Add class distribution dataframe to aspectemo dataset

clarin_datasets/aspectemo_dataset.py

@@ -48,6 +48,7 @@ class AspectEmoDataset(DatasetToShow):
         header = st.container()
         description = st.container()
         dataframe_head = st.container()
+        class_distribution = st.container()
 
         with header:
             st.title(self.dataset_name)
@@ -62,3 +63,25 @@ class AspectEmoDataset(DatasetToShow):
             st.header("First 10 observations of the dataset")
             st.dataframe(df_to_show)
             st.text_area(label="Latex code", value=df_to_show.style.to_latex())
+
+        class_distribution_dict = {}
+        for subset in self.subsets:
+            all_labels = self.data_dict[subset]["labels"].tolist()
+            all_labels = [x for subarray in all_labels for x in subarray if x != 0]
+            all_labels = pd.Series(all_labels)
+            class_distribution_dict[subset] = (
+                all_labels.value_counts(normalize=True)
+                .sort_index()
+                .reset_index()
+                .rename({"index": "class", 0: subset}, axis="columns")
+            )
+
+        class_distribution_df = pd.merge(
+            class_distribution_dict["train"],
+            class_distribution_dict["test"],
+            on="class",
+        )
+        with class_distribution:
+            st.header("Class distribution in each subset (without '0')")
+            st.dataframe(class_distribution_df)
+            st.text_area(label="LaTeX code", value=class_distribution_df.style.to_latex())