feat: add osm data

research/experiment/experiment_builder.py

@@ -55,11 +55,11 @@ class ExperimentBuilder:
             # Check if this is the experiment we're looking for
             # Look for experiments that match the model type or contain the name
             if (
-                    experiment.get("model_type") == name
-                    or name.lower() in experiment.get("name", "").lower()
-                    or experiment.get("name") == name
-                    or f"baseline_{name}" == experiment.get("name")
-                    or f"advanced_{name}" == experiment.get("name")
+                experiment.get("model_type") == name
+                or name.lower() in experiment.get("name", "").lower()
+                or experiment.get("name") == name
+                or f"baseline_{name}" == experiment.get("name")
+                or f"advanced_{name}" == experiment.get("name")
             ):
                 return experiment
 
@@ -72,7 +72,9 @@ class ExperimentBuilder:
             f"Available experiments: {available_experiments}"
         )
 
-    def get_templates(self, templates_path: str = "research_templates.yaml") -> Dict[str, List[Dict]]:
+    def get_templates(
+        self, templates_path: str = "research_templates.yaml"
+    ) -> Dict[str, List[Dict]]:
         """Get all available experiments from templates organized by type"""
         templates = self.load_templates(templates_path)
 
@@ -80,7 +82,7 @@ class ExperimentBuilder:
             "baseline": templates.get("baseline_experiments", []),
             "advanced": templates.get("advanced_experiments", []),
             "feature_study": templates.get("feature_studies", []),
-            "tuning": templates.get("hyperparameter_tuning", [])
+            "tuning": templates.get("hyperparameter_tuning", []),
         }
 
     @classmethod
@@ -104,5 +106,5 @@ class ExperimentBuilder:
             tags=template_config.get("tags", []),
             test_size=template_config.get("test_size", 0.2),
             cross_validation_folds=template_config.get("cross_validation_folds", 5),
-            train_data_filter=template_config.get("train_data_filter")
+            train_data_filter=template_config.get("train_data_filter"),
         )

research/experiment/experiment_runner.py

@@ -158,12 +158,12 @@ class ExperimentRunner:
 
     @classmethod
     def _create_prediction_examples(
-            cls,
-            X_test: pd.DataFrame,
-            y_test: pd.Series,
-            predictions: np.ndarray,
-            model: BaseModel,
-            n_examples: int = 10,
+        cls,
+        X_test: pd.DataFrame,
+        y_test: pd.Series,
+        predictions: np.ndarray,
+        model: BaseModel,
+        n_examples: int = 10,
     ) -> List[Dict]:
         """Create prediction examples for analysis"""
         examples = []
@@ -237,7 +237,7 @@ class ExperimentRunner:
         return None
 
     def compare_experiments(
-            self, experiment_ids: List[str], metric: str = "accuracy"
+        self, experiment_ids: List[str], metric: str = "accuracy"
     ) -> pd.DataFrame:
         """Compare experiments and return analysis"""
         comparison_df = self.tracker.compare_experiments(experiment_ids)

research/experiment/experiment_tracker.py

@@ -77,10 +77,10 @@ class ExperimentTracker:
         return self._results.get(experiment_id)
 
     def list_experiments(
-            self,
-            status: Optional[ExperimentStatus] = None,
-            tags: Optional[List[str]] = None,
-            model_type: Optional[str] = None,
+        self,
+        status: Optional[ExperimentStatus] = None,
+        tags: Optional[List[str]] = None,
+        model_type: Optional[str] = None,
     ) -> List[ExperimentResult]:
         """List experiments with optional filtering"""
         results = list(self._results.values())
@@ -97,7 +97,7 @@ class ExperimentTracker:
         return sorted(results, key=lambda x: x.start_time, reverse=True)
 
     def get_best_experiment(
-            self, metric: str = "accuracy", dataset: str = "test", filters: Optional[Dict] = None
+        self, metric: str = "accuracy", dataset: str = "test", filters: Optional[Dict] = None
     ) -> Optional[ExperimentResult]:
         """Get the best experiment based on a metric"""
         experiments = self.list_experiments()
@@ -159,8 +159,8 @@ class ExperimentTracker:
         """Export all results to CSV"""
         if output_path is None:
             output_path = (
-                    self.experiments_dir
-                    / f"experiments_export_{datetime.now().strftime('%Y%m%d_%H%M%S')}.csv"
+                self.experiments_dir
+                / f"experiments_export_{datetime.now().strftime('%Y%m%d_%H%M%S')}.csv"
             )
 
         rows = []

research/experiment/feature_extractor.py

@@ -43,7 +43,7 @@ class FeatureExtractor:
         return features_df
 
     def _extract_single_feature(
-            self, df: pd.DataFrame, feature_type: FeatureType
+        self, df: pd.DataFrame, feature_type: FeatureType
     ) -> Union[pd.Series, pd.DataFrame]:
         """Extract a single type of feature"""
         if feature_type == FeatureType.FULL_NAME: