hotfixes

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_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

@@ -7,7 +7,6 @@ from typing import Optional, Dict, List
 import pandas as pd
 
 from core.config import PipelineConfig, get_config
-
 from research.experiment import ExperimentConfig, ExperimentStatus
 from research.experiment.experiement_result import ExperimentResult
 
@@ -78,10 +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())
@@ -98,7 +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()
@@ -160,8 +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/neural_network_model.py

@@ -83,7 +83,7 @@ class NeuralNetworkModel(BaseModel):
         return self
 
     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)
@@ -140,7 +140,7 @@ 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

@@ -93,7 +93,7 @@ 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__}")