fix pre-commit errors

Author: fraboniface

policy_analysis/dspy_policies_and_taxonomy_extraction/policy_extraction/policy_dspy_model_creation.py

@@ -134,6 +134,6 @@ def __call__(self,example, pred, trace=None):
 print(f"Final Score on Validation Set (optimized): {optimized_score}%")
 
 # --- Saving the optimized model ---
-model_path = f"saved_dspy_model/policy_model/" 
+model_path = "saved_dspy_model/policy_model/" 
 compiled_program.save(model_path,save_program=True)
 print(f"Optimized model saved to {model_path}")

policy_analysis/dspy_policies_and_taxonomy_extraction/taxonomy_extraction/classify_data_with_trained_model.py

@@ -5,7 +5,6 @@
 from datasets import load_dataset
 import pyarrow as pa
 import pyarrow.parquet as pq
-from itertools import islice
 
 # ---------------------------------------------------------------------
 # 0. Config

policy_analysis/dspy_policies_and_taxonomy_extraction/taxonomy_extraction/geography_only_dspy_model_creation.py

@@ -270,7 +270,7 @@ def geography_f1_metric(example, pred, trace=None):
 print("Final Geography F1:", score)
 
 # Save results
-optimized_score = evaluator(compiled_program, save_as_json=f"results.json")
+optimized_score = evaluator(compiled_program, save_as_json="results.json")
 
 # ---------------------------------------------------------------------
 # 8. SAVE MODEL

policy_analysis/dspy_policies_and_taxonomy_extraction/taxonomy_extraction/impact_classification_model_training.py

@@ -16,12 +16,6 @@
 
 from sentence_transformers import SentenceTransformer
 
-# ---------------------------------------------------------------------
-# PATH SETUP
-# ---------------------------------------------------------------------
-sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../..")))
-load_dotenv()
-
 # ---------------------------------------------------------------------
 # 0. IMPORT TAXONOMY ENUMS
 # ---------------------------------------------------------------------
@@ -33,6 +27,12 @@
     Planetary_boundaries,
 )
 
+# ---------------------------------------------------------------------
+# PATH SETUP
+# ---------------------------------------------------------------------
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../..")))
+load_dotenv()
+
 # ---------------------------------------------------------------------
 # ENUM NORMALIZATION
 # ---------------------------------------------------------------------
@@ -73,13 +73,13 @@ def normalize_labels(labels, allowed_enum, allow_unknown=False):
         labels = [labels]
 
     cleaned = []
-    for l in labels:
-        if not l:
+    for label in labels:
+        if not label:
             continue
 
         # --- FIX: FORCE SNAKE_CASE ---
         # 1. Lowercase and strip
-        l_norm = l.lower().strip()
+        l_norm = label.lower().strip()
         # 2. Replace spaces and hyphens with underscores 
         #    (e.g., "Climate Change" -> "climate_change", "Land-System Change" -> "land_system_change")
         l_norm = re.sub(r"[\s\-]+", "_", l_norm)
@@ -91,7 +91,7 @@ def normalize_labels(labels, allowed_enum, allow_unknown=False):
             cleaned.append(l_norm)
         # Optional: Print warning if label is rejected (good for debugging)
         # else: 
-        #    print(f"Warning: Label '{l}' normalized to '{l_norm}' not found in Enum.")
+        #    print(f"Warning: Label '{label}' normalized to '{l_norm}' not found in Enum.")
 
     if not cleaned and allow_unknown:
         return ["unknown"]
@@ -255,8 +255,8 @@ def load_taxonomy_jsonl(path, source_name):
     y_true_labels = mlb_dict[field].inverse_transform(y_true)
     y_pred_labels = mlb_dict[field].inverse_transform(y_pred)
 
-    results[f"{field}_true"] = [list(l) for l in y_true_labels]
-    results[f"{field}_pred"] = [list(l) for l in y_pred_labels]
+    results[f"{field}_true"] = [list(label) for label in y_true_labels]
+    results[f"{field}_pred"] = [list(label) for label in y_pred_labels]
 
     f1 = f1_score(y_true, y_pred, average="micro")
     f1_scores[field] = round(f1, 4)