Merge branch 'dev' into angoho_CSDI_T

Author: Julien Roussel

.github/workflows/test.yml

@@ -41,3 +41,7 @@ jobs:
         run: |
           mypy qolmat
           echo you should uncomment mypy qolmat and delete this line
+      - name: Upload coverage reports to Codecov
+        uses: codecov/codecov-action@v3
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

MANIFEST.in

@@ -1,6 +1,6 @@
 .. -*- mode: rst -*-
 
-|GitHubActions|_ |ReadTheDocs|_ |License|_ |PythonVersion|_ |PyPi|_ |Release|_ |Commits|_
+|GitHubActions|_ |ReadTheDocs|_ |License|_ |PythonVersion|_ |PyPi|_ |Release|_ |Commits|_ |Codecov|_
 
 .. |GitHubActions| image:: https://github.com/Quantmetry/qolmat/actions/workflows/test.yml/badge.svg
 .. _GitHubActions: https://github.com/Quantmetry/qolmat/actions
@@ -23,6 +23,9 @@
 .. |Commits| image:: https://img.shields.io/github/commits-since/Quantmetry/qolmat/latest/main
 .. _Commits: https://github.com/Quantmetry/qolmat/commits/main
 
+.. |Codecov| image:: https://codecov.io/gh/quantmetry/qolmat/branch/master/graph/badge.svg
+.. _Codecov: https://codecov.io/gh/quantmetry/qolmat
+
 .. image:: https://raw.githubusercontent.com/Quantmetry/qolmat/main/docs/images/logo.png
     :align: center
 

README.rst

@@ -1,12 +1,14 @@
 name: env_qolmat_doc
 channels:
-    - defaults
     - conda-forge
+    - defaults
 dependencies:
     - numpydoc=1.1.0
     - python=3.8
     - sphinx=4.3.2
     - sphinx-gallery=0.10.1
     - sphinx_rtd_theme=1.0.0
-    - sphinx_markdown_tables==0.0.17
     - typing_extensions=4.0.1
+    - pip
+    - pip:
+      - sphinx-markdown-tables==0.0.17

environment.doc.yml

@@ -18,6 +18,7 @@
 
 from qolmat.imputations import em_sampler
 from qolmat.imputations.rpca import rpca, rpca_noisy, rpca_pcp
+from qolmat.imputations import softimpute
 from qolmat.utils.exceptions import NotDataFrame
 from qolmat.utils.utils import HyperValue
 
@@ -1772,6 +1773,120 @@ def _transform_element(
         return df_imputed
 
 
+class ImputerSoftImpute(_Imputer):
+    """_summary_
+
+    Parameters
+    ----------
+    """
+
+    def __init__(
+        self,
+        groups: Tuple[str, ...] = (),
+        columnwise: bool = False,
+        random_state: Union[None, int, np.random.RandomState] = None,
+        period: int = 1,
+        rank: int = 2,
+        tolerance: float = 1e-05,
+        tau: float = 0,
+        max_iterations: int = 100,
+        verbose: bool = False,
+        projected: bool = True,
+    ):
+        super().__init__(
+            imputer_params=(
+                "period",
+                "rank",
+                "tolerance",
+                "tau",
+                "max_iterations",
+                "verbose",
+                "projected",
+            ),
+            groups=groups,
+            columnwise=columnwise,
+            random_state=random_state,
+        )
+        self.period = period
+        self.rank = rank
+        self.tolerance = tolerance
+        self.tau = tau
+        self.max_iterations = max_iterations
+        self.verbose = verbose
+        self.projected = projected
+
+    def _fit_element(
+        self, df: pd.DataFrame, col: str = "__all__", ngroup: int = 0
+    ) -> softimpute.SoftImpute:
+        """
+        Fits the imputer on `df`, at the group and/or column level depending on
+        self.groups and self.columnwise.
+
+        Parameters
+        ----------
+        df : pd.DataFrame
+            Dataframe on which the imputer is fitted
+        col : str, optional
+            Column on which the imputer is fitted, by default "__all__"
+        ngroup : int, optional
+            Id of the group on which the method is applied
+
+        Returns
+        -------
+        Any
+            Return fitted SoftImpute model
+
+        Raises
+        ------
+        NotDataFrame
+            Input has to be a pandas.DataFrame.
+        """
+        self._check_dataframe(df)
+        assert col == "__all__"
+        hyperparams = self.get_hyperparams()
+        model = softimpute.SoftImpute(random_state=self._rng, **hyperparams)
+        model = model.fit(df.values)
+        return model
+
+    def _transform_element(
+        self, df: pd.DataFrame, col: str = "__all__", ngroup: int = 0
+    ) -> pd.DataFrame:
+        """
+        Transforms the fataframe `df`, at the group level depending on
+        self.groups
+
+        Parameters
+        ----------
+        df : pd.DataFrame
+            Dataframe or column to impute
+        col : str, optional
+            Column transformed by the imputer, by default "__all__"
+
+        Returns
+        -------
+        pd.DataFrame
+            Imputed dataframe
+
+        Raises
+        ------
+        NotDataFrame
+            Input has to be a pandas.DataFrame.
+        """
+        self._check_dataframe(df)
+        assert col == "__all__"
+        model = self._dict_fitting["__all__"][ngroup]
+        X_imputed = model.transform(df.values)
+        return pd.DataFrame(X_imputed, index=df.index, columns=df.columns)
+
+    def _more_tags(self):
+        return {
+            "_xfail_checks": {
+                "check_fit2d_1sample": "This test shouldn't be running at all!",
+                "check_fit2d_1feature": "This test shouldn't be running at all!",
+            },
+        }
+
+
 class ImputerEM(_Imputer):
     """
     This class implements an imputation method based on joint modelling and an inference using a
@@ -1874,7 +1989,7 @@ def get_model(self, **hyperparams) -> em_sampler.EM:
 
     def _fit_element(
         self, df: pd.DataFrame, col: str = "__all__", ngroup: int = 0
-    ) -> IterativeImputer:
+    ) -> em_sampler.EM:
         """
         Fits the imputer on `df`, at the group and/or column level depending onself.groups and
         self.columnwise.
@@ -1891,7 +2006,7 @@ def _fit_element(
         Returns
         -------
         Any
-            Return fitted KNN model
+            Return fitted EM model
 
         Raises
         ------