black

Author: jmafoster1

examples/covasim_/doubling_beta/example_beta.py

@@ -36,7 +36,7 @@
 
 
 def doubling_beta_CATE_on_csv(
-        observational_data_path: str, simulate_counterfactuals: bool = False, verbose: bool = False
+    observational_data_path: str, simulate_counterfactuals: bool = False, verbose: bool = False
 ):
     """Compute the CATE of increasing beta from 0.016 to 0.032 on cum_infections using the dataframe
     loaded from the specified path. Additionally simulate the counterfactuals by repeating the analysis
@@ -65,8 +65,9 @@ def doubling_beta_CATE_on_csv(
     )
 
     # Add squared terms for beta, since it has a quadratic relationship with cumulative infections
-    causal_test_result = causal_test_case.execute_test(estimator=linear_regression_estimator,
-                                                       data_collector=data_collector)
+    causal_test_result = causal_test_case.execute_test(
+        estimator=linear_regression_estimator, data_collector=data_collector
+    )
 
     # Repeat for association estimate (no adjustment)
     no_adjustment_linear_regression_estimator = LinearRegressionEstimator(
@@ -78,8 +79,9 @@ def doubling_beta_CATE_on_csv(
         df=past_execution_df,
         formula="cum_infections ~ beta + np.power(beta, 2)",
     )
-    association_test_result = causal_test_case.execute_test(estimator=no_adjustment_linear_regression_estimator,
-                                                            data_collector=data_collector)
+    association_test_result = causal_test_case.execute_test(
+        estimator=no_adjustment_linear_regression_estimator, data_collector=data_collector
+    )
 
     # Store results for plotting
     results_dict["association"] = {
@@ -110,7 +112,8 @@ def doubling_beta_CATE_on_csv(
             formula="cum_infections ~ beta + np.power(beta, 2) + avg_age + contacts",
         )
         counterfactual_causal_test_result = causal_test_case.execute_test(
-            estimator=linear_regression_estimator, data_collector=data_collector)
+            estimator=linear_regression_estimator, data_collector=data_collector
+        )
 
         results_dict["counterfactual"] = {
             "ate": counterfactual_causal_test_result.test_value.value,

examples/lr91/example_max_conductances_test_suite.py

@@ -146,7 +146,6 @@ def effects_on_APD90(observational_data_path, test_suite):
     # 7. Create a data collector
     data_collector = ObservationalDataCollector(scenario, pd.read_csv(observational_data_path))
 
-
     # 8. Run the causal test suite
     causal_test_results = test_suite.execute_test_suite(data_collector, causal_specification)
     return causal_test_results

tests/specification_tests/test_causal_dag.py

@@ -174,18 +174,19 @@ def test_proper_backdoor_graph(self):
         """Test whether converting a Causal DAG to a proper back-door graph works correctly."""
         causal_dag = CausalDAG(self.dag_dot_path)
         proper_backdoor_graph = causal_dag.get_proper_backdoor_graph(["X1", "X2"], ["Y"])
-        edges = set([
-                    ("X1", "X2"),
-                    ("X2", "V"),
-                    ("X2", "D2"),
-                    ("D1", "D2"),
-                    ("D1", "Y"),
-                    ("Y", "D3"),
-                    ("Z", "X2"),
-                    ("Z", "Y"),
-                ])
-        self.assertTrue(
-            set(proper_backdoor_graph.graph.edges).issubset(edges))
+        edges = set(
+            [
+                ("X1", "X2"),
+                ("X2", "V"),
+                ("X2", "D2"),
+                ("D1", "D2"),
+                ("D1", "Y"),
+                ("Y", "D3"),
+                ("Z", "X2"),
+                ("Z", "Y"),
+            ]
+        )
+        self.assertTrue(set(proper_backdoor_graph.graph.edges).issubset(edges))
 
     def test_constructive_backdoor_criterion_should_hold(self):
         """Test whether the constructive criterion holds when it should."""
@@ -195,7 +196,7 @@ def test_constructive_backdoor_criterion_should_hold(self):
         self.assertTrue(causal_dag.constructive_backdoor_criterion(proper_backdoor_graph, xs, ys, zs))
 
     def test_constructive_backdoor_criterion_should_not_hold_not_d_separator_in_proper_backdoor_graph(
-            self,
+        self,
     ):
         """Test whether the constructive criterion fails when the adjustment set is not a d-separator."""
         causal_dag = CausalDAG(self.dag_dot_path)
@@ -204,7 +205,7 @@ def test_constructive_backdoor_criterion_should_not_hold_not_d_separator_in_prop
         self.assertFalse(causal_dag.constructive_backdoor_criterion(proper_backdoor_graph, xs, ys, zs))
 
     def test_constructive_backdoor_criterion_should_not_hold_descendent_of_proper_causal_path(
-            self,
+        self,
     ):
         """Test whether the constructive criterion holds when the adjustment set Z contains a descendent of a variable
         on a proper causal path between X and Y."""

tests/testing_tests/test_causal_test_suite.py

@@ -116,4 +116,3 @@ def test_execute_test_suite_multiple_estimators(self):
         causal_forrest_result = causal_test_case_result["CausalForestEstimator"][0]
         self.assertAlmostEqual(linear_regression_result.test_value.value, 4, delta=1e-1)
         self.assertAlmostEqual(causal_forrest_result.test_value.value, 4, delta=1e-1)
-