Add transform helpers: null drop, dedup, type casting

src/transform/clean.py

@@ -0,0 +1,30 @@
+import pandas as pd
+
+
+def drop_nulls(df: pd.DataFrame, required_cols: list[str]) -> pd.DataFrame:
+    before = len(df)
+    df = df.dropna(subset=required_cols)
+    dropped = before - len(df)
+    if dropped:
+        print(f"[clean] Dropped {dropped} rows with nulls in {required_cols}")
+    return df
+
+
+def normalise_timestamps(df: pd.DataFrame, col: str) -> pd.DataFrame:
+    df[col] = pd.to_datetime(df[col], utc=True)
+    return df
+
+
+def deduplicate(df: pd.DataFrame, key_cols: list[str]) -> pd.DataFrame:
+    before = len(df)
+    df = df.drop_duplicates(subset=key_cols, keep="last")
+    print(f"[clean] Dedup removed {before - len(df)} rows")
+    return df
+
+
+def cast_types(df: pd.DataFrame, schema: dict) -> pd.DataFrame:
+    """Cast columns to specified types. schema = {col: dtype}"""
+    for col, dtype in schema.items():
+        if col in df.columns:
+            df[col] = df[col].astype(dtype)
+    return df