Add test and example for yli.pearsonr

This commit is contained in:
RunasSudo 2022-10-20 20:57:57 +11:00
parent 5248abf859
commit ee36ac9d14
Signed by: RunasSudo
GPG Key ID: 7234E476BF21C61A
2 changed files with 67 additions and 0 deletions

51
tests/test_correlation.py Normal file
View File

@ -0,0 +1,51 @@
# scipy-yli: Helpful SciPy utilities and recipes
# Copyright © 2022 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 pandas as pd
import yli
def test_pearsonr_ol11_15():
"""Compare yli.pearsonr for Ott & Longnecker (2016) example 11.15"""
df = pd.DataFrame({
'y': [41, 39, 47, 51, 43, 40, 57, 46, 50, 59, 61, 52],
'x': [24, 30, 33, 35, 36, 36, 37, 37, 38, 40, 43, 49]
})
result = yli.pearsonr(df, 'y', 'x')
assert result.statistic.point == approx(0.646, abs=0.001)
assert result.pvalue == approx(0.0234, abs=0.0001)
expected_summary = 'r (95% CI) = 0.65 (0.11–0.89); p = 0.02*'
assert result.summary() == expected_summary
def test_pearsonr_ol11_16():
"""Compare yli.pearsonr for Ott & Longnecker (2016) example 11.16"""
df = pd.DataFrame({
'Eggs': [27, 32, 39, 48, 59, 67, 71, 65, 73, 67, 78, 72, 81, 74, 83, 75, 84, 77, 83, 76, 82, 75, 78, 77, 75, 73, 71, 70, 68, 65],
'Weight': [2.1, 2.3, 2.4, 2.5, 2.9, 3.1, 3.2, 3.3, 3.4, 3.4, 3.5, 3.5, 3.5, 3.6, 3.6, 3.6, 3.6, 3.7, 3.7, 3.7, 3.8, 3.9, 4.0, 4.3, 4.4, 4.7, 4.8, 4.9, 5.0, 5.1]
})
result = yli.pearsonr(df, 'Eggs', 'Weight')
assert result.statistic.point == approx(0.606, abs=0.001)
assert result.statistic.ci_lower == approx(0.314, abs=0.001)
assert result.statistic.ci_upper == approx(0.793, abs=0.001)

View File

@ -543,6 +543,22 @@ def pearsonr(df, dep, ind, *, nan_policy='warn'):
:type nan_policy: str
:rtype: :class:`yli.sig_tests.PearsonRResult`
**Example:**
.. code-block::
df = pd.DataFrame({
'y': [41, 39, 47, 51, 43, 40, 57, 46, 50, 59, 61, 52],
'x': [24, 30, 33, 35, 36, 36, 37, 37, 38, 40, 43, 49]
})
yli.pearsonr(df, 'y', 'x')
.. code-block:: text
r (95% CI) = 0.65 (0.110.89); p = 0.02*
The output states that the value of the Pearson correlation coefficient is 0.65, with 95% confidence interval 0.110.89, and the test is significant with *p* value 0.02.
"""
# Check for/clean NaNs