Cleaned add_..._terms_to_df

Author: jmafoster1

causal_testing/testing/estimators.py

@@ -331,54 +331,6 @@ def add_modelling_assumptions(self):
             "do not need to be linear."
         )
 
-    # def add_squared_term_to_df(self, term_to_square: str):
-    #     """Add a squared term to the linear regression model and df.
-    #
-    #     This enables the user to capture curvilinear relationships with a linear regression model, not just straight
-    #     lines, while automatically adding the modelling assumption imposed by the addition of this term.
-    #
-    #     :param term_to_square: The term (column in data and variable in DAG) which is to be squared.
-    #     """
-    #     new_term = str(term_to_square) + "^2"
-    #     self.df[new_term] = self.df[term_to_square] ** 2
-    #     self.adjustment_set.add(new_term)
-    #     self.modelling_assumptions += (
-    #         f"Relationship between {self.treatment} and {self.outcome} varies quadratically" f"with {term_to_square}."
-    #     )
-    #     self.square_terms.append(term_to_square)
-
-    # def add_inverse_term_to_df(self, term_to_invert: str):
-    #     """Add an inverse term to the linear regression model and df.
-    #
-    #     This enables the user to capture curvilinear relationships with a linear regression model, not just straight
-    #     lines, while automatically adding the modelling assumption imposed by the addition of this term.
-    #
-    #     :param term_to_square: The term (column in data and variable in DAG) which is to be squared.
-    #     """
-    #     new_term = "1/" + str(term_to_invert)
-    #     self.df[new_term] = 1 / self.df[term_to_invert]
-    #     self.adjustment_set.add(new_term)
-    #     self.modelling_assumptions += (
-    #         f"Relationship between {self.treatment} and {self.outcome} varies inversely" f"with {term_to_invert}."
-    #     )
-    #     self.inverse_terms.append(term_to_invert)
-
-    # def add_product_term_to_df(self, term_a: str, term_b: str):
-    #     """Add a product term to the linear regression model and df.
-    #
-    #     This enables the user to capture interaction between a pair of variables in the model. In other words, while
-    #     each covariate's contribution to the mean is assumed to be independent of the other covariates, the pair of
-    #     product terms term_a*term_b a are restricted to vary linearly with each other.
-    #
-    #     :param term_a: The first term of the product term.
-    #     :param term_b: The second term of the product term.
-    #     """
-    #     new_term = str(term_a) + "*" + str(term_b)
-    #     self.df[new_term] = self.df[term_a] * self.df[term_b]
-    #     self.adjustment_set.add(new_term)
-    #     self.modelling_assumptions += f"{term_a} and {term_b} vary linearly with each other."
-    #     self.product_terms.append((term_a, term_b))
-
     def estimate_unit_ate(self) -> float:
         """Estimate the unit average treatment effect of the treatment on the outcome. That is, the change in outcome
         caused by a unit change in treatment.

examples/covasim_/doubling_beta/causal_test_beta.py

@@ -54,7 +54,6 @@ def doubling_beta_CATE_on_csv(observational_data_path: str, simulate_counterfact
                                                             formula="cum_infections ~ beta + np.power(beta, 2) + avg_age + contacts")
 
     # Add squared terms for beta, since it has a quadratic relationship with cumulative infections
-    # linear_regression_estimator.add_squared_term_to_df('beta')
     causal_test_result = causal_test_engine.execute_test(linear_regression_estimator, causal_test_case, 'ate')
 
     # Repeat for association estimate (no adjustment)
@@ -63,7 +62,6 @@ def doubling_beta_CATE_on_csv(observational_data_path: str, simulate_counterfact
                                                                           'cum_infections',
                                                                           df=past_execution_df,
                                                                           formula="cum_infections ~ beta + np.power(beta, 2)")
-    # no_adjustment_linear_regression_estimator.add_squared_term_to_df('beta')
     association_test_result = causal_test_engine.execute_test(no_adjustment_linear_regression_estimator, causal_test_case, 'ate')
 
     # Store results for plotting
@@ -86,7 +84,6 @@ def doubling_beta_CATE_on_csv(observational_data_path: str, simulate_counterfact
                                                                                'cum_infections',
                                                                                df=counterfactual_past_execution_df,
                                                                                formula="cum_infections ~ beta + np.power(beta, 2) + avg_age + contacts")
-        # counterfactual_linear_regression_estimator.add_squared_term_to_df('beta')
         counterfactual_causal_test_result = causal_test_engine.execute_test(linear_regression_estimator, causal_test_case, 'ate')
         results_dict['counterfactual'] = {'ate': counterfactual_causal_test_result.test_value.value,
                                           'cis': counterfactual_causal_test_result.confidence_intervals,

examples/poisson/run_causal_tests.py

@@ -150,11 +150,7 @@ class MyJsonUtility(JsonUtility):
     def add_modelling_assumptions(self, estimation_model: Estimator):
         # Add squared intensity term as a modelling assumption if intensity is the treatment of the test
         if "intensity" in estimation_model.treatment[0]:
-            estimation_model.add_squared_term_to_df("intensity")
             estimation_model.intercept = 0
-        if isinstance(estimation_model, WidthHeightEstimator):
-            estimation_model.add_product_term_to_df("width", "intensity")
-            estimation_model.add_product_term_to_df("height", "intensity")
 
 
 if __name__ == "__main__":

tests/testing_tests/test_causal_test_engine.py

@@ -220,7 +220,6 @@ def test_execute_test_observational_linear_regression_estimator_squared_term(sel
             self.causal_test_engine.scenario_execution_data_df,
             formula=f"C ~ A + {'+'.join(self.minimal_adjustment_set)} + (D ** 2)"
         )
-        # estimation_model.add_squared_term_to_df("D")
         causal_test_result = self.causal_test_engine.execute_test(estimation_model, self.causal_test_case)
         self.assertAlmostEqual(round(causal_test_result.test_value.value, 1), 4, delta=1)
 

tests/testing_tests/test_estimators.py

@@ -168,7 +168,6 @@ def test_program_11_3(self):
         """Test whether our linear regression implementation produces the same results as program 11.3 (p. 144)."""
         df = self.chapter_11_df.copy()
         linear_regression_estimator = LinearRegressionEstimator("treatments", 100, 90, set(), "outcomes", df, formula="outcomes ~ treatments + np.power(treatments, 2)")
-        # linear_regression_estimator.add_squared_term_to_df("treatments")
         model = linear_regression_estimator._run_linear_regression()
         ate, _ = linear_regression_estimator.estimate_unit_ate()
         self.assertEqual(
@@ -210,7 +209,6 @@ def test_program_15_1A(self):
         # terms_to_square = ["age", "wt71", "smokeintensity", "smokeyrs"]
         # terms_to_product = [("qsmk", "smokeintensity")]
         # for term_to_square in terms_to_square:
-        #     linear_regression_estimator.add_squared_term_to_df(term_to_square)
         # for term_a, term_b in terms_to_product:
         #     linear_regression_estimator.add_product_term_to_df(term_a, term_b)
 
@@ -242,7 +240,6 @@ def test_program_15_no_interaction(self):
         formula="wt82_71 ~ qsmk + age + np.power(age, 2) + wt71 + np.power(wt71, 2) + smokeintensity + np.power(smokeintensity, 2) + smokeyrs + np.power(smokeyrs, 2)")
         # terms_to_square = ["age", "wt71", "smokeintensity", "smokeyrs"]
         # for term_to_square in terms_to_square:
-        #     linear_regression_estimator.add_squared_term_to_df(term_to_square)
         ate, [ci_low, ci_high] = linear_regression_estimator.estimate_unit_ate()
         self.assertEqual(round(ate, 1), 3.5)
         self.assertEqual([round(ci_low, 1), round(ci_high, 1)], [2.6, 4.3])
@@ -271,7 +268,6 @@ def test_program_15_no_interaction_ate(self):
         formula="wt82_71 ~ qsmk + age + np.power(age, 2) + wt71 + np.power(wt71, 2) + smokeintensity + np.power(smokeintensity, 2) + smokeyrs + np.power(smokeyrs, 2)")
         # terms_to_square = ["age", "wt71", "smokeintensity", "smokeyrs"]
         # for term_to_square in terms_to_square:
-        #     linear_regression_estimator.add_squared_term_to_df(term_to_square)
         ate, [ci_low, ci_high] = linear_regression_estimator.estimate_ate()
         self.assertEqual(round(ate, 1), 3.5)
         self.assertEqual([round(ci_low, 1), round(ci_high, 1)], [2.6, 4.3])
@@ -300,7 +296,6 @@ def test_program_15_no_interaction_ate_calculated(self):
         formula="wt82_71 ~ qsmk + age + np.power(age, 2) + wt71 + np.power(wt71, 2) + smokeintensity + np.power(smokeintensity, 2) + smokeyrs + np.power(smokeyrs, 2)")
         # terms_to_square = ["age", "wt71", "smokeintensity", "smokeyrs"]
         # for term_to_square in terms_to_square:
-        #     linear_regression_estimator.add_squared_term_to_df(term_to_square)
         ate, [ci_low, ci_high] = linear_regression_estimator.estimate_ate_calculated(
             {k: self.nhefs_df.mean()[k] for k in covariates}
         )