| """Stateless feature engineering shared by training and serving. |
| |
| Raw input schema (same as the Kaggle ULB creditcard dataset, minus the label): |
| V1..V28 anonymised PCA components |
| Amount transaction amount |
| Time seconds since the first transaction of the dataset |
| """ |
|
|
| import numpy as np |
| import pandas as pd |
|
|
| V_COLS = [f"V{i}" for i in range(1, 29)] |
| RAW_FEATURES = V_COLS + ["Amount", "Time"] |
| DERIVED_FEATURES = ["log_amount", "hour_sin", "hour_cos"] |
| MODEL_FEATURES = V_COLS + DERIVED_FEATURES |
| SCALED_FEATURES = ["log_amount"] |
|
|
|
|
| def make_features(raw: pd.DataFrame) -> pd.DataFrame: |
| """Raw transactions -> unscaled model features (deterministic, no fitting).""" |
| missing = [c for c in RAW_FEATURES if c not in raw.columns] |
| if missing: |
| raise ValueError(f"Missing raw feature columns: {missing}") |
| out = raw[V_COLS].astype(float).copy() |
| out["log_amount"] = np.log1p(raw["Amount"].astype(float).clip(lower=0)) |
| hour = (raw["Time"].astype(float) % 86400) / 3600.0 |
| out["hour_sin"] = np.sin(2 * np.pi * hour / 24.0) |
| out["hour_cos"] = np.cos(2 * np.pi * hour / 24.0) |
| return out[MODEL_FEATURES] |
|
|
