Merge pull request #219 from lambda-feedback/tr124-restructuring

KarlLundengaard · web-flow · commit 0b1c61feae6f · 2025-08-04T06:57:57.000Z
Some minor updates after checking compatibility with SymbolicEqual
diff --git a/app/context/symbolic.py b/app/context/symbolic.py
@@ -316,7 +316,12 @@ def equality_equivalence(unused_input):
 
         # TODO: Remove when criteria for checking proportionality is implemented
         if isinstance(res, Equality) and isinstance(ans, Equality):
-            symbols_in_equality_ratio = ((res.args[0]-res.args[1])/(ans.args[0]-ans.args[1])).simplify().free_symbols
+            if (res.args[0]-res.args[1]).simplify() == 0:
+                symbols_in_equality_ratio = (ans.args[0]-ans.args[1]).simplify().free_symbols
+            elif (ans.args[0]-ans.args[1]).simplify() == 0:
+                symbols_in_equality_ratio = (res.args[0]-res.args[1]).simplify().free_symbols
+            else:
+                symbols_in_equality_ratio = ((res.args[0]-res.args[1])/(ans.args[0]-ans.args[1])).simplify().free_symbols
             result = {str(s) for s in symbols_in_equality_ratio}.issubset(parameters_dict["parsing_parameters"]["constants"])
         if result is True:
             return {
diff --git a/app/tests/example_tests.py b/app/tests/example_tests.py
@@ -4,6 +4,17 @@
 from ..evaluation import evaluation_function
 from ..preview import preview_function
 
+def create_diagram_for_documentation(filename, result):
+    for (index, graph) in enumerate(result["criteria_graphs_vis"].values()):
+        with open(filename+"_"+str(index)+".md", "w") as f:
+            #f.write(r'<!DOCTYPE html><html lang="en"><body><style>.mermaid {display: inline-flex;}</style>'+'\n')
+            f.write("```mermaid\n")
+            for g in result["criteria_graphs_vis"].values():
+                print(g)
+                #f.write('<pre class="mermaid">\n'+g+'\n</pre>\n')
+                f.write(g+"\n")
+            #f.write('<script type="module"> import mermaid from "https://cdn.jsdelivr.net/npm/mermaid@10/dist/mermaid.esm.min.mjs";</script></body></html>')
+            f.write("```\n")
 
 class TestEvaluationFunction():
     """
@@ -143,6 +154,18 @@ def test_checking_the_value_of_a_physical_quantity(self, response, answer, respo
         assert tags == set(result["tags"])
         assert result["is_correct"] == value
 
+    def test_checking_the_value_of_a_physical_quantity_and_create_diagram_for_docs(self):
+        params = {
+            "strict_syntax": False,
+            "elementary_functions": True,
+            "physical_quantity": True,
+        }
+        response = "2.00 kilometre/hour"
+        answer = "2.00 km/h"
+        result = evaluation_function(response, answer, params, include_test_data=True)
+        create_diagram_for_documentation("physical_quantity", result)
+        assert result["is_correct"] == True
+
     @pytest.mark.parametrize(
         "res,ans,convention,value",
         [
@@ -573,6 +596,13 @@ def test_custom_comparison_with_criteria_order(self, response, value, tags):
         }
         answer = "2*x^2"
         result = evaluation_function(response, answer, params, include_test_data=True)
+        create_diagram_for_documentation("custom_comparison_with_criteria_order", result)
+#        with open("diagrams.html", "w") as f:
+#            f.write(r'<!DOCTYPE html><html lang="en"><body><style>.mermaid {display: inline-flex;}</style>'+'\n')
+#            for g in result["criteria_graphs_vis"].values():
+#                print(g)
+#                f.write('<pre class="mermaid">\n'+g+'\n</pre>\n')
+#            f.write('<script type="module"> import mermaid from "https://cdn.jsdelivr.net/npm/mermaid@10/dist/mermaid.esm.min.mjs";</script></body></html>')
         assert result["is_correct"] is value
         assert set(tags) == set(result["tags"])
 
diff --git a/app/tests/physical_quantity_evaluation_tests.py b/app/tests/physical_quantity_evaluation_tests.py
@@ -349,18 +349,6 @@ def test_physical_quantity_with_atol(self):
         result = evaluation_function(res, ans, params, include_test_data=True)
         assert result["is_correct"] is True
 
