import pandas as pd
import pytest

from data_processing import filter_by_date, hourly_average


@pytest.fixture
def sample_df():
    return pd.DataFrame(
        {
            "timestamp": pd.to_datetime(
                [
                    "2026-07-22 08:05",
                    "2026-07-22 08:40",
                    "2026-07-22 09:10",
                    "2026-07-23 08:05",  # andere dag, moet uitgefilterd worden
                ]
            ),
            "glucose_value": [6.0, 8.0, 7.0, 12.0],
        }
    )


def test_filter_by_date_keeps_only_selected_day(sample_df):
    result = filter_by_date(sample_df, pd.Timestamp("2026-07-22").date())
    assert len(result) == 3
    assert (result["timestamp"].dt.date == pd.Timestamp("2026-07-22").date()).all()


def test_hourly_average_computes_mean_per_hour(sample_df):
    filtered = filter_by_date(sample_df, pd.Timestamp("2026-07-22").date())
    result = hourly_average(filtered)

    hour_8 = result.loc[result["hour"] == 8, "glucose_value"].iloc[0]
    hour_9 = result.loc[result["hour"] == 9, "glucose_value"].iloc[0]

    assert hour_8 == pytest.approx(7.0)  # gemiddelde van 6.0 en 8.0
    assert hour_9 == pytest.approx(7.0)


def test_hourly_average_handles_empty_input():
    empty = pd.DataFrame(columns=["timestamp", "glucose_value"])
    result = hourly_average(empty)
    assert result.empty
    assert list(result.columns) == ["hour", "glucose_value"]


def test_hourly_average_only_returns_hours_with_data(sample_df):
    filtered = filter_by_date(sample_df, pd.Timestamp("2026-07-22").date())
    result = hourly_average(filtered)
    # alleen uur 8 en 9 hebben data op deze dag, dus precies 2 rijen
    assert len(result) == 2