Update documentation

This commit is contained in:
RunasSudo 2022-12-03 20:01:05 +11:00
parent fa89f2f156
commit 5633a191f1
Signed by: RunasSudo
GPG Key ID: 7234E476BF21C61A
2 changed files with 50 additions and 4 deletions

View File

@ -14,6 +14,8 @@ Functions
.. autofunction:: yli.pearsonr
.. autofunction:: yli.spearman
.. autofunction:: yli.ttest_ind
Result classes
@ -38,5 +40,8 @@ Result classes
.. autoclass:: yli.sig_tests.PearsonRResult
:members:
.. autoclass:: yli.sig_tests.SpearmanResult
:members:
.. autoclass:: yli.sig_tests.TTestResult
:members:

View File

@ -606,7 +606,7 @@ def chi2(df, dep, ind, *, nan_policy='warn'):
The odds of *Stress* in the *Response* = *True* group are 1.33 times that in the *Response* = *False* group, with 95% confidence interval 1.111.60.
The risk of *Stress* in the *Response* = *True* group is 1.11 that in the *Response* = *False* group, with 95% confidence interval 1.031.18.
The risk of *Stress* in the *Response* = *True* group is 1.11 times that in the *Response* = *False* group, with 95% confidence interval 1.031.18.
"""
# Check for/clean NaNs
@ -649,13 +649,13 @@ def chi2(df, dep, ind, *, nan_policy='warn'):
class PearsonRResult:
"""
Result of Pearson correlation
Result of Pearson product-moment correlation
See :func:`yli.pearsonr`.
"""
def __init__(self, statistic, pvalue):
#: Pearson *r* correlation statistic (*float*)
#: Pearson *r* correlation statistic (:class:`yli.utils.Estimate`)
self.statistic = statistic
#: *p* value for the *r* statistic (*float*)
self.pvalue = pvalue
@ -679,7 +679,7 @@ class PearsonRResult:
def pearsonr(df, dep, ind, *, nan_policy='warn'):
"""
Compute the Pearson correlation coefficient (Pearson's *r*)
Compute the Pearson product-moment correlation coefficient (Pearson's *r*)
:param df: Data to perform the test on
:type df: DataFrame
@ -722,8 +722,16 @@ def pearsonr(df, dep, ind, *, nan_policy='warn'):
# Spearman correlation
class SpearmanResult:
"""
Result of Spearman rank correlation
See :func:`yli.spearman`.
"""
def __init__(self, statistic, pvalue):
#: Spearman *ρ* correlation statistic (:class:`yli.utils.Estimate`)
self.statistic = statistic
#: *p* value for the *ρ* statistic (*float*)
self.pvalue = pvalue
def __repr__(self):
@ -744,6 +752,39 @@ class SpearmanResult:
return 'ρ ({:g}% CI) = {}; p {}'.format((1-config.alpha)*100, self.statistic.summary(), fmt_p(self.pvalue, PValueStyle.RELATION))
def spearman(df, dep, ind, *, nan_policy='warn'):
"""
Compute the Spearman rank correlation coefficient (Spearman's *ρ*)
The confidence interval for *ρ* is computed analogously to SciPy's *pearsonr*, using the Fisher transformation and normal approximation, without adjustment to variance.
:param df: Data to perform the test on
:type df: DataFrame
:param dep: Column in *df* for the dependent variable (numerical)
:type dep: str
:param ind: Column in *df* for the independent variable (numerical)
:type ind: str
:param nan_policy: How to handle *nan* values (see :ref:`nan-handling`)
:type nan_policy: str
:rtype: :class:`yli.sig_tests.SpearmanResult`
**Example:**
.. code-block::
df = pd.DataFrame({
'Profit': [2.5, 6.2, 3.1, ...],
'Quality': [50, 57, 61, ...]
})
yli.spearman(df, 'Profit', 'Quality')
.. code-block:: text
ρ (95% CI) = 0.87 (0.600.96); p < 0.001*
The output states that the value of the Spearman correlation coefficient is 0.87, with 95% confidence interval 0.600.96, and the test is significant with *p* value < 0.001.
"""
# Check for/clean NaNs
df = check_nan(df[[ind, dep]], nan_policy)