Added Interestingness Scoring for Colored Bar and Line charts

lux/executor/PandasExecutor.py

@@ -200,6 +200,11 @@ def execute_aggregate(view: Vis,isFiltered = True):
                     for col in columns[1:]:
                         view.data[col] = view.data[col].fillna(0)
                     assert len(list(view.data[groupby_attr.attribute])) == len(all_attr_vals), f"Aggregated data missing values compared to original range of values of `{groupby_attr.attribute}`."
+            #need to compute the statistics and metadata for the view's data if no new rows were added
+            else:
+                if view.data.cardinality is None and has_color:
+                    view.data.compute_stats()
+                    view.data.compute_dataset_metadata()
             view.data = view.data.sort_values(by=groupby_attr.attribute, ascending=True)
             view.data = view.data.reset_index()
             view.data = view.data.drop(columns="index")

lux/interestingness/interestingness.py

@@ -90,8 +90,29 @@ def interestingness(vis:Vis ,ldf:LuxDataFrame) -> int:
 	elif (n_msr == 3):
 		return 0.1	
 	# colored line and barchart cases
-	elif ((vis.mark == "line" or vis.mark == "bar") and n_dim == 2):
-		return 0.2
+	elif (vis.mark == "line" and n_dim == 2):
+		return 0.15
+	elif (vis.mark == "bar" and n_dim == 2):
+		from scipy.stats import chi2_contingency
+		measure_column = vis.get_attr_by_data_model("measure")[0].attribute
+		dimension_columns = vis.get_attr_by_data_model("dimension")
+
+		groupby_column = dimension_columns[0].attribute
+		color_column = dimension_columns[1].attribute
+
+		contingency_table = []
+		groupby_cardinality = vis.data.cardinality[groupby_column]
+		groupby_unique_vals = vis.data.unique_values[groupby_column]
+		for c in range(0, groupby_cardinality):
+			contingency_table.append(vis.data[vis.data[groupby_column] == groupby_unique_vals[c]][measure_column])
+		score = 0.12
+		#ValueError results if an entire column of the contingency table is 0, can happen if an applied filter results in
+		#a category having no counts
+		try:
+			score = min(0.13, chi2_contingency(contingency_table)[0])
+		except ValueError:
+			pass
+		return(score)
 	# Default
 	else:
 		return -1

tests/test_interestingness.py

@@ -140,6 +140,22 @@ def test_interestingness_1_1_1():
     #check for top recommended Filter graph score is not none
     assert interestingness(df.recommendation['Filter'][0],df) != None
 
+def test_interestingness_1_2_0():
+    from lux.vis.Vis import Vis
+    from lux.vis.Vis import Clause
+    from lux.interestingness.interestingness import interestingness
+
+    df = pd.read_csv("lux/data/car.csv")
+    y_clause = Clause(attribute = "Name", channel = "y")
+    color_clause = Clause(attribute = 'Cylinders', channel = "color")
+
+    new_vis = Vis([y_clause, color_clause])
+    new_vis.refresh_source(df)
+    new_vis
+    #assert(len(new_vis.data)==color_cardinality*group_by_cardinality)
+
+    assert(interestingness(new_vis, df)==0.13)
+
 def test_interestingness_0_2_0():
     df = pd.read_csv("lux/data/car.csv")
     df["Year"] = pd.to_datetime(df["Year"], format='%Y')