Add derived author and text

app.py

@@ -174,6 +174,7 @@ app.layout = dmc.MantineProvider(
     },
     children=[
         dcc.Store(id="selected-view", data="all_downloads"),
+        dcc.Store(id="derived-author-toggle", data=True),  # Store for toggle state
         html.Div(
             [
                 # Header
@@ -184,7 +185,7 @@ app.layout = dmc.MantineProvider(
                                 html.Div(
                                     [
                                         html.Div(
-                                            children="Visualizing the Open Model Ecosystem",
+                                            children="Economies of Open Intelligence",
                                             style={
                                                 "fontSize": 22,
                                                 "fontWeight": "700",
@@ -192,7 +193,7 @@ app.layout = dmc.MantineProvider(
                                             },
                                         ),
                                         html.Div(
-                                            children="An interactive dashboard to explore trends in open models on Hugging Face",
+                                            children="Tracing Power & Participation in the Model Ecosystem",
                                             style={
                                                 "fontSize": 13,
                                                 "marginTop": 6,
@@ -309,7 +310,7 @@ app.layout = dmc.MantineProvider(
                 # Intro / description below header (kept but styled to match layout)
                 # Title
                 html.Div(
-                    children="Model Leaderboard",
+                    children="The Open Model Leaderboard",
                     style={
                         "fontSize": 40,
                         "fontWeight": "700",
@@ -319,7 +320,7 @@ app.layout = dmc.MantineProvider(
                     },
                 ),
                 html.Div(
-                    children="The model leaderboard assesses concentrations of power across three hierarchies: countries, developers, and models. Explore how downloads are distributed among these groups and identify key players shaping the open model ecosystem on Hugging Face.",
+                    children="This leaderboard assesses concentrations of power in the open model ecosystem across three hierarchies: countries, developers, and models. Explore how downloads are distributed among these groups and identify key players shaping the open model ecosystem on Hugging Face.",
                     style={
                         "fontSize": 14,
                         "marginTop": 18,
@@ -335,7 +336,7 @@ app.layout = dmc.MantineProvider(
                         html.Div(
                             [
                                 html.Div(
-                                    "Select Window",
+                                    "Select Download View",
                                     style={
                                         "fontWeight": "700",
                                         "marginBottom": 8,
@@ -360,7 +361,7 @@ app.layout = dmc.MantineProvider(
                                     mb=10,
                                 ),
                                 html.Div(
-                                    "Choose whether to view all downloads or only filtered downloads for the leaderboard.",
+                                    "Choose whether to view all downloads or only those within one year of the model's creation date.",
                                     style={
                                         "fontSize": 13,
                                         "color": "#555",
@@ -371,7 +372,7 @@ app.layout = dmc.MantineProvider(
                                 html.Div(
                                     [
                                         html.Div(
-                                            "Select Mode",
+                                            "Select Author Type",
                                             style={
                                                 "fontWeight": "700",
                                                 "marginBottom": 8,
@@ -379,13 +380,14 @@ app.layout = dmc.MantineProvider(
                                             },
                                         ),
                                         dmc.Switch(
+                                            id="derived-author-switch",  # <-- add id
                                             color="#AC482A",
                                             label="Derived Authors",
                                             checked=True,
                                             mb=10,
                                         ),
                                         html.Div(
-                                            "Switch between absolute numbers and relative percentages for leaderboard values.",
+                                            "Toggle between viewing downloads by original authors or derived authors (those who forked or adapted models).",
                                             style={
                                                 "fontSize": 13,
                                                 "color": "#555",
@@ -418,7 +420,7 @@ app.layout = dmc.MantineProvider(
                                 ),
                                 time_slider,
                                 html.Div(
-                                    "Adjust the time range to filter leaderboard results by model release date.",
+                                    "Adjust the time range to filter leaderboard results by model download times.",
                                     style={
                                         "fontSize": 13,
                                         "color": "#555",
@@ -453,12 +455,10 @@ app.layout = dmc.MantineProvider(
                                                 html.Span("All Downloads", style={"fontWeight": "600", "color": "#AC482A"}),
                                                 " and ",
                                                 html.Span("Filtered Downloads", style={"fontWeight": "600", "color": "#AC482A"}),
-                                                " to compare ecosystem-wide vs. curated model trends. ",
-                                                "You can also toggle between ",
-                                                html.Span("Absolute", style={"fontWeight": "600", "color": "#AC482A"}),
-                                                " and ",
-                                                html.Span("Relative", style={"fontWeight": "600", "color": "#AC482A"}),
-                                                " to see raw counts or percentages."
+                                                " to compare overall popularity versus early interest after model release. ",
+                                                "You can also toggle ON ",
+                                                html.Span("Derived Authors", style={"fontWeight": "600", "color": "#AC482A"}),
+                                                " to see how derivative works contribute to developer influence.",
                                             ],
                                             style={
                                                 "fontSize": 13,
@@ -672,12 +672,12 @@ def _get_filtered_top_n_from_duckdb(slider_value, group_col, top_n, view="all_do
         SELECT 
             {group_col},
             CASE 
-                WHEN org_country_single = 'HF' THEN 'United States of America'
-                WHEN org_country_single = 'International' THEN 'International/Online'
-                WHEN org_country_single = 'Online' THEN 'International/Online'
+                WHEN org_country_single IN ('HF', 'United States of America') THEN 'United States of America'
+                WHEN org_country_single IN ('International', 'Online') THEN 'International/Online'
                 ELSE org_country_single
             END AS org_country_single,
             author,
+            derived_author,
             merged_country_groups_single,
             merged_modality,
             downloads,
@@ -701,6 +701,7 @@ def _get_filtered_top_n_from_duckdb(slider_value, group_col, top_n, view="all_do
             -- Pick first non-null metadata values for reference
             ANY_VALUE(b.org_country_single) AS org_country_single,
             ANY_VALUE(b.author) AS author,
+            ANY_VALUE(b.derived_author) AS derived_author,
             ANY_VALUE(b.merged_country_groups_single) AS merged_country_groups_single,
             ANY_VALUE(b.merged_modality) AS merged_modality,
             ANY_VALUE(b.model) AS model
@@ -727,6 +728,7 @@ def _leaderboard_callback_logic(
     default_label="▼ Show Top 50",
     chip_color="#F0F9FF",
     view="all_downloads",
+    derived_author_toggle=True,
 ):
     # Normalize label on first load
     if current_label is None:
@@ -746,8 +748,8 @@ def _leaderboard_callback_logic(
     # Get filtered and aggregated data directly from DuckDB
     df_filtered = _get_filtered_top_n_from_duckdb(slider_value, group_col, top_n, view=view)
 
