feat: add osm data

research/base_model.py

@@ -41,14 +41,14 @@ class BaseModel(ABC):
 
     @abstractmethod
     def cross_validate(
-            self, X: pd.DataFrame, y: pd.Series, cv_folds: int = 5
+        self, X: pd.DataFrame, y: pd.Series, cv_folds: int = 5
     ) -> Dict[str, float] | dict[str, np.floating[Any]]:
         """Perform cross-validation and return average scores"""
         pass
 
     @abstractmethod
     def generate_learning_curve(
-            self, X: pd.DataFrame, y: pd.Series, train_sizes: List[float] = None
+        self, X: pd.DataFrame, y: pd.Series, train_sizes: List[float] = None
     ) -> Dict[str, Any]:
         """Generate learning curve data for the model"""
         pass

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:

research/model_trainer.py

@@ -27,13 +27,13 @@ class ModelTrainer:
         self.models_dir.mkdir(parents=True, exist_ok=True)
 
     def train_single_model(
-            self,
-            model_name: str,
-            model_type: str = "logistic_regression",
-            features: List[str] = None,
-            model_params: Dict[str, Any] = None,
-            tags: List[str] = None,
-            save_artifacts: bool = True,
+        self,
+        model_name: str,
+        model_type: str = "logistic_regression",
+        features: List[str] = None,
+        model_params: Dict[str, Any] = None,
+        tags: List[str] = None,
+        save_artifacts: bool = True,
     ) -> str:
         """
         Train a single model and save its artifacts.
@@ -75,7 +75,7 @@ class ModelTrainer:
         return experiment_id
 
     def train_multiple_models(
-            self, base_name: str, model_configs: List[Dict[str, Any]], save_all: bool = True
+        self, base_name: str, model_configs: List[Dict[str, Any]], save_all: bool = True
     ) -> List[str]:
         """
         Train multiple models with different configurations.

research/models/ensemble_model.py

@@ -82,7 +82,9 @@ class EnsembleModel(TraditionalModel):
         # Soft voting averages probabilities (preferred when members are calibrated);
         # hard voting uses majority class. Parallelize member predictions.
         voting_type = params.get("voting", "soft")  # 'hard' or 'soft'
-        return VotingClassifier(estimators=estimators, voting=voting_type, n_jobs=params.get("n_jobs", -1))
+        return VotingClassifier(
+            estimators=estimators, voting=voting_type, n_jobs=params.get("n_jobs", -1)
+        )
 
     def prepare_features(self, X: pd.DataFrame) -> np.ndarray:
         text_features = []

research/models/random_forest_model.py

@@ -55,7 +55,9 @@ class RandomForestModel(TraditionalModel):
                         encoder = self.label_encoders[feature_key]
                         column_clean = column.fillna("unknown").astype(str)
                         known_classes = set(encoder.classes_)
-                        default_class = "unknown" if "unknown" in known_classes else encoder.classes_[0]
+                        default_class = (
+                            "unknown" if "unknown" in known_classes else encoder.classes_[0]
+                        )
                         column_mapped = column_clean.apply(
                             lambda value: value if value in known_classes else default_class
                         )

research/models/transformer_model.py

@@ -36,9 +36,9 @@ class TransformerModel(NeuralNetworkModel):
 
         # Add positional encoding
         positions = tf.range(start=0, limit=params.get("max_len", 8), delta=1)
-        pos_embedding = Embedding(input_dim=params.get("max_len", 8), output_dim=params.get("embedding_dim", 64))(
-            positions
-        )
+        pos_embedding = Embedding(
+            input_dim=params.get("max_len", 8), output_dim=params.get("embedding_dim", 64)
+        )(positions)
         x = x + pos_embedding
 
         x = self._transformer_encoder(x, params)

research/neural_network_model.py

@@ -84,7 +84,9 @@ class NeuralNetworkModel(BaseModel):
     def _collect_text_corpus(self, X: pd.DataFrame) -> List[str]:
         """Combine configured textual features into one string per record."""
 
-        column_names = [feature.value for feature in self.config.features if feature.value in X.columns]
+        column_names = [
+            feature.value for feature in self.config.features if feature.value in X.columns
+        ]
         if not column_names:
             raise ValueError("No configured text features found in the provided DataFrame.")
 
@@ -101,7 +103,7 @@ class NeuralNetworkModel(BaseModel):
         return combined_rows
 
     def cross_validate(
-            self, X: pd.DataFrame, y: pd.Series, cv_folds: int = 5
+        self, X: pd.DataFrame, y: pd.Series, cv_folds: int = 5
     ) -> dict[str, np.floating[Any]]:
         features_df = self.feature_extractor.extract_features(X)
         X_prepared = self.prepare_features(features_df)
@@ -158,7 +160,7 @@ class NeuralNetworkModel(BaseModel):
         }
 
     def generate_learning_curve(
-            self, X: pd.DataFrame, y: pd.Series, train_sizes: List[float] = None
+        self, X: pd.DataFrame, y: pd.Series, train_sizes: List[float] = None
     ) -> Dict[str, Any]:
         """Generate learning curve data for the model"""
         logging.info(f"Generating learning curve for {self.__class__.__name__}")

research/traditional_model.py

@@ -103,7 +103,7 @@ class TraditionalModel(BaseModel):
         return results
 
     def generate_learning_curve(
-            self, X: pd.DataFrame, y: pd.Series, train_sizes: List[float] = None
+        self, X: pd.DataFrame, y: pd.Series, train_sizes: List[float] = None
     ) -> Dict[str, Any]:
         """Generate learning curve data for the model"""
         logging.info(f"Generating learning curve for {self.__class__.__name__}")