ValueError: Input contains infinity or a value too large for dtype('float64').

[csala]

sdv.evaluate call sometimes fails with a ValueError: Input contains infinity or a value too large for dtype('float64').

The exception is raised in pipeline fit step inside sdmetrics/detection/tabular/logistic.py.

We should review if we can prevent this, or at least capture it and return a 0.

This is the full traceback:

  ------------------
  from sdv.evaluation import evaluate
  
  evaluate(new_data, data)
  ------------------
  
  ---------------------------------------------------------------------------
  ValueError                                Traceback (most recent call last)
  <ipython-input-1-349ebfb54984> in <module>
        1 from sdv.evaluation import evaluate
        2 
  ----> 3 evaluate(new_data, data)
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sdv/evaluation.py in evaluate(synthetic_data, real_data, metadata, root_path, table_name, metrics, get_report, aggregate)
      152     computed = {}
      153     for metric in metrics:
  --> 154         computed[metric] = METRICS[metric](synth, real, metadata, details=get_report)
      155 
      156     if get_report:
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sdv/evaluation.py in _logistic_detection(synthetic, real, metadata, details)
       98 
       99 def _logistic_detection(synthetic, real, metadata=None, details=False):
  --> 100     return _tabular_metric(LogisticDetector(), synthetic, real, metadata, details)
      101 
      102 
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sdv/evaluation.py in _tabular_metric(sdmetric, synthetic, real, metadata, details)
       86         return list(metrics)
       87 
  ---> 88     return np.mean([metric.value for metric in metrics])
       89 
       90 
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sdv/evaluation.py in <listcomp>(.0)
       86         return list(metrics)
       87 
  ---> 88     return np.mean([metric.value for metric in metrics])
       89 
       90 
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sdmetrics/detection/tabular/base.py in metrics(self, metadata, real_tables, synthetic_tables)
       48             Metric: The next metric.
       49         """
  ---> 50         yield from self._single_table_detection(metadata, real_tables, synthetic_tables)
       51         yield from self._parent_child_detection(metadata, real_tables, synthetic_tables)
       52 
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sdmetrics/detection/tabular/base.py in _single_table_detection(self, metadata, real_tables, synthetic_tables)
       57             auroc = self._compute_auroc(
       58                 real_tables[table_name][table_fields],
  ---> 59                 synthetic_tables[table_name][table_fields])
       60 
       61             yield Metric(
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sdmetrics/detection/tabular/base.py in _compute_auroc(self, real_table, synthetic_table)
      123         kf = StratifiedKFold(n_splits=3, shuffle=True)
      124         for train_index, test_index in kf.split(X, y):
  --> 125             self.fit(X[train_index], y[train_index])
      126             y_pred = self.predict_proba(X[test_index])
      127             auroc = roc_auc_score(y[test_index], y_pred)
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sdmetrics/detection/tabular/logistic.py in fit(self, X, y)
       22             ('classifier', LogisticRegression(solver="lbfgs")),
       23         ])
  ---> 24         self.model.fit(X, y)
       25 
       26     def predict_proba(self, X):
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sklearn/pipeline.py in fit(self, X, y, **fit_params)
      328         """
      329         fit_params_steps = self._check_fit_params(**fit_params)
  --> 330         Xt = self._fit(X, y, **fit_params_steps)
      331         with _print_elapsed_time('Pipeline',
      332                                  self._log_message(len(self.steps) - 1)):
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sklearn/pipeline.py in _fit(self, X, y, **fit_params_steps)
      294                 message_clsname='Pipeline',
      295                 message=self._log_message(step_idx),
  --> 296                 **fit_params_steps[name])
      297             # Replace the transformer of the step with the fitted
      298             # transformer. This is necessary when loading the transformer
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/joblib/memory.py in __call__(self, *args, **kwargs)
      350 
      351     def __call__(self, *args, **kwargs):
  --> 352         return self.func(*args, **kwargs)
      353 
      354     def call_and_shelve(self, *args, **kwargs):
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
      738     with _print_elapsed_time(message_clsname, message):
      739         if hasattr(transformer, 'fit_transform'):
  --> 740             res = transformer.fit_transform(X, y, **fit_params)
      741         else:
      742             res = transformer.fit(X, y, **fit_params).transform(X)
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sklearn/base.py in fit_transform(self, X, y, **fit_params)
      691         else:
      692             # fit method of arity 2 (supervised transformation)
  --> 693             return self.fit(X, y, **fit_params).transform(X)
      694 
      695 
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sklearn/preprocessing/_data.py in fit(self, X, y)
     1200         X = self._validate_data(X, accept_sparse='csc', estimator=self,
     1201                                 dtype=FLOAT_DTYPES,
  -> 1202                                 force_all_finite='allow-nan')
     1203 
     1204         q_min, q_max = self.quantile_range
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sklearn/base.py in _validate_data(self, X, y, reset, validate_separately, **check_params)
      418                     f"requires y to be passed, but the target y is None."
      419                 )
  --> 420             X = check_array(X, **check_params)
      421             out = X
      422         else:
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sklearn/utils/validation.py in inner_f(*args, **kwargs)
       70                           FutureWarning)
       71         kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
  ---> 72         return f(**kwargs)
       73     return inner_f
       74 
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sklearn/utils/validation.py in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator)
      643         if force_all_finite:
      644             _assert_all_finite(array,
  --> 645                                allow_nan=force_all_finite == 'allow-nan')
      646 
      647     if ensure_min_samples > 0:
  
  ~/work/SDV/SDV/.tox/py36/lib/python3.6/site-packages/sklearn/utils/validation.py in _assert_all_finite(X, allow_nan, msg_dtype)
       97                     msg_err.format
       98                     (type_err,
  ---> 99                      msg_dtype if msg_dtype is not None else X.dtype)
      100             )
      101     # for object dtype data, we only check for NaNs (GH-13254)
  
  ValueError: Input contains infinity or a value too large for dtype('float64').