Add documentation

Author: BaptisteCalot

environment.dev.yml

@@ -1,5 +1,6 @@
 name: mapie-dev
 channels:
+    - defaults
     - conda-forge
 dependencies:
     - bump2version=1.0.1

mapie/classification.py

@@ -914,7 +914,16 @@ def _check_fit_parameter(
         y: ArrayLike,
         sample_weight: Optional[ArrayLike] = None,
         groups: Optional[ArrayLike] = None,
-    ):
+    ) -> Tuple[
+        Optional[ClassifierMixin],
+        Optional[Union[int, str, BaseCrossValidator]],
+        ArrayLike,
+        NDArray,
+        NDArray,
+        Optional[NDArray],
+        Optional[NDArray],
+        ArrayLike
+    ]:
         """
         Perform several checks on class parameters.
 
@@ -934,6 +943,14 @@ def _check_fit_parameter(
             train/test set.
             By default ``None``.
 
+        Returns
+        -------
+        Tuple[Optional[ClassifierMixin],
+        Optional[Union[int, str, BaseCrossValidator]],
+        ArrayLike, NDArray, NDArray, Optional[NDArray],
+        Optional[NDArray], ArrayLike]
+
+            Parameters checked
         Raises
         ------
         ValueError
@@ -973,7 +990,48 @@ def _check_fit_parameter(
 
         return (estimator, cv, X, y, y_enc, sample_weight, groups, n_samples)
 
-    def _split_data(self, X, y_enc, sample_weight, groups, size_raps):
+    def _split_data(
+        self,
+        X,
+        y_enc,
+        sample_weight,
+        groups,
+        size_raps
+    ) -> Tuple[ArrayLike, ArrayLike, ArrayLike, ArrayLike, NDArray, ArrayLike]:
+
+        """Split data for raps method
+        Parameters
+        ----------
+        X: ArrayLike
+            Observed values.
+
+        y_enc: ArrayLike
+            Target values as normalized encodings.
+
+        sample_weight: Optional[NDArray] of shape (n_samples,)
+            Non-null sample weights.
+
+        groups: Optional[ArrayLike] of shape (n_samples,)
+            Group labels for the samples used while splitting the dataset into
+            train/test set.
+            By default ``None``.
+
+        size_raps: : Optional[float]
+            Percentage of the data to be used for choosing lambda_star and
+            k_star for the RAPS method.
+
+        Returns
+        -------
+        Tuple[ArrayLike, ArrayLike, ArrayLike, NDArray, Optional[NDArray],
+        Optional[ArrayLike]]
+
+            - ArrayLike of shape (n_samples, n_features)
+            - ArrayLike of shape (n_samples,)
+            - ArrayLike of shape (n_samples,)
+            - ArrayLike of shape (n_samples,)
+            - NDArray of shape (n_samples,)
+            - ArrayLike of shape (n_samples,)
+        """
         raps_split = ShuffleSplit(
             1, test_size=size_raps, random_state=self.random_state
         )

mapie/estimator/classification/estimator.py

@@ -449,7 +449,7 @@ def predict(
         X: ArrayLike,
         alpha_np: ArrayLike = [],
         agg_scores: Any = None
-    ) -> Union[NDArray, Tuple[NDArray, NDArray, NDArray]]:
+    ) -> NDArray:
         """
         Predict target from X. It also computes the prediction per train sample
         for each test sample according to ``self.method``.
@@ -459,14 +459,19 @@ def predict(
         X: ArrayLike of shape (n_samples, n_features)
             Test data.
 
-        TODO
+        alpha_np: ArrayLike of shape (n_alphas)
+            Level of confidences.
+
+        agg_scores: Optional[str]
+            How to aggregate the scores output by the estimators on test data
+            if a cross-validation strategy is used
 
-        Returns TODO
+        Returns
         -------
-        Tuple[NDArray, NDArray, NDArray]
-            - Predictions
-            - The multiple predictions for the lower bound of the intervals.
-            - The multiple predictions for the upper bound of the intervals.
+        NDArray
+            Predictions of shape
+            (n_samples, n_classes)
+
         """
         check_is_fitted(self, self.fit_attributes)
         alpha_np = cast(NDArray, alpha_np)

mapie/estimator/classification/interface.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from abc import ABCMeta, abstractmethod
-from typing import Any, Optional, Tuple, Union
+from typing import Any, Optional
 
 from sklearn.base import ClassifierMixin
 
@@ -40,7 +40,8 @@ def fit(
         y: ArrayLike of shape (n_samples,)
             Input labels.
 
-        # TODO document this
+        y_enc: ArrayLike
+            Target values as normalized encodings.
 
         sample_weight: Optional[ArrayLike] of shape (n_samples,)
             Sample weights. If None, then samples are equally weighted.
@@ -66,7 +67,7 @@ def predict(
         X: ArrayLike,
         alpha_np: ArrayLike = [],
         agg_scores: Any = None
-    ) -> Union[NDArray, Tuple[NDArray, NDArray, NDArray]]:
+    ) -> NDArray:
         """
         Predict target from X. It also computes the prediction per train sample
         for each test sample according to ``self.method``.
@@ -76,12 +77,16 @@ def predict(
         X: ArrayLike of shape (n_samples, n_features)
             Test data.
 
-        TODO
+        alpha_np: ArrayLike of shape (n_alphas)
+            Level of confidences.
 
-        Returns TODO
+        agg_scores: Optional[str]
+            How to aggregate the scores output by the estimators on test data
+            if a cross-validation strategy is used
+
+        Returns
         -------
-        Tuple[NDArray, NDArray, NDArray]
-            - Predictions
-            - The multiple predictions for the lower bound of the intervals.
-            - The multiple predictions for the upper bound of the intervals.
+        NDArray
+            Predictions of shape
+            (n_samples, n_classes)
         """