Pietro GiacobazziandDevin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
fe10be5ecc
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
34 lines
1.2 KiB
Python
34 lines
1.2 KiB
Python
"""Feature engineering: costruisce la matrice X dalle colonne di contesto.
|
|
|
|
Le feature sono SOLO informazioni note al momento dell'incrocio (nessun esito
|
|
futuro). Categoriche e numeriche sono gestite da un ColumnTransformer
|
|
(one-hot per le categoriche, passthrough per le numeriche) per restare
|
|
compatibili con l'export ONNX della Fase 4.
|
|
"""
|
|
from __future__ import annotations
|
|
import pandas as pd
|
|
from sklearn.compose import ColumnTransformer
|
|
from sklearn.preprocessing import OneHotEncoder
|
|
from sklearn.impute import SimpleImputer
|
|
from sklearn.pipeline import Pipeline
|
|
|
|
|
|
def build_preprocessor(num_cols: list[str], cat_cols: list[str]) -> ColumnTransformer:
|
|
num = Pipeline([("impute", SimpleImputer(strategy="median"))])
|
|
cat = Pipeline([
|
|
("impute", SimpleImputer(strategy="most_frequent")),
|
|
("oh", OneHotEncoder(handle_unknown="ignore", sparse_output=False)),
|
|
])
|
|
return ColumnTransformer([
|
|
("num", num, num_cols),
|
|
("cat", cat, cat_cols),
|
|
])
|
|
|
|
|
|
def select_xy(df: pd.DataFrame, num_cols: list[str], cat_cols: list[str]):
|
|
cols = num_cols + cat_cols
|
|
X = df[cols].copy()
|
|
for c in cat_cols:
|
|
X[c] = X[c].astype(str)
|
|
return X
|