Add dataframe with first 10 observations

app.py

@@ -82,6 +82,7 @@ DATA_DICT, DATA_DESCRIPTION = load_hf_dataset()
 
 header = st.container()
 description = st.container()
+dataframe_head = st.container()
 dataset_statistics = st.container()
 
 with header:
@@ -91,6 +92,22 @@ with description:
     st.header("Dataset description")
     st.write(DATA_DESCRIPTION)
 
+with dataframe_head:
+    filtering_options = DATA_DICT["train"]["target"].unique().tolist()
+    filtering_options.append("All classes")
+
+    st.header("First 10 observations of train subset")
+    class_to_show = st.selectbox(
+        label="Select class to show", options=filtering_options
+    )
+    df_to_show = DATA_DICT["train"].copy()
+    if class_to_show == "All classes":
+        df_to_show = df_to_show.head(10)
+    else:
+        df_to_show = df_to_show.loc[df_to_show["target"] == class_to_show].head(10)
+    st.dataframe(df_to_show)
+    st.text_area(label="Latex code", value=df_to_show.style.to_latex())
+
 with dataset_statistics:
     st.header("Dataset statistics")
     st.subheader("Number of samples in each data split")
@@ -125,8 +142,8 @@ with dataset_statistics:
                 for k, df in DATA_DICT.items()
             ]
         )
-            .reset_index()
-            .rename({"index": "split_name"}, axis=1)
+        .reset_index()
+        .rename({"index": "split_name"}, axis=1)
     )
     plot_data = [
         go.Bar(