More tutorials, bugfixing (#30)

* cleanup

* bump version

* cleanup

* cleanup

* cleanup

* improvements

* debug

* bugfixing

* debug

* debug

Author: bcebere

src/hyperimpute/plugins/core/base_plugin.py

@@ -38,6 +38,8 @@ class Plugin(Serializable, metaclass=ABCMeta):
     def __init__(self) -> None:
         super().__init__()
 
+        self.drop_consts = []
+
     @staticmethod
     @abstractmethod
     def hyperparameter_space(*args: Any, **kwargs: Any) -> List[Params]:
@@ -119,6 +121,13 @@ def fit_predict(self, X: pd.DataFrame, *args: Any, **kwargs: Any) -> pd.DataFram
 
     def fit(self, X: pd.DataFrame, *args: Any, **kwargs: Any) -> Any:
         X = cast.to_dataframe(X)
+
+        for col in X.columns:
+            if len(X.loc[X[col].notna(), col].unique()) <= 1:
+                self.drop_consts.append(col)
+
+        X = X.drop(columns=self.drop_consts)
+        self.columns = X.columns
         return self._fit(X, *args, **kwargs)
 
     @abstractmethod
@@ -127,6 +136,7 @@ def _fit(self, X: pd.DataFrame, *args: Any, **kwargs: Any) -> "Plugin":
 
     def transform(self, X: pd.DataFrame) -> pd.DataFrame:
         X = cast.to_dataframe(X)
+        X = X.drop(columns=self.drop_consts)
         return pd.DataFrame(self._transform(X))
 
     @abstractmethod
@@ -135,6 +145,7 @@ def _transform(self, X: pd.DataFrame) -> pd.DataFrame:
 
     def predict(self, X: pd.DataFrame, *args: Any, **kwargs: Any) -> pd.DataFrame:
         X = cast.to_dataframe(X)
+        X = X.drop(columns=self.drop_consts)
         return pd.DataFrame(self._predict(X, *args, *kwargs))
 
     @abstractmethod

src/hyperimpute/plugins/imputers/base.py

@@ -7,6 +7,7 @@
 
 # hyperimpute absolute
 import hyperimpute.plugins.core.base_plugin as plugin
+from hyperimpute.utils.distributions import enable_reproducible_results
 
 
 class ImputerPlugin(_BaseImputer, plugin.Plugin):
@@ -24,8 +25,10 @@ class ImputerPlugin(_BaseImputer, plugin.Plugin):
     """
 
     def __init__(self, random_state: int = 0) -> None:
-        super().__init__()
+        _BaseImputer.__init__(self)
+        plugin.Plugin.__init__(self)
 
+        enable_reproducible_results(random_state)
         self.random_state = random_state
 
     @staticmethod

src/hyperimpute/plugins/prediction/classifiers/base.py

@@ -9,6 +9,7 @@
 import hyperimpute.plugins.core.base_plugin as plugin
 import hyperimpute.plugins.prediction.base as prediction_base
 import hyperimpute.plugins.utils.cast as cast
+from hyperimpute.utils.distributions import enable_reproducible_results
 from hyperimpute.utils.tester import Eval
 
 
@@ -26,17 +27,23 @@ class ClassifierPlugin(
     If any method implementation is missing, the class constructor will fail.
     """
 
-    def __init__(self, **kwargs: Any) -> None:
+    def __init__(self, random_state: int = 0, **kwargs: Any) -> None:
         self.args = kwargs
+        self.random_state = random_state
 
-        super().__init__()
+        enable_reproducible_results(self.random_state)
+
+        ClassifierMixin.__init__(self)
+        BaseEstimator.__init__(self)
+        prediction_base.PredictionPlugin.__init__(self)
 
     @staticmethod
     def subtype() -> str:
         return "classifier"
 
     def fit(self, X: pd.DataFrame, *args: Any, **kwargs: Any) -> plugin.Plugin:
         X = cast.to_dataframe(X)
+        enable_reproducible_results(self.random_state)
 
         if len(args) == 0:
             raise RuntimeError("Please provide the training labels as well")

src/hyperimpute/plugins/prediction/classifiers/plugin_catboost.py

@@ -54,7 +54,7 @@ def __init__(
         random_strength: float = 1,
         **kwargs: Any
     ) -> None:
-        super().__init__(**kwargs)
+        super().__init__(random_state=random_state, **kwargs)
         if model is not None:
             self.model = model
             return

src/hyperimpute/plugins/prediction/classifiers/plugin_gpboost.py

@@ -65,7 +65,7 @@ def __init__(
         hyperparam_search_iterations: Optional[int] = None,
         **kwargs: Any
     ) -> None:
-        super().__init__(**kwargs)
+        super().__init__(random_state=random_state, **kwargs)
         if hyperparam_search_iterations:
             n_estimators = int(hyperparam_search_iterations)
 

src/hyperimpute/plugins/prediction/classifiers/plugin_kneighbors.py

@@ -36,7 +36,7 @@ def __init__(
         model: Any = None,
         **kwargs: Any
     ) -> None:
-        super().__init__(**kwargs)
+        super().__init__(random_state=random_state, **kwargs)
         if model is not None:
             self.model = model
             return

src/hyperimpute/plugins/prediction/classifiers/plugin_lgbm.py

@@ -65,7 +65,7 @@ def __init__(
         random_state: int = 0,
         **kwargs: Any
     ) -> None:
-        super().__init__(**kwargs)
+        super().__init__(random_state=random_state, **kwargs)
         if model is not None:
             self.model = model
             return

src/hyperimpute/plugins/prediction/classifiers/plugin_logistic_regression.py

@@ -53,7 +53,7 @@ def __init__(
         hyperparam_search_iterations: Optional[int] = None,
         **kwargs: Any
     ) -> None:
-        super().__init__(**kwargs)
+        super().__init__(random_state=random_state, **kwargs)
         if model is not None:
             self.model = model
             return

src/hyperimpute/plugins/prediction/classifiers/plugin_neural_nets.py

@@ -251,7 +251,7 @@ def __init__(
         hyperparam_search_iterations: Optional[int] = None,
         **kwargs: Any,
     ) -> None:
-        super().__init__(**kwargs)
+        super().__init__(random_state=random_state, **kwargs)
 
         enable_reproducible_results(random_state)
 

src/hyperimpute/plugins/prediction/classifiers/plugin_random_forest.py

@@ -56,7 +56,7 @@ def __init__(
         hyperparam_search_iterations: Optional[int] = None,
         **kwargs: Any
     ) -> None:
-        super().__init__(**kwargs)
+        super().__init__(random_state=random_state, **kwargs)
         if hyperparam_search_iterations:
             n_estimators = int(hyperparam_search_iterations)