-#    def test_rad_vs_Hz(self):
-#        ans = "28.53 rad/s"
-#        res = "4.5405 H"
-#        params = {
-#            'rtol': 0.03,
-#            'strict_syntax': False,
-#            'physical_quantity': True,
-#            'elementary_functions': True,
-#        }
-#        result = evaluation_function(res, ans, params, include_test_data=True)
-#        assert result["is_correct"] is True
-
     def test_tolerance_given_as_string(self):
         ans = "4.52 kg"
         res = "13.74 kg"
diff --git a/app/tests/symbolic_evaluation_tests.py b/app/tests/symbolic_evaluation_tests.py
@@ -1970,6 +1970,25 @@ def test_input_symbols_takes_priority_when_containing_elementary_function_names_
         result = evaluation_function(response, answer, params)
         assert result["is_correct"] is True
 
+    def test_equality_with_both_sides_equal_in_response(self):
+        response = "(1/3)^(1/4)= (1/3)^(1/4)"
+        answer = "Vbar=(1/3)^(1/4)"
+        params = {
+            'atol': 0,
+            'rtol': 0,
+            'strict_syntax': False,
+            'elementary_functions': True,
+            'symbols': {
+                'LtDmax': {'aliases': [''], 'latex': '$(L/D)_{max}$'},
+                'etap': {'aliases': [''], 'latex': '$\\eta_p$'},
+                'sigma': {'aliases': [''], 'latex': '$\\sigma$'},
+                'Vbar': {'aliases': [''], 'latex': '$\\overline{V}$'},
+                'Pbar': {'aliases': [''], 'latex': '$\\overline{P}$'},
+            },
+        }
+        result = evaluation_function(response, answer, params)
+        assert result["is_correct"] is False
+        
     def test_integral(self):
         response = "6y"
         answer = "int(3*x*y, (x, 0, 2))"
diff --git a/app/utility/criteria_graph_utilities.py b/app/utility/criteria_graph_utilities.py
@@ -180,16 +180,23 @@ def json(self):
         return str(json.dumps(graph))
 
     def mermaid(self):
-        output = ["graph TD"]
+        output = ["flowchart TD"]
+        linebreak = '<br/>---<br/>'
         edges = set()
         sufficiencies = set()
         node_sets = [self.evaluations, self.criteria, self.outputs]
         node_styles = [evaluation_style, criterion_style, output_style]
+        node_keys = {}
+        for set_index, nodes in enumerate(node_sets):
+            index = 0
+            for (label, node) in nodes.items():
+                node_keys.update({label: "N_"+str(set_index)+"_"+str(index)})
+                index += 1
         for set_index, nodes in enumerate(node_sets):
             style = node_styles[set_index]
             for (label, node) in nodes.items():
-                output.append(label+style[0]+'"'+node.summary+'"'+style[1])
-                edges.update([(edge.source.label, edge.target.label) for edge in node.outgoing+node.incoming])
+                output.append(node_keys[label]+style[0]+'"'+label+linebreak+node.details+'"'+style[1])
+                edges.update([(node_keys[edge.source.label], node_keys[edge.target.label]) for edge in node.outgoing+node.incoming])
                 if self.sufficiencies.get(label, None) is not None:
                     sufficiencies.update([(label, sufficiency) for sufficiency in self.sufficiencies.get(label, None)])
         for edge in edges:
diff --git a/app/utility/evaluation_result_utilities.py b/app/utility/evaluation_result_utilities.py
@@ -5,6 +5,7 @@ def __init__(self):
         self._feedback = []  # A list that will hold all feedback items
         self._feedback_tags = {}  # A dictionary that holds a list with indices to all feedback items with the same tag
         self._criteria_graphs = {}
+        self._criteria_graphs_vis = {}
         self.latex = ""
         self.simplified = ""
 
