add median absolute error to metrics and fix missing kwargs in Defaul…

…tPipeline

examples/advanced/gpboost.py

@@ -0,0 +1,85 @@
+# pip install gpboost -U
+from sklearn.base import BaseEstimator, ClassifierMixin
+from sklearn.model_selection import GroupKFold, KFold
+from photonai.base import Hyperpipe, PipelineElement
+import numpy as np
+import pandas as pd
+import gpboost as gpb
+# from gpboost import GPBoostRegressor
+
+
+class GPBoostDataWrapper(BaseEstimator, ClassifierMixin):
+
+    def __init__(self):
+        self.needs_covariates = True
+        # self.gpmodel = gpb.GPModel(likelihood="gaussian")
+        self.gpboost = None
+
+
+    def fit(self, X, y, **kwargs):
+        self.gpboost = gpb.GPBoostRegressor()
+        if "clusters" in kwargs:
+            clst = pd.Series(kwargs["clusters"])
+            gpmodel = gpb.GPModel(likelihood="gaussian", group_data=clst)
+            self.gpboost.fit(X, y, gp_model=gpmodel)
+        else:
+            raise NotImplementedError("GPBoost needs clusters")
+        return self
+
+    def predict(self, X, **kwargs):
+        clst = pd.Series(kwargs["clusters"])
+        preds = self.gpboost.predict(X, group_data_pred=clst)
+        preds = preds["response_mean"]
+        return preds
+
+    def save(self):
+        return None
+
+
+def get_gpboost_pipe(pipe_name, project_folder, split="group"):
+
+    if split == "group":
+        outercv = GroupKFold(n_splits=10)
+    else:
+        outercv = KFold(n_splits=10)
+
+    my_pipe = Hyperpipe(pipe_name,
+                        optimizer='grid_search',
+                        metrics=['mean_absolute_error', 'mean_squared_error',
+                                 'spearman_correlation', 'pearson_correlation'],
+                        best_config_metric='mean_absolute_error',
+                        outer_cv=outercv,
+                        inner_cv=KFold(n_splits=10),
+                        calculate_metrics_across_folds=True,
+                        use_test_set=True,
+                        verbosity=1,
+                        project_folder=project_folder)
+
+    # Add transformer elements
+    my_pipe += PipelineElement("StandardScaler", hyperparameters={},
+                               test_disabled=True, with_mean=True, with_std=True)
+
+    my_pipe += PipelineElement.create("GPBoost", GPBoostDataWrapper(), hyperparameters={})
+
+    return my_pipe
+
+
+def get_mock_data():
+
+    X = np.random.randint(10, size=(200, 9))
+    y = np.sum(X, axis=1)
+    clst = np.random.randint(10, size=200)
+
+    return X, y, clst
+
+
+if __name__ == '__main__':
+
+
+    X, y, clst = get_mock_data()
+
+    # define project folder
+    project_folder = "/tmp/gpboost_debug"
+
+    my_pipe = get_gpboost_pipe("Test_gpboost", project_folder, split="random")
+    my_pipe.fit(X, y, clusters=clst)

examples/basic/classification_custom.py

@@ -5,7 +5,7 @@
 my_pipe = Hyperpipe('basic_svm_pipe',
                     inner_cv=KFold(n_splits=5),
                     outer_cv=KFold(n_splits=3),
-                    optimizer='sk_opt',
+                    optimizer='random_grid_search',
                     optimizer_params={'n_configurations': 15},
                     metrics=['accuracy', 'precision', 'recall', 'balanced_accuracy'],
                     best_config_metric='accuracy',

examples/basic/regression.py

@@ -2,6 +2,7 @@
 from photonai import RegressionPipe
 
 my_pipe = RegressionPipe('diabetes',
+                         best_config_metric='median_absolute_error',
                          add_default_pipeline_elements=True,
                          scaling=True,
                          imputation=False,

photonai/base/model_zoo.py

@@ -217,7 +217,7 @@ def set_default_pipeline(self, scaling, imputation, imputation_nan_value, featur
                     logger.photon_system_log("---")
         logger.stars()
 
-    def fit(self, X=None, y=None):
+    def fit(self, X=None, y=None, **kwargs):
         if (X is not None and self.X_csv_path is not None) or (y is not None and self.y_csv_path is not None):
             raise ValueError("You can either give the fit function data or the pipe definition paths "
                              "to csv files to load data from. Not both.")
@@ -228,7 +228,7 @@ def fit(self, X=None, y=None):
 
         X = X if X is not None else pd.read_csv(self.X_csv_path, delimiter=self.delimiter)
         y = y if y is not None else pd.read_csv(self.y_csv_path, delimiter=self.delimiter)
-        super().fit(X, y)
+        super().fit(X, y, **kwargs)
 
 
 class ClassificationPipe(DefaultPipeline):

photonai/processing/metrics.py

@@ -37,6 +37,7 @@ class Scorer:
         # Regression
         'mean_squared_error': ('sklearn.metrics', 'mean_squared_error', 'error'),
         'mean_absolute_error': ('sklearn.metrics', 'mean_absolute_error', 'error'),
+        'median_absolute_error': ('sklearn.metrics', 'median_absolute_error', 'error'),
         'explained_variance': ('sklearn.metrics', 'explained_variance_score', 'score'),
         'r2': ('sklearn.metrics', 'r2_score', 'score'),
         'pearson_correlation': ('photonai.processing.metrics', 'pearson_correlation', 'score'),