Merge pull request #196 from DoubleML/s-inc-dev

Remove changed api decorators

Author: SvenKlaassen

README.md

@@ -20,8 +20,7 @@ The R package is also available on [GitHub](https://github.com/DoubleML/doubleml
 Documentation and website: [https://docs.doubleml.org/](https://docs.doubleml.org/)
 
 **DoubleML** is currently maintained by
-[@MalteKurz](https://github.com/MalteKurz) and
-[@PhilippBach](https://github.com/PhilippBach).
+[@MalteKurz](https://github.com/MalteKurz), [@PhilippBach](https://github.com/PhilippBach) and [@SvenKlaassen](https://github.com/SvenKlaassen).
 
 Bugs can be reported to the issue tracker at
 [https://github.com/DoubleML/doubleml-for-py/issues](https://github.com/DoubleML/doubleml-for-py/issues).

doubleml/double_ml_blp.py

@@ -7,7 +7,7 @@
 
 
 class DoubleMLBLP:
-    """Best linear predictor (BLP) for DoubleML with orthogonal signals.
+    """Best linear predictor (BLP) for DoubleML with orthogonal signals. Mainly used for CATE and GATE estimation for IRM models.
 
         Parameters
         ----------
@@ -110,7 +110,7 @@ def summary(self):
 
     def fit(self):
         """
-        Estimate DoubleML models.
+        Estimate DoubleMLBLP models.
 
         Returns
         -------

doubleml/double_ml_cvar.py

@@ -79,16 +79,16 @@ class DoubleMLCVAR(LinearScoreMixin, DoubleML):
     >>> import numpy as np
     >>> import doubleml as dml
     >>> from doubleml.datasets import make_irm_data
-    >>> from sklearn.ensemble import RandomForestClassifier
+    >>> from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor
     >>> np.random.seed(3141)
-    >>> ml_g = RandomForestClassifier(n_estimators=100, max_features=20, max_depth=10, min_samples_leaf=2)
+    >>> ml_g = RandomForestRegressor(n_estimators=100, max_features=20, max_depth=10, min_samples_leaf=2)
     >>> ml_m = RandomForestClassifier(n_estimators=100, max_features=20, max_depth=10, min_samples_leaf=2)
     >>> data = make_irm_data(theta=0.5, n_obs=500, dim_x=20, return_type='DataFrame')
     >>> obj_dml_data = dml.DoubleMLData(data, 'y', 'd')
     >>> dml_cvar_obj = dml.DoubleMLCVAR(obj_dml_data, ml_g, ml_m, treatment=1, quantile=0.5)
     >>> dml_cvar_obj.fit().summary
-           coef   std err          t         P>|t|     2.5 %   97.5 %
-    d  1.462533  0.075714  19.316536  3.899567e-83  1.314136  1.61093
+           coef   std err          t         P>|t|     2.5 %    97.5 %
+    d  1.591441  0.095781  16.615498  5.382582e-62  1.403715  1.779167
     """
 
     def __init__(self,

doubleml/double_ml_irm.py

@@ -402,7 +402,7 @@ def gate(self, groups):
         groups : :class:`pandas.DataFrame`
             The group indicator for estimating the best linear predictor.
             Has to be dummy coded with shape ``(n_obs, d)``, where ``n_obs`` is the number of observations
-            and ``d`` is the number of groups or ``(n_obs, 1)`` and contain the corresponding groups.
+            and ``d`` is the number of groups or ``(n_obs, 1)`` and contain the corresponding groups (as str).
 
         Returns
         -------

doubleml/double_ml_pliv.py

@@ -6,30 +6,13 @@
 from sklearn.dummy import DummyRegressor
 
 import warnings
-from functools import wraps
 
 from .double_ml import DoubleML
 from .double_ml_data import DoubleMLData
 from .double_ml_score_mixins import LinearScoreMixin
 from ._utils import _dml_cv_predict, _dml_tune, _check_finite_predictions
 
 
-# To be removed in version 0.6.0
-def changed_api_decorator(f):
-    @wraps(f)
-    def wrapper(*args, **kwds):
-        ml_l_missing = (len(set(kwds).intersection({'obj_dml_data', 'ml_l', 'ml_m', 'ml_r'})) + len(args)) < 5
-        if ml_l_missing & ('ml_g' in kwds):
-            warnings.warn(("The required positional argument ml_g was renamed to ml_l. "
-                          "Please adapt the argument name accordingly. "
-                           "ml_g is redirected to ml_l. "
-                           "The redirection will be removed in a future version."),
-                          DeprecationWarning, stacklevel=2)
-            kwds['ml_l'] = kwds.pop('ml_g')
-        return f(*args, **kwds)
-    return wrapper
-
-
 class DoubleMLPLIV(LinearScoreMixin, DoubleML):
     """Double machine learning for partially linear IV regression models
 
