From 70fba04b2f2b6a8c0c895e84ea74c89e235b0bc5 Mon Sep 17 00:00:00 2001
From: RunasSudo <runassudo@yingtongli.me>
Date: Sat, 15 Oct 2022 01:42:06 +1100
Subject: [PATCH] Regression output: Hide boolean reference categories by
 default if reference category is False

---
 tests/test_regress.py |  2 +-
 yli/regress.py        | 28 +++++++++++++++++++---------
 2 files changed, 20 insertions(+), 10 deletions(-)

diff --git a/tests/test_regress.py b/tests/test_regress.py
index 7bb6de6..721861d 100644
--- a/tests/test_regress.py
+++ b/tests/test_regress.py
@@ -138,7 +138,7 @@ def test_regress_logit_ol10_18():
 		'Stress': np.repeat([d[1] for d in data], [d[2] for d in data])
 	})
 	
-	result = yli.regress(sm.Logit, df, 'Stress', 'Response')
+	result = yli.regress(sm.Logit, df, 'Stress', 'Response', bool_baselevels=True)
 	
 	assert isinstance(result.terms['Response'], CategoricalTerm)
 	assert result.terms['Response'].ref_category == False
diff --git a/yli/regress.py b/yli/regress.py
index 2bb07f5..6efd25a 100644
--- a/yli/regress.py
+++ b/yli/regress.py
@@ -340,9 +340,15 @@ class CategoricalTerm:
 
 def regress(
 	model_class, df, dep, formula, *,
-	nan_policy='warn', exp=None
+	nan_policy='warn',
+	bool_baselevels=False, exp=None
 ):
-	"""Fit a statsmodels regression model"""
+	"""
+	Fit a statsmodels regression model
+	
+	bool_baselevels: Show reference categories for boolean independent variables even if reference category is False
+	exp: Report exponentiated parameters rather than raw parameters
+	"""
 	
 	# Autodetect whether to exponentiate
 	if exp is None:
@@ -392,16 +398,20 @@ def regress(
 			
 			if contrast is not None:
 				# Categorical term
-				# Add a new categorical term if not exists
-				if column not in terms:
-					ref_category = formula_factor_ref_category(formula, df, factor)
-					terms[column] = CategoricalTerm({}, ref_category)
 				
-				terms[column].categories[contrast] = SingleTerm(raw_name, beta, result.pvalues[raw_name])
+				if bool_baselevels is False and contrast == 'True' and set(df[column].unique()) == set([True, False]):
+					# Treat as single term
+					terms[column] = SingleTerm(raw_name, beta, result.pvalues[raw_name])
+				else:
+					# Add a new categorical term if not exists
+					if column not in terms:
+						ref_category = formula_factor_ref_category(formula, df, factor)
+						terms[column] = CategoricalTerm({}, ref_category)
+					
+					terms[column].categories[contrast] = SingleTerm(raw_name, beta, result.pvalues[raw_name])
 			else:
 				# Single term
-				term = raw_name
-				terms[term] = SingleTerm(raw_name, beta, result.pvalues[raw_name])
+				terms[column] = SingleTerm(raw_name, beta, result.pvalues[raw_name])
 	
 	# Fit null model (for llnull)
 	if hasattr(result, 'llnull'):