@@ -41,6 +42,7 @@ def add_feedback_from_tags(self, tags, graph, custom_feedback=None):
 
     def add_criteria_graph(self, name, graph):
         self._criteria_graphs.update({name: graph.json()})
+        self._criteria_graphs_vis.update({name: graph.mermaid()})
 
     def _serialise_feedback(self) -> str:
         feedback = []
@@ -56,6 +58,7 @@ def serialise(self, include_test_data=False) -> dict:
         out.update(dict(tags=list(self._feedback_tags.keys())))
         if include_test_data is True:
             out.update(dict(criteria_graphs=self._criteria_graphs))
+            out.update(dict(criteria_graphs_vis=self._criteria_graphs_vis))
         if self.latex is not None:
             out.update(dict(response_latex=self.latex))
         if self.simplified is not None:
diff --git a/custom_comparison_with_criteria_order_0.md b/custom_comparison_with_criteria_order_0.md
@@ -0,0 +1,26 @@
+```mermaid
+flowchart TD
+	N_0_0(["answer <= response<br/>---<br/>Checks if answer <= response is true."])
+	N_1_0["answer <= response_TRUE<br/>---<br/>answer <= response is true."]
+	N_1_1["answer <= response_FALSE<br/>---<br/>answer <= response is false."]
+	N_1_2["answer <= response_UNKNOWN<br/>---<br/>answer <= response is false."]
+	N_2_0{{"END<br/>---<br/>Evaluation completed."}}
+	N_0_0 --> N_1_2
+	N_1_0 --> N_2_0
+	N_1_1 --> N_2_0
+	N_0_0 --> N_1_0
+	N_0_0 --> N_1_1
+	N_1_2 --> N_2_0
+flowchart TD
+	N_0_0(["2+answer > response<br/>---<br/>Checks if 2+answer > response is true."])
+	N_1_0["2+answer > response_TRUE<br/>---<br/>2+answer > response is true."]
+	N_1_1["2+answer > response_FALSE<br/>---<br/>2+answer > response is false."]
+	N_1_2["2+answer > response_UNKNOWN<br/>---<br/>2+answer > response is false."]
+	N_2_0{{"END<br/>---<br/>Evaluation completed."}}
+	N_0_0 --> N_1_2
+	N_1_0 --> N_2_0
+	N_1_1 --> N_2_0
+	N_0_0 --> N_1_0
+	N_0_0 --> N_1_1
+	N_1_2 --> N_2_0
+```
diff --git a/custom_comparison_with_criteria_order_1.md b/custom_comparison_with_criteria_order_1.md
@@ -0,0 +1,26 @@
+```mermaid
+flowchart TD
+	N_0_0(["answer <= response<br/>---<br/>Checks if answer <= response is true."])
+	N_1_0["answer <= response_TRUE<br/>---<br/>answer <= response is true."]
+	N_1_1["answer <= response_FALSE<br/>---<br/>answer <= response is false."]
+	N_1_2["answer <= response_UNKNOWN<br/>---<br/>answer <= response is false."]
+	N_2_0{{"END<br/>---<br/>Evaluation completed."}}
+	N_0_0 --> N_1_2
+	N_1_0 --> N_2_0
+	N_1_1 --> N_2_0
+	N_0_0 --> N_1_0
+	N_0_0 --> N_1_1
+	N_1_2 --> N_2_0
+flowchart TD
+	N_0_0(["2+answer > response<br/>---<br/>Checks if 2+answer > response is true."])
+	N_1_0["2+answer > response_TRUE<br/>---<br/>2+answer > response is true."]
+	N_1_1["2+answer > response_FALSE<br/>---<br/>2+answer > response is false."]
+	N_1_2["2+answer > response_UNKNOWN<br/>---<br/>2+answer > response is false."]
+	N_2_0{{"END<br/>---<br/>Evaluation completed."}}
+	N_0_0 --> N_1_2