-    # Process the already-filtered data
-    df, download_df = get_top_n_leaderboard(df_filtered, group_col, top_n)
+    # Process the already-filtered data - pass derived_author_toggle
+    df, download_df = get_top_n_leaderboard(df_filtered, group_col, top_n, derived_author_toggle=derived_author_toggle)
     return render_table_content(
         df, download_df, chip_color=chip_color, filename=filename
     ), new_label
@@ -756,6 +758,15 @@ def _leaderboard_callback_logic(
 # -- end helpers --
 
 
+# --- Callback to store derived author toggle state ---
+@app.callback(
+    Output("derived-author-toggle", "data"),
+    Input("derived-author-switch", "checked"),
+)
+def update_derived_author_toggle(checked):
+    return checked
+
+
 # Callbacks for interactivity (modularized)
 @app.callback(
     Output("top_countries-table", "children"),
@@ -763,9 +774,10 @@ def _leaderboard_callback_logic(
     Input("top_countries-toggle", "n_clicks"),
     Input("time-slider", "value"),
     Input("selected-view", "data"),
+    Input("derived-author-toggle", "data"),
     State("top_countries-toggle", "children"),
 )
-def update_top_countries(n_clicks, slider_value, selected_view, current_label):
+def update_top_countries(n_clicks, slider_value, selected_view, derived_author_toggle, current_label):
     return _leaderboard_callback_logic(
         n_clicks,
         slider_value,
@@ -775,6 +787,7 @@ def update_top_countries(n_clicks, slider_value, selected_view, current_label):
         default_label="▼ Show Top 50",
         chip_color="#F0F9FF",
         view=selected_view,
+        derived_author_toggle=derived_author_toggle,
     )
 
