tests/test_main.py

import numpy as np
import pandas as pd
import pytest

from main import create_station_stats


@pytest.fixture
def sample_pivoted_data():
    """Create a sample pivoted dataset that matches the expected structure"""
    # Create sample data
    index = pd.MultiIndex.from_product(
        [
            ["1.00", "3.20"],  # Station_Number
            [
                "Depth, Secchi Disk Depth",
                "Temperature, Water",
                "Dissolved Oxygen",
                "Turbidity",
                "Salinity",
                "pH",
            ],  # Org_Analyte_Name
        ],
        names=["Station_Number", "Org_Analyte_Name"],
    )

    # Create MultiIndex columns
    columns = pd.MultiIndex.from_product(
        [
            ["count", "max", "mean", "min"],  # Aggregation functions
            ["Bottom", "Surface"],  # Sample_Position
        ]
    )

    # Create sample data with consistent values
    data = np.full((len(index), len(columns)), 10.0)

    # Create DataFrame first
    df = pd.DataFrame(data, index=index, columns=columns)

    # Set count values to 100 using proper MultiIndex access
    df.loc[:, ("count", "Bottom")] = 100
    df.loc[:, ("count", "Surface")] = 100

    return df


def test_create_station_stats_basic(sample_pivoted_data):
    """Test basic functionality of create_station_stats"""
    station = "3.20"
    result = create_station_stats(sample_pivoted_data, station)

    # Check basic structure
    assert isinstance(result, pd.DataFrame)
    assert len(result) == 4  # Average, Maximum, Minimum, n=
    assert "Station" in result.columns
    assert "Statistic" in result.columns


def test_create_station_stats_values(sample_pivoted_data):
    """Test that values are correctly mapped from pivoted data"""
    station = "3.20"
    result = create_station_stats(sample_pivoted_data, station)

    # Check specific values for Dissolved Oxygen
    surface_do = result["Dissolved Oxygen (mg/L) Surface"].tolist()
    assert surface_do == [10.0, 10.0, 10.0, 100]  # mean, max, min, count


def test_create_station_stats_columns(sample_pivoted_data):
    """Test that all expected columns are present"""
    station = "3.20"
    result = create_station_stats(sample_pivoted_data, station)

    expected_columns = {
        "Station",
        "Statistic",
        "Secchi Depth (feet)",
        "Temperature (°C) Surface",
        "Temperature (°C) Bottom",
        "Dissolved Oxygen (mg/L) Surface",
        "Dissolved Oxygen (mg/L) Bottom",
        "Turbidity (NTU) Surface",
        "Turbidity (NTU) Bottom",
        "Salinity (ppt) Surface",
        "Salinity (ppt) Bottom",
        "pH Surface",
        "pH Bottom",
    }

    assert set(result.columns) == expected_columns


def test_create_station_stats_missing_data(sample_pivoted_data):
    """Test handling of missing data"""
    station = "3.20"
    # Introduce some NaN values
    sample_pivoted_data.loc[(station, "pH"), ("mean", "Surface")] = np.nan

    result = create_station_stats(sample_pivoted_data, station)
    assert pd.isna(result["pH Surface"][0])  # Check if NaN is preserved


def test_create_station_stats_statistics(sample_pivoted_data):
    """Test that statistics are in correct order"""
    station = "3.20"
    result = create_station_stats(sample_pivoted_data, station)

    expected_statistics = ["Average", "Maximum", "Minimum", "n="]
    assert result["Statistic"].tolist() == expected_statistics


def test_create_station_stats_invalid_station(sample_pivoted_data):
    """Test behavior with invalid station"""
    with pytest.raises(KeyError):
        create_station_stats(sample_pivoted_data, "invalid_station")