+	N_1_0 --> N_2_0
+	N_1_1 --> N_2_0
+	N_0_0 --> N_1_0
+	N_0_0 --> N_1_1
+	N_1_2 --> N_2_0
+```
diff --git a/physical_quantity_0.md b/physical_quantity_0.md
@@ -0,0 +1,41 @@
+```mermaid
+flowchart TD
+	N_0_0(["response matches answer<br/>---<br/>Converts QUANTITY: response tags:  {} and QUANTITY: answer tags:  {} match to a common set of base units and compares their values."])
+	N_0_1(["response matches answer_DIMENSION_MATCH<br/>---<br/>Do the dimensions of QUANTITY: response tags:  {} and QUANTITY: answer tags:  {} match?"])
+	N_0_2(["response matches answer_UNIT_COMPARISON<br/>---<br/>Compares how similar the units of QUANTITY: response tags:  {} and QUANTITY: answer tags:  {} are."])
+	N_1_0["response matches answer_TRUE<br/>---<br/>The quantities QUANTITY: response tags:  {} and QUANTITY: answer tags:  {} match."]
+	N_1_1["response matches answer_FALSE<br/>---<br/>The quantities QUANTITY: response tags:  {} and QUANTITY: answer tags:  {} does not match."]
+	N_1_2["response matches answer_MISSING_VALUE<br/>---<br/>The response is missing a value."]
+	N_1_3["response matches answer_UNEXPECTED_VALUE<br/>---<br/>The response is expected only have unit(s), no value."]
+	N_1_4["response matches answer_MISSING_UNIT<br/>---<br/>The response is missing unit(s)."]
+	N_1_5["response matches answer_UNEXPECTED_UNIT<br/>---<br/>The response is expected to be a value without unit(s)."]
+	N_1_6["response matches answer_DIMENSION_MATCH_TRUE<br/>---<br/>The quantities QUANTITY: response tags:  {} and QUANTITY: answer tags:  {} have the same dimensions."]
+	N_1_7["response matches answer_DIMENSION_MATCH_FALSE<br/>---<br/>The quantities QUANTITY: response tags:  {} and QUANTITY: answer tags:  {} have different dimensions."]
+	N_1_8["response matches answer_UNIT_COMPARISON_IDENTICAL<br/>---<br/>The units of quantities QUANTITY: response tags:  {} and QUANTITY: answer tags:  {} are identical."]
+	N_1_9["response matches answer_UNIT_COMPARISON_SIMILAR<br/>---<br/>The units of quantities QUANTITY: response tags:  {} and QUANTITY: answer tags:  {} are similar."]
+	N_1_10["response matches answer_UNIT_COMPARISON_PREFIX_IS_LARGE<br/>---<br/>The units of QUANTITY: response tags:  {} are at least 1000 times greater than the units of QUANTITY: answer tags:  {}."]
+	N_1_11["response matches answer_UNIT_COMPARISON_PREFIX_IS_SMALL<br/>---<br/>The units of QUANTITY: response tags:  {} are at least 1000 times smaller than the units of QUANTITY: answer tags:  {}."]
+	N_2_0{{"END<br/>---<br/>Evaluation completed."}}
+	N_0_1 --> N_1_7
+	N_0_2 --> N_1_9
+	N_0_2 --> N_1_11
+	N_1_10 --> N_2_0
+	N_1_1 --> N_0_1
+	N_1_6 --> N_2_0
+	N_0_0 --> N_1_5
+	N_1_11 --> N_2_0
+	N_1_0 --> N_0_2
+	N_0_1 --> N_1_6
+	N_0_2 --> N_1_8
+	N_1_7 --> N_2_0
+	N_0_2 --> N_1_10
+	N_0_0 --> N_1_3
+	N_0_0 --> N_1_1
+	N_1_4 --> N_2_0
+	N_0_0 --> N_1_4
+	N_0_0 --> N_1_0
+	N_1_2 --> N_2_0
+	N_1_5 --> N_2_0
+	N_1_3 --> N_2_0
+	N_0_0 --> N_1_2
+```
