From 169e9dfe198f3278ce79fcec0db7a8e46ef6d362 Mon Sep 17 00:00:00 2001 From: xadupre Date: Sat, 7 Sep 2024 18:58:22 +0200 Subject: [PATCH] fix wrong change --- mlinsights/helpers/pipeline.py | 2 +- mlinsights/mlbatch/cache_model.py | 2 +- mlinsights/mlmodel/categories_to_integers.py | 13 +++++++------ mlinsights/mlmodel/classification_kmeans.py | 2 +- mlinsights/mlmodel/kmeans_l1.py | 2 +- mlinsights/mlmodel/sklearn_testing.py | 4 ++-- mlinsights/sklapi/sklearn_base.py | 6 +++--- mlinsights/sklapi/sklearn_base_transform_learner.py | 2 +- .../sklapi/sklearn_base_transform_stacking.py | 2 +- 9 files changed, 18 insertions(+), 17 deletions(-) diff --git a/mlinsights/helpers/pipeline.py b/mlinsights/helpers/pipeline.py index a4caec8..ec4d833 100644 --- a/mlinsights/helpers/pipeline.py +++ b/mlinsights/helpers/pipeline.py @@ -120,7 +120,7 @@ def to_str(self, nrows=5): """ rows = [f"BaseEstimatorDebugInformation({self.model.__class__.__name__})"] for k in sorted(self.inputs): - assert k in self.outputs, f"Unable to find output for method '{k}'." + assert k in self.outputs, f"Unable to find output for method {k!r}." rows.append(" " + k + "(") self.display(self.inputs[k], nrows) rows.append(textwrap.indent(self.display(self.inputs[k], nrows), " ")) diff --git a/mlinsights/mlbatch/cache_model.py b/mlinsights/mlbatch/cache_model.py index f7d4cde..98387ca 100644 --- a/mlinsights/mlbatch/cache_model.py +++ b/mlinsights/mlbatch/cache_model.py @@ -80,7 +80,7 @@ def as_key(params): elif v is None: sv = "" else: - raise TypeError(f"Unable to create a key with value '{k}':{v}") + raise TypeError(f"Unable to create a key with value {k!r}:{v!r}") els.append((k, sv)) return str(els) diff --git a/mlinsights/mlmodel/categories_to_integers.py b/mlinsights/mlmodel/categories_to_integers.py index 6055cd4..7dabf29 100644 --- a/mlinsights/mlmodel/categories_to_integers.py +++ b/mlinsights/mlmodel/categories_to_integers.py @@ -70,10 +70,11 @@ def fit(self, X, y=None, **fit_params): """ if not isinstance(X, pandas.DataFrame): raise TypeError(f"this transformer only accept Dataframes, not {type(X)}") - if self.columns: - columns = self.columns - else: - columns = [c for c, d in zip(X.columns, X.dtypes) if d in (object,)] + columns = ( + self.columns + if self.columns + else [c for c, d in zip(X.columns, X.dtypes) if d in (object, str)] + ) self._fit_columns = columns max_cat = max(len(X) // 2 + 1, 10000) @@ -86,7 +87,7 @@ def fit(self, X, y=None, **fit_params): raise ValueError( f"Too many categories ({nb}) for one column '{c}' max_cat={max_cat}" ) - self._categories[c] = dict(enumerate(list(sorted(distinct)))) + self._categories[c] = {c: i for i, c in enumerate(list(sorted(distinct)))} self._schema = self._build_schema() return self @@ -181,7 +182,7 @@ def transform(v, vec): lv.append("...") m = "\n".join(map(str, lv)) raise ValueError( - f"Unable to find category value {k}: {v} " + f"Unable to find category value {k!r}: {v!r} " f"type(v)={type(v)} among\n{m}" ) p = pos[k] diff --git a/mlinsights/mlmodel/classification_kmeans.py b/mlinsights/mlmodel/classification_kmeans.py index 3ff238e..de3e556 100644 --- a/mlinsights/mlmodel/classification_kmeans.py +++ b/mlinsights/mlmodel/classification_kmeans.py @@ -147,7 +147,7 @@ def set_params(self, **values): elif k.startswith("c_"): pc[k[2:]] = v else: - raise ValueError(f"Unexpected parameter name '{k}'") + raise ValueError(f"Unexpected parameter name {k!r}") self.clus.set_params(**pc) self.estimator.set_params(**pe) diff --git a/mlinsights/mlmodel/kmeans_l1.py b/mlinsights/mlmodel/kmeans_l1.py index 9e50907..8ac28d2 100644 --- a/mlinsights/mlmodel/kmeans_l1.py +++ b/mlinsights/mlmodel/kmeans_l1.py @@ -173,7 +173,7 @@ def _validate_center_shape(X, k, centers): """Check if centers is compatible with X and n_clusters""" assert centers.shape[0] == k, ( f"The shape of the initial centers {centers.shape} does not " - f"match the number of clusters {k}." + f"match the number of clusters {k!r}." ) assert centers.shape[1] == X.shape[1], ( f"The shape of the initial centers {centers.shape} does not " diff --git a/mlinsights/mlmodel/sklearn_testing.py b/mlinsights/mlmodel/sklearn_testing.py index ac91d1c..0e8f0ac 100644 --- a/mlinsights/mlmodel/sklearn_testing.py +++ b/mlinsights/mlmodel/sklearn_testing.py @@ -131,7 +131,7 @@ def run_test_sklearn_clone(fct_model, ext=None, copy_fitted=False): ext.assertEqual(p1[k], p2[k]) except AssertionError as e: raise AssertionError( - f"Difference for key '{k}'\n==1 {p1[k]}\n==2 {p2[k]}" + f"Difference for key {k!r}\n==1 {p1[k]}\n==2 {p2[k]}" ) from e return conv, cloned @@ -303,7 +303,7 @@ def adjust(obj1, obj2): v1 = getattr(obj1, k) setattr(obj2, k, clone_with_fitted_parameters(v1)) else: - raise RuntimeError(f"Cloned object is missing '{k}' in {obj2}.") + raise RuntimeError(f"Cloned object is missing {k!r} in {obj2}.") if isinstance(est, BaseEstimator): cloned = clone(est) diff --git a/mlinsights/sklapi/sklearn_base.py b/mlinsights/sklapi/sklearn_base.py index e3584eb..318b0e7 100644 --- a/mlinsights/sklapi/sklearn_base.py +++ b/mlinsights/sklapi/sklearn_base.py @@ -91,12 +91,12 @@ def compare_params( for k in p1: if k not in p2: if exc: - raise KeyError(f"Key '{k}' was removed.") + raise KeyError(f"Key {k!r} was removed.") return False for k in p2: if k not in p1: if exc: - raise KeyError(f"Key '{k}' was added.") + raise KeyError(f"Key {k!r} was added.") return False for k in sorted(p1): v1, v2 = p1[k], p2[k] @@ -133,7 +133,7 @@ def compare_params( if not b: if exc: raise ValueError( - f"Values for key '{k}' are different.\n---\n{v1}\n---\n{v2}" + f"Values for key {k!r} are different.\n---\n{v1}\n---\n{v2}" ) return False return True diff --git a/mlinsights/sklapi/sklearn_base_transform_learner.py b/mlinsights/sklapi/sklearn_base_transform_learner.py index 9fe9dc0..f557074 100644 --- a/mlinsights/sklapi/sklearn_base_transform_learner.py +++ b/mlinsights/sklapi/sklearn_base_transform_learner.py @@ -166,7 +166,7 @@ def set_params(self, **values): del values["method"] for k in values: if not k.startswith("model__"): - raise ValueError(f"Parameter '{k}' must start with 'model__'.") + raise ValueError(f"Parameter {k!r} must start with 'model__'.") d = len("model__") pars = {k[d:]: v for k, v in values.items()} self.model.set_params(**pars) diff --git a/mlinsights/sklapi/sklearn_base_transform_stacking.py b/mlinsights/sklapi/sklearn_base_transform_stacking.py index 664987b..c3f8aa7 100644 --- a/mlinsights/sklapi/sklearn_base_transform_stacking.py +++ b/mlinsights/sklapi/sklearn_base_transform_stacking.py @@ -163,7 +163,7 @@ def set_params(self, **values): del values["method"] for k, _v in values.items(): if not k.startswith("models_"): - raise ValueError(f"Parameter '{k}' must start with 'models_'.") + raise ValueError(f"Parameter {k!r} must start with 'models_'.") d = len("models_") pars = [{} for m in self.models] for k, v in values.items():