuncWrapper.__call__(self, *args, **kwargs)
    115 def __call__(self, *args, **kwargs):
    116     with config_context(**self.config):
--> 117         return self.function(*args, **kwargs)

File ~/miniconda3/envs/test_notebooks/lib/python3.8/site-packages/sklearn/model_selection/_validation.py:672, in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, return_estimator, split_progress, candidate_progress, error_score)
    670     cloned_parameters = {}
    671     for k, v in parameters.items():
--> 672         cloned_parameters[k] = clone(v, safe=False)
    674     estimator = estimator.set_params(**cloned_parameters)
    676 start_time = time.time()

File ~/miniconda3/envs/test_notebooks/lib/python3.8/site-packages/sklearn/base.py:87, in clone(estimator, safe)
     79             raise TypeError(
     80                 "Cannot clone object '%s' (type %s): "
     81                 "it does not seem to be a scikit-learn "
     82                 "estimator as it does not implement a "
     83                 "'get_params' method." % (repr(estimator), type(estimator))
     84             )
     86 klass = estimator.__class__
---> 87 new_object_params = estimator.get_params(deep=False)
     88 for name, param in new_object_params.items():
     89     new_object_params[name] = clone(param, safe=False)

File ~/miniconda3/envs/test_notebooks/lib/python3.8/site-packages/sklearn/base.py:170, in BaseEstimator.get_params(self, deep)
    168 out = dict()
    169 for key in self._get_param_names():
--> 170     value = getattr(self, key)
    171     if deep and hasattr(value, "get_params") and not isinstance(value, type):
    172         deep_items = value.get_params().items()

AttributeError: 'Landscape' object has no attribute 'sample_range'

[mglisse]

That happens when calling get_params before fit: Landscape().get_params(), which can happen naturally. Adding self.sample_range = self.sample_range_init in Landscape.__init__ would likely kill the warning, but it may be a sign that what I did in GUDHI/gudhi-devel#719 does not match sklearn's expectations 😞

[VincentRouvreau]

To be tested with gudhi > 3.7.0

[VincentRouvreau]

Tested and ok with gudhi 3.8.0