add predict_proba functionality

Author: diegomarvid

ml_garden/core/data_container.py

@@ -6,7 +6,7 @@
 import logging
 import os
 import sys
-from typing import Any, Optional, Union
+from typing import Any, Dict, Optional, Union
 
 import dill as pickle
 import pandas as pd
@@ -675,6 +675,32 @@ def predictions(self, value: pd.Series):
         """
         self["predictions"] = value
 
+    @property
+    def predict_proba(self) -> pd.DataFrame:
+        """
+        Get the prediction probabilities from the DataContainer.
+
+        Returns
+        -------
+        pd.DataFrame
+            The prediction probabilities stored in the DataContainer.
+            For binary and multiclass classification, returns a DataFrame with a column for each class.
+        """
+        return self["predict_proba"]
+
+    @predict_proba.setter
+    def predict_proba(self, value: pd.DataFrame):
+        """
+        Set the prediction probabilities in the DataContainer.
+
+        Parameters
+        ----------
+        value : pd.DataFrame
+            The prediction probabilities to be stored in the DataContainer.
+            Should be a DataFrame with a column for each class.
+        """
+        self["predict_proba"] = value
+
     @property
     def explainer(self) -> BaseExplainer:
         """

ml_garden/core/model.py

@@ -24,3 +24,19 @@ def fit(
     @abstractmethod
     def predict(self, X: pd.DataFrame) -> pd.Series:
         """Abstract method for making predictions."""
+
+    def predict_proba(self, X: pd.DataFrame) -> pd.DataFrame:
+        """
+        Predict class probabilities with the trained model.
+
+        Parameters
+        ----------
+        X : pd.DataFrame
+            Features to make probability predictions on.
+
+        Returns
+        -------
+        pd.DataFrame
+            Predicted class probabilities for the input features.
+        """
+        pass

ml_garden/core/steps/fit_model.py

@@ -4,6 +4,7 @@
 
 import numpy as np
 import optuna
+import pandas as pd
 from sklearn.metrics import (
     accuracy_score,
     f1_score,
@@ -300,4 +301,14 @@ def predict(self, data: DataContainer) -> DataContainer:
         self.logger.info(f"Predicting with {self.model_class.__name__} model")
         data.flow[data.prediction_column] = data.model.predict(data.X_prediction)
         data.predictions = data.flow[data.prediction_column]
+
+        # If the task is classification, also get the prediction probabilities
+        if data.task == Task.CLASSIFICATION:
+            proba_df = data.model.predict_proba(data.X_prediction)
+            proba_df.columns = [f"proba_{col}" for col in proba_df.columns]
+
+            # Concatenate the probabilities DataFrame with the existing DataFrame
+            data.flow = pd.concat([data.flow, proba_df], axis=1)
+            data.predict_proba = proba_df
+
         return data

ml_garden/implementation/tabular/autogluon/model.py

@@ -33,4 +33,10 @@ def fit(self, X: pd.DataFrame, y: pd.Series, eval_set=None, verbose=True) -> Non
 
     def predict(self, X: pd.DataFrame) -> pd.Series:
         predictions = self.model.predict(X)
-        return predictions
+        return pd.Series(predictions, index=X.index)
+
+    def predict_proba(self, X: pd.DataFrame) -> pd.DataFrame:
+        if self.model.problem_type == "regression":
+            raise ValueError("predict_proba is not available for regression tasks.")
+        probabilities = self.model.predict_proba(X)
+        return pd.DataFrame(probabilities, index=X.index)

ml_garden/implementation/tabular/xgboost/model.py

@@ -1,4 +1,5 @@
 import logging
+from typing import List
 
 import pandas as pd
 import xgboost as xgb
@@ -75,4 +76,5 @@ def predict_proba(self, X: pd.DataFrame) -> pd.DataFrame:
         pd.DataFrame
             Predicted class probabilities for the input features.
         """
-        return self.model.predict_proba(X)
+        proba = self.model.predict_proba(X)
+        return pd.DataFrame(proba, columns=self.model.classes_)