REF: raise instead of warn if k_constant > 0

statsmodels · Sep 21, 2020 · 72709ba · 72709ba
1 parent eeb1eb2
commit 72709ba
Show file tree

Hide file tree

Showing 2 changed files with 43 additions and 56 deletions.
diff --git a/statsmodels/miscmodels/ordinal_model.py b/statsmodels/miscmodels/ordinal_model.py
@@ -107,6 +107,9 @@ def __init__(self, endog, exog, offset=None, distr='probit', **kwds):
                 # Note: Doing the following here would break from_formula
                 # self.endog = self.endog.argmax(1)
 
+        if self.k_constant > 0:
+            raise ValueError("there should not be a constant in the model")
+
         self._initialize_labels(labels)
 
         self.results_class = OrderedResults
@@ -173,16 +176,6 @@ def from_formula(cls, formula, data, subset=None, drop_cols=None,
 
         # we want an explicit Intercept in the model that we can remove
         # Removing constant with "0 +" or "- 1" does not work for categ. exog
-        # copied from PHReg
-        import re
-        terms = re.split(r"[+\-~]", formula)
-        for term in terms:
-            term = term.strip()
-            if term in ("0", "1"):
-                import warnings
-                msg = ("OrderedModel formulas should not include any '0' or "
-                       "'1' terms if those create an implicit constant.")
-                warnings.warn(msg, SpecificationWarning)
 
         endog_name = formula.split("~")[0].strip()
         original_endog = data[endog_name]

diff --git a/statsmodels/miscmodels/tests/test_ordinal_model.py b/statsmodels/miscmodels/tests/test_ordinal_model.py
@@ -136,15 +136,13 @@ def setup_class(cls):
                             distr='logit')
         resp = modp.fit(method='bfgs', disp=False)
         # fit with formula
-        with warnings.catch_warnings():
-            warnings.simplefilter("ignore", SpecificationWarning)
-            modf = OrderedModel.from_formula(
-                "apply ~ pared + public + gpa - 1",
-                data={"apply": data['apply'].values.codes,
-                      "pared": data['pared'],
-                      "public": data['public'],
-                      "gpa": data['gpa']},
-                distr='logit')
+        modf = OrderedModel.from_formula(
+            "apply ~ pared + public + gpa - 1",
+            data={"apply": data['apply'].values.codes,
+                  "pared": data['pared'],
+                  "public": data['public'],
+                  "gpa": data['gpa']},
+            distr='logit')
         resf = modf.fit(method='bfgs', disp=False)
         # fit on data with ordered=False
         modu = OrderedModel(
@@ -178,15 +176,13 @@ def setup_class(cls):
                             distr='probit')
         resp = modp.fit(method='bfgs', disp=False)
 
-        with warnings.catch_warnings():
-            warnings.simplefilter("ignore", SpecificationWarning)
-            modf = OrderedModel.from_formula(
-                "apply ~ pared + public + gpa - 1",
-                data={"apply": data['apply'].values.codes,
-                      "pared": data['pared'],
-                      "public": data['public'],
-                      "gpa": data['gpa']},
-                distr='probit')
+        modf = OrderedModel.from_formula(
+            "apply ~ pared + public + gpa - 1",
+            data={"apply": data['apply'].values.codes,
+                  "pared": data['pared'],
+                  "public": data['public'],
+                  "gpa": data['gpa']},
+            distr='probit')
         resf = modf.fit(method='bfgs', disp=False)
 
         modu = OrderedModel(
@@ -234,11 +230,9 @@ def test_formula_categorical(self):
         resp = self.resp
         data = ds.df
 
-        with warnings.catch_warnings():
-            warnings.simplefilter("ignore", SpecificationWarning)
-            formula = "apply ~ pared + public + gpa - 1"
-            modf2 = OrderedModel.from_formula(formula,
-                                              data, distr='probit')
+        formula = "apply ~ pared + public + gpa - 1"
+        modf2 = OrderedModel.from_formula(formula,
+                                          data, distr='probit')
         resf2 = modf2.fit(method='bfgs', disp=False)
         assert_allclose(resf2.params, resp.params, atol=1e-8)
         assert modf2.exog_names == resp.model.exog_names
@@ -247,15 +241,13 @@ def test_formula_categorical(self):
         assert not hasattr(modf2, "frame")
 
         with pytest.raises(ValueError):
-            with warnings.catch_warnings():
-                warnings.simplefilter("ignore", SpecificationWarning)
-                OrderedModel.from_formula(
-                    "apply ~ pared + public + gpa - 1",
-                    data={"apply": np.asarray(data['apply']),
-                          "pared": data['pared'],
-                          "public": data['public'],
-                          "gpa": data['gpa']},
-                    distr='probit')
+            OrderedModel.from_formula(
+                "apply ~ pared + public + gpa - 1",
+                data={"apply": np.asarray(data['apply']),
+                      "pared": data['pared'],
+                      "public": data['public'],
+                      "gpa": data['gpa']},
+                distr='probit')
 
 
 class TestLogitModelFormula():
@@ -301,16 +293,18 @@ def test_setup(self):
             assert_allclose(resf1.predict(data[:5]), fittedvalues[:5])
 
         # test over parameterized model with implicit constant
-        # warns but doesn't raise
         formula = "apply ~ 0 + pared + public + gpa + C(dummy)"
 
-        with pytest.warns(SpecificationWarning):
-            modf2 = OrderedModel.from_formula(formula, data, distr='logit')
+        with pytest.raises(ValueError):
+            OrderedModel.from_formula(formula, data, distr='logit')
 
-        with pytest.warns(HessianInversionWarning):
+        # ignore constant, so we get results without exception
+        modf2 = OrderedModel.from_formula(formula, data, distr='logit',
+                                          hasconst=False)
+        # we get a warning in some environments
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", HessianInversionWarning)
             resf2 = modf2.fit(method='bfgs')
-        assert resf2.converged is False
-        # assert np.isnan(resf2.bse).all()
 
         assert_allclose(resf2.predict(data[:5]), fittedvalues[:5], rtol=1e-4)
 
@@ -342,14 +336,14 @@ def _cdf(self, x):
                             distr=cloglog)
         resp = modp.fit(method='bfgs', disp=False)
 
-        with pytest.warns(UserWarning):
-            modf = OrderedModel.from_formula(
-                "apply ~ pared + public + gpa - 1",
-                data={"apply": data['apply'].values.codes,
-                      "pared": data['pared'],
-                      "public": data['public'],
-                      "gpa": data['gpa']},
-                distr=cloglog)
+        # with pytest.warns(UserWarning):
+        modf = OrderedModel.from_formula(
+            "apply ~ pared + public + gpa - 1",
+            data={"apply": data['apply'].values.codes,
+                  "pared": data['pared'],
+                  "public": data['public'],
+                  "gpa": data['gpa']},
+            distr=cloglog)
         resf = modf.fit(method='bfgs', disp=False)
 
         modu = OrderedModel(