@@ -117,7 +100,7 @@ class DoubleMLPLIV(LinearScoreMixin, DoubleML):
     :math:`X = (X_1, \\ldots, X_p)` consists of other confounding covariates, and :math:`\\zeta` and
     :math:`V` are stochastic errors.
     """
-    @changed_api_decorator
+
     def __init__(self,
                  obj_dml_data,
                  ml_l,

doubleml/double_ml_plr.py

@@ -4,30 +4,13 @@
 from sklearn.base import clone
 
 import warnings
-from functools import wraps
 
 from .double_ml import DoubleML
 from .double_ml_data import DoubleMLData
 from .double_ml_score_mixins import LinearScoreMixin
 from ._utils import _dml_cv_predict, _dml_tune, _check_finite_predictions, _check_is_propensity
 
 
-# To be removed in version 0.6.0
-def changed_api_decorator(f):
-    @wraps(f)
-    def wrapper(*args, **kwds):
-        ml_l_missing = (len(set(kwds).intersection({'obj_dml_data', 'ml_l', 'ml_m'})) + len(args)) < 4
-        if ml_l_missing & ('ml_g' in kwds):
-            warnings.warn(("The required positional argument ml_g was renamed to ml_l. "
-                          "Please adapt the argument name accordingly. "
-                           "ml_g is redirected to ml_l. "
-                           "The redirection will be removed in a future version."),
-                          DeprecationWarning, stacklevel=2)
-            kwds['ml_l'] = kwds.pop('ml_g')
-        return f(*args, **kwds)
-    return wrapper
-
-
 class DoubleMLPLR(LinearScoreMixin, DoubleML):
     """Double machine learning for partially linear regression models
 
@@ -110,7 +93,7 @@ class DoubleMLPLR(LinearScoreMixin, DoubleML):
     The high-dimensional vector :math:`X = (X_1, \\ldots, X_p)` consists of other confounding covariates,
     and :math:`\\zeta` and :math:`V` are stochastic errors.
     """
-    @changed_api_decorator
+
     def __init__(self,
                  obj_dml_data,
                  ml_l,

doubleml/double_ml_pq.py

@@ -24,7 +24,7 @@ class DoubleMLPQ(NonLinearScoreMixin, DoubleML):
     ml_g : classifier implementing ``fit()`` and ``predict()``
         A machine learner implementing ``fit()`` and ``predict_proba()`` methods (e.g.
         :py:class:`sklearn.ensemble.RandomForestClassifier`) for the nuisance function
-         :math:`g_0(X) = E[Y <= \\theta | X, D=d]` .
+        :math:`g_0(X) = E[Y <= \\theta | X, D=d]` .
 
     ml_m : classifier implementing ``fit()`` and ``predict_proba()``
         A machine learner implementing ``fit()`` and ``predict_proba()`` methods (e.g.

doubleml/tests/test_doubleml_exceptions.py

@@ -715,10 +715,6 @@ def test_doubleml_exception_learner():
     with pytest.raises(ValueError, match=msg):
         _ = DoubleMLPLR(dml_data, Lasso(), LogisticRegression())
 
-    msg = 'ml_g was renamed to ml_l'
-    with pytest.warns(DeprecationWarning, match=msg):
-        _ = DoubleMLPLR(dml_data, ml_g=Lasso(), ml_m=ml_m)  # pylint: disable=no-value-for-parameter
-
     msg = r"For score = 'IV-type', learners ml_l and ml_g should be specified. Set ml_g = clone\(ml_l\)."
     with pytest.warns(UserWarning, match=msg):
         _ = DoubleMLPLR(dml_data, ml_l=Lasso(), ml_m=ml_m, score='IV-type')
@@ -727,10 +723,6 @@ def test_doubleml_exception_learner():
     with pytest.warns(UserWarning, match=msg):
         _ = DoubleMLPLR(dml_data, ml_l=Lasso(), ml_m=Lasso(), ml_g=Lasso(), score='partialling out')
 
-    msg = 'ml_g was renamed to ml_l'
-    with pytest.warns(DeprecationWarning, match=msg):
-        _ = DoubleMLPLIV(dml_data_pliv, ml_g=Lasso(), ml_m=ml_m, ml_r=ml_r)  # pylint: disable=no-value-for-parameter
-
     msg = "For score = 'IV-type', learners ml_l, ml_m, ml_r and ml_g need to be specified."
     with pytest.raises(ValueError, match=msg):
         _ = DoubleMLPLIV(dml_data_pliv, ml_l=ml_l, ml_m=ml_m, ml_r=ml_r,