Update curated.py

curated.py

@@ -440,7 +440,7 @@ table_div_phil = Div(NotStr(table_html_phil), style="margin: 40px;")
 
 filtering_process = Div(
     Section(
-          P("This section contains the specific steps taken to filter all 14 curated source datasets.")  
+          H3("This section contains the specific filtering steps taken for all 14 curated datasets."),
     ),
     Section(
         Div(
@@ -965,7 +965,7 @@ for dataset in df.columns[1:]:
 # Update the layout
 fig.update_layout(
     barmode='stack',
-    title='Stacked Bar Chart of Line Reductions by Filter for Each Dataset',
+    title='Document Reduction by Filter for Each Dataset',
     xaxis_title='Filter',
     yaxis_title='Number of Lines',
     legend_title='Dataset',
@@ -1123,14 +1123,14 @@ def curated(request):
             copyright_disclaimer,
             plotly2fasthtml(treemap_chart),
             data_preprocessing_div,
-            plotly2fasthtml(diff2_stacked_bar),
             H2("Curated Sources Processing"),
-            H3("TALK ABOUT THE DIFFERENT FILTERS BEFORE HAND"),
+            plotly2fasthtml(diff2_stacked_bar),
+            P("The figure above provides a global view of the document filtering results. ~8% of documents were removed during these three steps."),
             filtering_process,
             data_preparation_div,
-            H2("Local Deduplication"),
-            local_dedup_text,
-            table_div_data_pipe, 
+            #H2("Local Deduplication"), are these numbers even right?
+            #local_dedup_text,
+            #table_div_data_pipe,
             id="inner-text",
 )