fix docstrings

README.rst

@@ -9,19 +9,19 @@ explanations of your supervised machine learning models.
 FACET is composed of the following key components:
 
 +----------------+---------------------------------------------------------------------+
-| |inspect|      | **Model Inspection**                                                |
+| |spacer|       | **Model Inspection**                                                |
 |                |                                                                     |
-|                | FACET introduces a new algorithm to quantify dependencies and       |
+| |inspect|      | FACET introduces a new algorithm to quantify dependencies and       |
 |                | interactions between features in ML models.                         |
 |                | This new tool for human-explainable AI adds a new, global           |
 |                | perspective to the observation-level explanations provided by the   |
 |                | popular `SHAP <https://shap.readthedocs.io/en/latest/>`__ approach. |
 |                | To learn more about FACET’s model inspection capabilities, see the  |
 |                | getting started example below.                                      |
 +----------------+---------------------------------------------------------------------+
-| |sim|          | **Model Simulation**                                                |
+| |              | **Model Simulation**                                                |
 |                |                                                                     |
-|                | FACET’s model simulation algorithms use ML models for               |
+| |sim|          | FACET’s model simulation algorithms use ML models for               |
 |                | *virtual experiments* to help identify scenarios that optimise      |
 |                | predicted outcomes.                                                 |
 |                | To quantify the uncertainty in simulations, FACET utilises a range  |
@@ -30,9 +30,9 @@ FACET is composed of the following key components:
 |                | For an example of FACET’s bootstrap simulations, see the getting    |
 |                | started example below.                                              |
 +----------------+---------------------------------------------------------------------+
-| |pipe|         | **Enhanced Machine Learning Workflow**                              |
-| |spacer|       |                                                                     |
-|                | FACET offers an efficient and transparent machine learning          |
+| |              | **Enhanced Machine Learning Workflow**                              |
+|                |                                                                     |
+| |pipe|         | FACET offers an efficient and transparent machine learning          |
 |                | workflow, enhancing                                                 |
 |                | `scikit-learn <https://scikit-learn.org/stable/index.html>`__'s     |
 |                | tried and tested pipelining paradigm with new capabilities for model|

src/facet/crossfit/_crossfit.py

@@ -141,9 +141,9 @@ def __init__(
         """
         :param pipeline: learner pipeline to be fitted
         :param cv: the cross-validator generating the train splits
-        :param shuffle_features: if ``True``, shuffle column order of features for \
+        :param shuffle_features: if ``True``, shuffle column order of features for
             every crossfit (default: ``False``)
-        :param random_state: optional random seed or random state for shuffling the \
+        :param random_state: optional random seed or random state for shuffling the
             feature column order
         """
         super().__init__(
@@ -199,10 +199,10 @@ def fit(self: T, sample: Sample, **fit_params) -> T:
         Fit the underlying pipeline to the full sample, and fit clones of the pipeline
         to each of the train splits generated by the cross-validator.
 
-        :param sample: the sample to fit the estimators to; if the sample specifies \
-            weights these are passed on to the learner as keyword argument \
+        :param sample: the sample to fit the estimators to; if the sample specifies
+            weights these are passed on to the learner as keyword argument
             ``sample_weight``
-        :param fit_params: optional fit parameters, to be passed on to the fit method \
+        :param fit_params: optional fit parameters, to be passed on to the fit method
             of the base estimator
         :return: ``self``
         """
@@ -226,11 +226,11 @@ def score(
 
         The crossfit must already be fitted, see :meth:`.fit`
 
-        :param scoring: scoring to use to score the models (see \
-            :meth:`sklearn.metrics.check_scoring` for details); if the crossfit \
-            was fitted using sample weights, these are passed on to the scoring \
+        :param scoring: scoring to use to score the models (see
+            :meth:`sklearn.metrics.check_scoring` for details); if the crossfit
+            was fitted using sample weights, these are passed on to the scoring
             function as keyword argument ``sample_weight``
-        :param train_scores: if ``True``, calculate train scores instead of test \
+        :param train_scores: if ``True``, calculate train scores instead of test
             scores (default: ``False``)
         :return: the resulting scores as a 1d numpy array
         """
@@ -249,14 +249,14 @@ def fit_score(
 
         See :meth:`.fit` and :meth:`.score` for details.
 
