RunasSudo
/
scipy-yli
1
Fork 0
Code Issues 1 Pull Requests Releases Activity

In auto_univariable, omit NaN only from affected analyses

This commit is contained in:
RunasSudo 2022-11-10 18:47:30 +11:00
parent f80afd0e80
commit c3eef0efea
Signed by: RunasSudo
GPG Key ID: 7234E476BF21C61A
1 changed files with 14 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
yli/sig_tests.py
View File

@ -766,6 +766,8 @@ def auto_univariable(df, dep, inds, *, ordinal=[], nan_policy='warn'):
* For a continuous independent variable – :func:`yli.ttest_ind`
* For an ordinal independent variable – :func:`yli.mannwhitney`
If *nan_policy* is *warn* or *omit*, rows with *nan* values are omitted only from the individual tests of association for the missing variables.
:param df: Data to perform the test on
:type df: DataFrame
:param dep: Column in *df* for the dependent variable (dichotomous)
@ -780,9 +782,8 @@ def auto_univariable(df, dep, inds, *, ordinal=[], nan_policy='warn'):
:rtype: :class:`yli.sig_tests.AutoBinaryResult`
"""
# Check for/clean NaNs
# Following this, we pass nan_policy='raise' to assert no NaNs remaining
df = check_nan(df[inds + [dep]], nan_policy)
# Check for/clean NaNs in dependent variable
df = check_nan(df[inds + [dep]], nan_policy, cols=[dep])
# Ensure 2 groups for dep
# TODO: Work for non-binary dependent variables?
@ -792,11 +793,15 @@ def auto_univariable(df, dep, inds, *, ordinal=[], nan_policy='warn'):
result_labels = []
for ind in inds:
if df[ind].dtype in ('bool', 'category', 'object'):
# Check for/clean NaNs in independent variable
# Following this, we pass nan_policy='raise' to assert no NaNs remaining
df_cleaned = check_nan(df, nan_policy, cols=[ind])
if df_cleaned[ind].dtype in ('bool', 'boolean', 'category', 'object'):
# Pearson chi-squared test
result = chi2(df, dep, ind, nan_policy='raise')
result = chi2(df_cleaned, dep, ind, nan_policy='raise')
values = sorted(df[ind].unique())
values = sorted(df_cleaned[ind].unique())
# Value counts
result_labels.append((
@ -808,10 +813,10 @@ def auto_univariable(df, dep, inds, *, ordinal=[], nan_policy='warn'):
':'.join(str((data2[ind] == v).sum()) for v in values),
result
))
elif df[ind].dtype in ('float64', 'int64', 'Float64', 'Int64'):
elif df_cleaned[ind].dtype in ('float64', 'int64', 'Float64', 'Int64'):
if ind in ordinal:
# Mann-Whitney test
result = mannwhitney(df, ind, dep, nan_policy='raise')
result = mannwhitney(df_cleaned, ind, dep, nan_policy='raise')
result_labels.append((
'{}, median (IQR)'.format(ind),
@ -824,7 +829,7 @@ def auto_univariable(df, dep, inds, *, ordinal=[], nan_policy='warn'):
))
else:
# t test
result = ttest_ind(df, ind, dep, nan_policy='raise')
result = ttest_ind(df_cleaned, ind, dep, nan_policy='raise')
result_labels.append((
'{}, μ (SD)'.format(ind),