Python sklearn.utils.fixes.MaskedArray() Examples

def test_masked_array_obj_dtype_pickleable():
    marr = MaskedArray([1, None, 'a'], dtype=object)

    for mask in (True, False, [0, 1, 0]):
        marr.mask = mask
        marr_pickled = pickle.loads(pickle.dumps(marr))
        assert_array_equal(marr.data, marr_pickled.data)
        assert_array_equal(marr.mask, marr_pickled.mask) 

def test_masked_array_obj_dtype_pickleable():
    marr = MaskedArray([1, None, 'a'], dtype=object)

    for mask in (True, False, [0, 1, 0]):
        marr.mask = mask
        marr_pickled = pickle.loads(pickle.dumps(marr))
        assert_array_equal(marr.data, marr_pickled.data)
        assert_array_equal(marr.mask, marr_pickled.mask) 

def _process_outputs(self, out, n_splits):
        """return results dict and best dict for given outputs"""

        # if one choose to see train score, "out" will contain train score info
        if self.return_train_score:
            (train_scores, test_scores, test_sample_counts,
             fit_time, score_time, parameters) = zip(*out)
        else:
            (test_scores, test_sample_counts,
             fit_time, score_time, parameters) = zip(*out)

        candidate_params = parameters[::n_splits]
        n_candidates = len(candidate_params)

        results = dict()

        # Computed the (weighted) mean and std for test scores alone
        # NOTE test_sample counts (weights) remain the same for all candidates
        test_sample_counts = np.array(test_sample_counts[:n_splits],
                                      dtype=np.int)

        results = self._store_results(
            results, n_splits, n_candidates, 'test_score',
            test_scores, splits=True, rank=True,
            weights=test_sample_counts if self.iid else None)
        if self.return_train_score:
            results = self._store_results(
                results, n_splits, n_candidates,
                'train_score', train_scores, splits=True)
        results = self._store_results(
            results, n_splits, n_candidates, 'fit_time', fit_time)
        results = self._store_results(
            results, n_splits, n_candidates, 'score_time', score_time)

        best_index = np.flatnonzero(results["rank_test_score"] == 1)[0]

        # Use one MaskedArray and mask all the places where the param is not
        # applicable for that candidate. Use defaultdict as each candidate may
        # not contain all the params
        param_results = defaultdict(partial(MaskedArray,
                                            np.empty(n_candidates,),
                                            mask=True,
                                            dtype=object))
        for cand_i, params in enumerate(candidate_params):
            for name, value in params.items():
                # An all masked empty array gets created for the key
                # `"param_%s" % name` at the first occurence of `name`.
                # Setting the value at an index also unmasks that index
                param_results["param_%s" % name][cand_i] = value

        results.update(param_results)

        # Store a list of param dicts at the key 'params'
        results['params'] = candidate_params

        return results, best_index 

def _format_results(candidate_params, scorers, n_splits, out):
        n_candidates = len(candidate_params)

        (test_score_dicts,) = zip(*out)

        test_scores = aggregate_score_dicts(test_score_dicts)

        results = {}

        def _store(key_name, array, splits=False, rank=False):
            """A small helper to store the scores/times to the cv_results_"""
            array = np.array(array, dtype=np.float64).reshape(n_candidates,
                                                              n_splits)
            if splits:
                for split_i in range(n_splits):
                    # Uses closure to alter the results
                    results["split%d_%s"
                            % (split_i, key_name)] = array[:, split_i]

            array_means = np.mean(array, axis=1)
            results['mean_%s' % key_name] = array_means
            array_stds = np.std(array, axis=1)
            results['std_%s' % key_name] = array_stds

            if rank:
                results["rank_%s" % key_name] = np.asarray(
                    rankdata(-array_means, method='min'), dtype=np.int32)

        # Use one MaskedArray and mask all the places where the param is not
        # applicable for that candidate. Use defaultdict as each candidate may
        # not contain all the params
        param_results = defaultdict(partial(MaskedArray,
                                            np.empty(n_candidates, ),
                                            mask=True,
                                            dtype=object))
        for cand_i, params in enumerate(candidate_params):
            for name, value in params.items():
                # An all masked empty array gets created for the key
                # `"param_%s" % name` at the first occurrence of `name`.
                # Setting the value at an index also unmasks that index
                param_results["param_%s" % name][cand_i] = value

        results.update(param_results)
        # Store a list of param dicts at the key 'params'
        results['params'] = candidate_params

        for scorer_name in scorers.keys():
            _store('test_%s' % scorer_name, test_scores[scorer_name],
                   splits=True, rank=True)

        return results