-        :param sample: the sample to fit the estimators to; if the sample specifies \
-            weights these are passed on to the learner and scoring function as keyword \
+        :param sample: the sample to fit the estimators to; if the sample specifies
+            weights these are passed on to the learner and scoring function as keyword
              argument ``sample_weight``
-        :param fit_params: optional fit parameters, to be passed on to the fit method \
+        :param fit_params: optional fit parameters, to be passed on to the fit method
             of the learner
-        :param scoring: scoring function to use to score the models \
+        :param scoring: scoring function to use to score the models
             (see :meth:`~sklearn.metrics.check_scoring` for details)
-        :param train_scores: if ``True``, calculate train scores instead of test \
+        :param train_scores: if ``True``, calculate train scores instead of test
             scores (default: ``False``)
 
         :return: the resulting scores
@@ -272,7 +272,7 @@ def fit_score(
     def resize(self: T, n_splits: int) -> T:
         """
         Reduce the size of this crossfit by removing a subset of the fits.
-        :param n_splits: the number of fits to keep. Must be lower, or equal to, the \
+        :param n_splits: the number of fits to keep. Must be lower, or equal to, the
             current number of fits
         :return:
         """

src/facet/data/_sample.py

@@ -70,14 +70,14 @@ def __init__(
         weight_name: Optional[str] = None,
     ) -> None:
         """
-        :param observations: a table of observational data; \
+        :param observations: a table of observational data;
             each row represents one observation
-        :param target_name: the name of the column representing the target \
+        :param target_name: the name of the column representing the target
             variable; or an iterable of names representing multiple targets
-        :param feature_names: optional iterable of strings naming the columns that \
+        :param feature_names: optional iterable of strings naming the columns that
             represent features; if omitted, all non-target and non-weight columns are
             considered features
-        :param weight_name: optional name of a column representing the weight of each \
+        :param weight_name: optional name of a column representing the weight of each
             observation
         """
 
@@ -256,7 +256,7 @@ def subsample(
 
         :param loc: indices of observations to select
         :param iloc: integer indices of observations to select
-        :return: copy of this sample, comprising only the observations in the given \
+        :return: copy of this sample, comprising only the observations in the given
             rows
         """
         subsample = copy(self)

src/facet/inspection/_explainer.py

@@ -110,10 +110,10 @@ def __init__(
     ) -> None:
         """
         :param model_output: (optional) override the default model output parameter
-        :param feature_perturbation: (optional) override the default \
+        :param feature_perturbation: (optional) override the default
             feature_perturbation parameter
-        :param use_background_dataset: if ``False``, don't pass the background \
-            dataset on to the tree explainer even if a background dataset is passed \
+        :param use_background_dataset: if ``False``, don't pass the background
+            dataset on to the tree explainer even if a background dataset is passed
             to :meth:`.make_explainer`
         """
         super().__init__()
@@ -174,7 +174,7 @@ def make_explainer(
 @inheritdoc(match="[see superclass]")
 class KernelExplainerFactory(ExplainerFactory):
     """
-    A factory constructing class:`~shap.KernelExplainer` objects.
+    A factory constructing :class:`~shap.KernelExplainer` objects.
     """
 
     def __init__(
@@ -185,12 +185,12 @@ def __init__(
     ) -> None:
         """
         :param link: (optional) override the default link parameter
-        :param l1_reg: (optional) override the default l1_reg parameter of method \
-            :meth:`~shap.KernelExplainer.shap_values`; pass ``None`` to use the \
+        :param l1_reg: (optional) override the default l1_reg parameter of method
+            :meth:`~shap.KernelExplainer.shap_values`; pass ``None`` to use the
             default value used by :meth:`~shap.KernelExplainer.shap_values`
-        :param data_size_limit: (optional) maximum number of observations to use as \
-            the background data set; larger data sets will be down-sampled using \
-            method :meth:`~shap.kmeans`. \
+        :param data_size_limit: (optional) maximum number of observations to use as
+            the background data set; larger data sets will be down-sampled using
+            method :meth:`~shap.kmeans`.
             Pass ``None`` to prevent down-sampling the background data set.
         """
         super().__init__()