extract years from dates

src/preprocess_utils.py

@@ -721,6 +721,10 @@ def safe_extract_year(date_str: str) -> str:
     except (ValueError, TypeError):
         return UNKNOWN_TOKEN
 
+def extract_year(df: pd.DataFrame, column_name) -> pd.DataFrame:
+    df[column_name + "_Year"] = df[column_name].apply(safe_extract_year)
+    return df
+
 def calculate_ages(df: pd.DataFrame) -> pd.DataFrame:
     """
     Calculate:
@@ -729,9 +733,9 @@ def calculate_ages(df: pd.DataFrame) -> pd.DataFrame:
     3. Age gap between recipient and donor
     """
     # Extract years safely
-    df["Recepient_DOB_Year"] = df["Recepient_DOB"].apply(safe_extract_year)
-    df["Donor_DOB_Year"] = df["Donor_DOB"].apply(safe_extract_year)
-    df["HSCT_date_Year"] = df["HSCT_date"].apply(safe_extract_year)
+    df = extract_year(df, "HSCT_date")
+    df = extract_year(df, "Recepient_DOB")
+    df = extract_year(df, "Donor_DOB") 
     
     # Calculate ages with safe conversion
     def calculate_age_diff(row, dob_col, transplant_col):
@@ -924,7 +928,12 @@ def preprocess_pipeline(df) -> pd.DataFrame:
     df = process_hla_columns(df)
     df = expand_HLA_cols(df)
 
-    # Feature engineering
+    # Extract years
+    df = extract_year(df, "HSCT_date")
+    df = extract_year(df, "Recepient_DOB")
+    df = extract_year(df, "Donor_DOB")
+    df = extract_year(df, "Date of first diagnosis/BMBx date")
+ 
     df = calculate_ages(df)
 
     # Final missing value handling