#   scipy-yli: Helpful SciPy utilities and recipes
#   Copyright © 2022–2023  Lee Yingtong Li (RunasSudo)
#
#   This program is free software: you can redistribute it and/or modify
#   it under the terms of the GNU Affero General Public License as published by
#   the Free Software Foundation, either version 3 of the License, or
#   (at your option) any later version.
#
#   This program is distributed in the hope that it will be useful,
#   but WITHOUT ANY WARRANTY; without even the implied warranty of
#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#   GNU Affero General Public License for more details.
#
#   You should have received a copy of the GNU Affero General Public License
#   along with this program.  If not, see <https://www.gnu.org/licenses/>.

from pytest import approx

import numpy as np
import pandas as pd

import yli

def test_mannwhitney_ol6_6():
	"""Compare yli.mannwhitney for Ott & Longnecker (2016) example 6.6"""
	
	df = pd.DataFrame({
		'Sample': ['Before'] * 12 + ['After'] * 12,
		'Oxygen': [11.0, 11.2, 11.2, 11.2, 11.4, 11.5, 11.6, 11.7, 11.8, 11.9, 11.9, 12.1, 10.2, 10.3, 10.4, 10.6, 10.6, 10.7, 10.8, 10.8, 10.9, 11.1, 11.1, 11.3]
	})
	
	result = yli.mannwhitney(df, 'Oxygen', 'Sample', method='asymptotic', alternative='less')
	
	assert result.pvalue == approx(0.00007, abs=0.00001)
	
	expected_summary = '''Sample                        After               Before
Oxygen                                                  
Median (IQR)    10.75 (10.55–10.95)  11.55 (11.20–11.83)
Median (range)  10.75 (11.00–12.10)  11.55 (11.00–12.10)

U = 6.0; p < 0.001*
r = 0.92, Before > After'''
	
	assert result.summary() == expected_summary
	assert result._repr_html_() == '<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border="1" class="dataframe">\n  <thead>\n    <tr style="text-align: right;">\n      <th>Sample</th>\n      <th>After</th>\n      <th>Before</th>\n    </tr>\n    <tr>\n      <th>Oxygen</th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>Median (IQR)</th>\n      <td>10.75 (10.55–10.95)</td>\n      <td>11.55 (11.20–11.83)</td>\n    </tr>\n    <tr>\n      <th>Median (range)</th>\n      <td>10.75 (11.00–12.10)</td>\n      <td>11.55 (11.00–12.10)</td>\n    </tr>\n  </tbody>\n</table>\n</div><br><i>U</i> = 6.0; <i>p</i> &lt; 0.001*<br><i>r</i> = 0.92, Before > After'