hotfixes

processing/ner/ner_data_builder.py

@@ -9,7 +9,6 @@ from spacy.tokens import DocBin
 from spacy.util import filter_spans
 
 from core.config import PipelineConfig
-from core.utils import get_data_file_path
 from core.utils.data_loader import DataLoader
 
 
@@ -98,10 +97,8 @@ class NERDataBuilder:
         return docs
 
     def build(self) -> int:
-        input_filepath = get_data_file_path(
-            self.config.data.output_files["engineered"], self.config
-        )
-        df = self.data_loader.load_csv_complete(input_filepath)
+        filepath = self.config.paths.get_data_path(self.config.data.output_files["engineered"])
+        df = self.data_loader.load_csv_complete(filepath)
         df = df[["name", "ner_tagged", "ner_entities"]]
 
         # Filter early
@@ -139,8 +136,8 @@ class NERDataBuilder:
         doc_bin = DocBin(docs=docs)
 
         # Save
-        json_path = Path(self.config.paths.data_dir) / self.config.data.output_files["ner_data"]
-        spacy_path = Path(self.config.paths.data_dir) / self.config.data.output_files["ner_spacy"]
+        json_path = self.config.paths.get_data_path(self.config.data.output_files["ner_data"])
+        spacy_path = self.config.paths.get_data_path(self.config.data.output_files["ner_spacy"])
 
         with open(json_path, "w", encoding="utf-8") as f:
             json.dump(training_data, f, ensure_ascii=False, separators=(",", ":"))

processing/ner/ner_engineering.py

@@ -7,7 +7,6 @@ import pandas as pd
 from tqdm import tqdm
 
 from core.config import PipelineConfig
-from core.utils import get_data_file_path
 from core.utils.data_loader import OPTIMIZED_DTYPES, DataLoader
 from processing.ner.formats.connectors_format import ConnectorFormatter
 from processing.ner.formats.extended_surname_format import ExtendedSurnameFormatter
@@ -55,7 +54,7 @@ class NEREngineering:
     def load_data(self) -> pd.DataFrame:
         """Load and filter NER-tagged data from CSV file"""
 
-        filepath = get_data_file_path(self.config.data.output_files["featured"], self.config)
+        filepath = self.config.paths.get_data_path(self.config.data.output_files["featured"])
         df = self.data_loader.load_csv_complete(filepath)
 
         # Filter only NER-tagged rows
@@ -66,10 +65,8 @@ class NEREngineering:
 
     def compute(self) -> None:
         logging.info("Applying feature engineering transformations...")
-        input_filepath = get_data_file_path(self.config.data.output_files["featured"], self.config)
-        output_filepath = get_data_file_path(
-            self.config.data.output_files["engineered"], self.config
-        )
+        input_filepath = self.config.paths.get_data_path(self.config.data.output_files["featured"])
+        output_filepath = self.config.paths.get_data_path(self.config.data.output_files["engineered"])
 
         df = self.data_loader.load_csv_complete(input_filepath)
         ner_df = df[df["ner_tagged"] == 1].copy()

processing/steps/feature_extraction_step.py

@@ -127,7 +127,7 @@ class FeatureExtractionStep(PipelineStep):
 
     def _process_simple_names(self, df: pd.DataFrame) -> None:
         """Process 3-word names efficiently with vectorized operations"""
-        mask = df["words"] == 3
+        mask = pd.Series(df["words"] == 3)
 
         if not mask.any():
             return