Integrate clusters into the DoubleMLData class, Refactor data generators

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -24,11 +24,10 @@ body:
       label: Minimum reproducible code snippet
       description: |
         Please provide a short reproducible code snippet. Example:
-
         ```python
         import numpy as np
         import doubleml as dml
-        from doubleml.datasets import make_plr_CCDDHNR2018
+        from doubleml.plm.datasets import make_plr_CCDDHNR2018
         from sklearn.ensemble import RandomForestRegressor
         from sklearn.base import clone
         np.random.seed(3141)

CONTRIBUTING.md

@@ -15,7 +15,7 @@ To submit a **bug report**, you can use our
 ```python
 import numpy as np
 import doubleml as dml
-from doubleml.datasets import make_plr_CCDDHNR2018
+from doubleml.plm.datasets import make_plr_CCDDHNR2018
 from sklearn.ensemble import RandomForestRegressor
 from sklearn.base import clone
 np.random.seed(3141)

doubleml/__init__.py

@@ -1,6 +1,6 @@
 import importlib.metadata
 
-from .data import DoubleMLClusterData, DoubleMLData
+from .data import DoubleMLClusterData, DoubleMLData, DoubleMLDIDData, DoubleMLPanelData, DoubleMLRDDData, DoubleMLSSMData
 from .did.did import DoubleMLDID
 from .did.did_cs import DoubleMLDIDCS
 from .double_ml_framework import DoubleMLFramework, concat
@@ -29,6 +29,10 @@
     "DoubleMLIIVM",
     "DoubleMLData",
     "DoubleMLClusterData",
+    "DoubleMLDIDData",
+    "DoubleMLPanelData",
+    "DoubleMLRDDData",
+    "DoubleMLSSMData",
     "DoubleMLDID",
     "DoubleMLDIDCS",
     "DoubleMLPQ",

doubleml/data/__init__.py

@@ -2,12 +2,78 @@
 The :mod:`doubleml.data` module implements data classes for double machine learning.
 """
 
+import warnings
+
 from .base_data import DoubleMLData
-from .cluster_data import DoubleMLClusterData
+from .did_data import DoubleMLDIDData
 from .panel_data import DoubleMLPanelData
+from .rdd_data import DoubleMLRDDData
+from .ssm_data import DoubleMLSSMData
+
+
+class DoubleMLClusterData(DoubleMLData):
+    """
+    Backwards compatibility wrapper for DoubleMLData with cluster_cols.
+    This class is deprecated and will be removed in a future version.
+    Use DoubleMLData with cluster_cols instead.
+    """
+
+    def __init__(
+        self,
+        data,
+        y_col,
+        d_cols,
+        cluster_cols,
+        x_cols=None,
+        z_cols=None,
+        t_col=None,
+        s_col=None,
+        use_other_treat_as_covariate=True,
+        force_all_x_finite=True,
+    ):
+        warnings.warn(
+            "DoubleMLClusterData is deprecated and will be removed with version 0.12.0. "
+            "Use DoubleMLData with cluster_cols instead.",
+            FutureWarning,
+            stacklevel=2,
+        )
+        super().__init__(
+            data=data,
+            y_col=y_col,
+            d_cols=d_cols,
+            x_cols=x_cols,
+            z_cols=z_cols,
+            cluster_cols=cluster_cols,
+            use_other_treat_as_covariate=use_other_treat_as_covariate,
+            force_all_x_finite=force_all_x_finite,
+            force_all_d_finite=True,
+        )
+
+    @classmethod
+    def from_arrays(
+        cls, x, y, d, cluster_vars, z=None, t=None, s=None, use_other_treat_as_covariate=True, force_all_x_finite=True
+    ):
+        """
+        Initialize :class:`DoubleMLClusterData` from :class:`numpy.ndarray`'s.
+        This method is deprecated and will be removed with version 0.12.0,
+        use DoubleMLData.from_arrays with cluster_vars instead.
+        """
+        warnings.warn(
+            "DoubleMLClusterData is deprecated and will be removed with version 0.12.0. "
+            "Use DoubleMLData.from_arrays with cluster_vars instead.",
+            FutureWarning,
+            stacklevel=2,
+        )
+        return DoubleMLData.from_arrays(
+            x=x,
+            y=y,
+            d=d,
+            z=z,
+            cluster_vars=cluster_vars,
+            use_other_treat_as_covariate=use_other_treat_as_covariate,
+            force_all_x_finite=force_all_x_finite,
+            force_all_d_finite=True,
+        )
+
 
-__all__ = [
-    "DoubleMLData",
-    "DoubleMLClusterData",
-    "DoubleMLPanelData",
-]
+__all__ = ["DoubleMLData", "DoubleMLClusterData", "DoubleMLDIDData", "DoubleMLPanelData", "DoubleMLRDDData", "DoubleMLSSMData"]