tests/conftest.py

"""Shared fixtures for DVF pipeline tests."""

import polars as pl
import pytest


@pytest.fixture
def sample_raw_df() -> pl.DataFrame:
    """
    Small synthetic DVF dataset mimicking raw CSV structure.
    Contains known edge cases: multi-row mutations, mixed types,
    arrondissements, outliers, commercial properties.
    """
    return pl.DataFrame(
        {
            "id_mutation": [
                # Normal single-row mutations
                "M001", "M002", "M003", "M004", "M005",
                # Multi-row same type (should be aggregated)
                "M006", "M006",
                # Multi-row mixed type (should be excluded)
                "M007", "M007",
                # Outliers
                "M008", "M009",
                # Commercial (should be filtered after config change)
                "M010",
                # Paris arrondissement
                "M011",
                # Non-sale
                "M012",
                # Null price
                "M013",
            ],
            "date_mutation": [
                "2024-06-15", "2023-01-20", "2022-07-10", "2021-03-05", "2020-11-22",
                "2024-03-10", "2024-03-10",
                "2023-06-01", "2023-06-01",
                "2024-01-01", "2024-01-01",
                "2024-05-01",
                "2024-08-20",
                "2023-09-15",
                "2024-02-01",
            ],
            "nature_mutation": [
                "Vente", "Vente", "Vente", "Vente", "Vente",
                "Vente", "Vente",
                "Vente", "Vente",
                "Vente", "Vente",
                "Vente",
                "Vente",
                "Echange",
                "Vente",
            ],
            "valeur_fonciere": [
                200000.0, 150000.0, 300000.0, 180000.0, 250000.0,
                400000.0, 400000.0,
                350000.0, 350000.0,
                5000.0, 9000000.0,
                120000.0,
                500000.0,
                100000.0,
                None,
            ],
            "code_postal": [
                "75001", "69001", "13001", "31000", "33000",
                "75002", "75002",
                "06000", "06000",
                "44000", "44000",
                "34000",
                "75101",
                "59000",
                "75003",
            ],
            "code_commune": [
                "75101", "69381", "13201", "31555", "33063",
                "75102", "75102",
                "06088", "06088",
                "44109", "44109",
                "34172",
                "75101",
                "59350",
                "75103",
            ],
            "nom_commune": [
                "Paris 1er", "Lyon 1er", "Marseille 1er", "Toulouse", "Bordeaux",
                "Paris 2e", "Paris 2e",
                "Nice", "Nice",
                "Nantes", "Nantes",
                "Montpellier",
                "Paris 1er",
                "Lille",
                "Paris 3e",
            ],
            "code_departement": [
                "75", "69", "13", "31", "33",
                "75", "75",
                "06", "06",
                "44", "44",
                "34",
                "75",
                "59",
                "75",
            ],
            "id_parcelle": [
                "75101000A001", "69381000B002", "13201000C003", "31555000D004", "33063000E005",
                "75102000F006", "75102000F007",
                "06088000G008", "06088000G009",
                "44109000H010", "44109000H011",
                "34172000I012",
                "75101000J013",
                "59350000K014",
                "75103000L015",
            ],
            "code_type_local": [
                "2", "2", "1", "1", "2",
                "2", "2",
                "2", "4",
                "2", "2",
                "4",
                "2",
                "1",
                "2",
            ],
            "type_local": [
                "Appartement", "Appartement", "Maison", "Maison", "Appartement",
                "Appartement", "Appartement",
                "Appartement", "Dependance",
                "Appartement", "Appartement",
                "Local industriel. commercial ou assimilé",
                "Appartement",
                "Maison",
                "Appartement",
            ],
            "surface_reelle_bati": [
                50.0, 75.0, 120.0, 90.0, 65.0,
                80.0, 30.0,
                60.0, 10.0,
                3.0, 45.0,
                200.0,
                55.0,
                100.0,
                40.0,
            ],
            "nombre_pieces_principales": [
                2, 3, 5, 4, 3,
                3, 1,
                2, 0,
                1, 2,
                0,
                2,
                4,
                2,
            ],
            "nombre_lots": [
                1, 1, 1, 1, 1,
                2, 2,
                2, 2,
                1, 1,
                1,
                1,
                1,
                1,
            ],
            "longitude": [
                2.34, 4.83, 5.37, 1.44, -0.57,
                2.34, 2.34,
                7.26, 7.26,
                -1.55, -1.55,
                3.87,
                2.34,
                3.06,
                2.36,
            ],
            "latitude": [
                48.86, 45.76, 43.30, 43.60, 44.84,
                48.87, 48.87,
                43.71, 43.71,
                47.22, 47.22,
                43.61,
                48.86,
                50.63,
                48.86,
            ],
        }
    )


@pytest.fixture
def sample_clean_df() -> pl.DataFrame:
    """
    Pre-cleaned dataset with derived columns, ready for aggregation.
    Represents what comes out of the cleaner.
    """
    return pl.DataFrame(
        {
            "id_mutation": ["M1", "M2", "M3", "M4", "M5", "M6", "M7", "M8"],
            "date_mutation": [
                "2024-06-15", "2024-01-10", "2023-06-01",
                "2022-01-15", "2021-06-01", "2020-01-10",
                "2024-09-01", "2024-03-15",
            ],
            "type_local": [
                "Appartement", "Maison", "Appartement",
                "Maison", "Appartement", "Maison",
                "Appartement", "Maison",
            ],
            "valeur_fonciere": [
                250000.0, 180000.0, 200000.0,
                150000.0, 300000.0, 120000.0,
                400000.0, 220000.0,
            ],
            "surface_reelle_bati": [
                50.0, 90.0, 80.0,
                100.0, 60.0, 80.0,
                40.0, 110.0,
            ],
            "prix_m2": [
                5000.0, 2000.0, 2500.0,
                1500.0, 5000.0, 1500.0,
                10000.0, 2000.0,
            ],
            "temporal_weight": [
                0.97**2, 0.97**7, 0.97**13,
                0.97**25, 0.97**37, 0.97**49,
                0.97**(-2), 0.97**4,
            ],
            "code_departement": ["75", "69", "75", "69", "75", "69", "75", "69"],
            "code_commune": ["75056", "69123", "75056", "69123", "75056", "69123", "75056", "69123"],
            "code_commune_city": ["75056", "69123", "75056", "69123", "75056", "69123", "75056", "69123"],
            "code_postal": ["75001", "69001", "75002", "69002", "75003", "69003", "75001", "69002"],
            "code_section": ["7510100001", "6938100001", "7510200001", "6912300001", "7510300001", "6912300002", "7510100002", "6912300003"],
            "code_region": ["11", "84", "11", "84", "11", "84", "11", "84"],
            "year": ["2024", "2024", "2023", "2022", "2021", "2020", "2024", "2024"],
            "months_since": [2.0, 7.0, 13.0, 25.0, 37.0, 49.0, -2.0, 4.0],
        }
    )