 
@@ -784,18 +797,22 @@ def update_top_countries(n_clicks, slider_value, selected_view, current_label):
     Input("top_developers-toggle", "n_clicks"),
     Input("time-slider", "value"),
     Input("selected-view", "data"),
+    Input("derived-author-toggle", "data"),
     State("top_developers-toggle", "children"),
 )
-def update_top_developers(n_clicks, slider_value, selected_view, current_label):
+def update_top_developers(n_clicks, slider_value, selected_view, derived_author_toggle, current_label):
+    # Use derived_author if toggle is True, else author
+    group_col = "derived_author" if derived_author_toggle else "author"
     return _leaderboard_callback_logic(
         n_clicks,
         slider_value,
         current_label,
-        group_col="author",
+        group_col=group_col,
         filename="top_developers",
         default_label="▼ Show Top 50",
         chip_color="#F0F9FF",
         view=selected_view,
+        derived_author_toggle=derived_author_toggle,
     )
 
 
@@ -805,9 +822,10 @@ def update_top_developers(n_clicks, slider_value, selected_view, current_label):
     Input("top_models-toggle", "n_clicks"),
     Input("time-slider", "value"),
     Input("selected-view", "data"),
+    Input("derived-author-toggle", "data"),
     State("top_models-toggle", "children"),
 )
-def update_top_models(n_clicks, slider_value, selected_view, current_label):
+def update_top_models(n_clicks, slider_value, selected_view, derived_author_toggle, current_label):
     return _leaderboard_callback_logic(
         n_clicks,
         slider_value,
@@ -817,6 +835,7 @@ def update_top_models(n_clicks, slider_value, selected_view, current_label):
         default_label="▼ Show More",
         chip_color="#F0F9FF",
         view=selected_view,
+        derived_author_toggle=derived_author_toggle,
     )
 
 
@@ -840,5 +859,3 @@ def update_selected_view(seg_value):
 # Run the app
 if __name__ == "__main__":
     app.run(debug=True)
-if __name__ == "__main__":
-    app.run(debug=True)

graphs/leaderboard.py

@@ -36,9 +36,11 @@ country_emoji_fallback = {
 meta_cols_map = {
     "org_country_single": ["org_country_single"],
     "author": ["org_country_single", "author", "merged_country_groups_single"],
+    "derived_author": ["org_country_single", "derived_author", "merged_country_groups_single"],
     "model": [
         "org_country_single",
         "author",
+        "derived_author",
         "merged_country_groups_single",
         "merged_modality",
         "total_downloads",
@@ -281,7 +283,7 @@ def render_table_content(
     )
 
 # Function to get top N leaderboard (now accepts pandas DataFrame from DuckDB query)
-def get_top_n_leaderboard(filtered_df, group_col, top_n=10):
+def get_top_n_leaderboard(filtered_df, group_col, top_n=10, derived_author_toggle=True):
     """
     Get top N entries for a leaderboard
     
@@ -289,6 +291,7 @@ def get_top_n_leaderboard(filtered_df, group_col, top_n=10):
         filtered_df: Pandas DataFrame (already filtered by time from DuckDB query)
         group_col: Column to group by
         top_n: Number of top entries to return
+        derived_author_toggle: Whether to use derived_author or author column
         
     Returns:
         tuple: (display_df, download_df)
@@ -322,7 +325,6 @@ def get_top_n_leaderboard(filtered_df, group_col, top_n=10):
         name_data = filtered_df[filtered_df[group_col] == name]
         meta_map[name] = {}
         download_map[name] = {}
-        
         for col in meta_cols:
             if col in name_data.columns:
                 unique_vals = name_data[col].unique()
@@ -350,8 +352,9 @@ def get_top_n_leaderboard(filtered_df, group_col, top_n=10):
                 flag_emoji = country_emoji_fallback.get(c, "🌍")
             chips.append((flag_emoji, c, "country"))
         
-        # Author
-        for a in meta.get("author", []):
+        # Author - use derived_author_toggle to determine which column
+        author_key = "derived_author" if derived_author_toggle else "author"
+        for a in meta.get(author_key, []):
             icon = company_icon_map.get(a, "")
             if icon == "":
                 if meta.get("merged_country_groups_single", ["User"])[0] != "User":
@@ -428,12 +431,12 @@ def get_top_n_from_duckdb(con, group_col, top_n=10, time_filter=None, view="all_
         SELECT 
             {group_col},
             CASE 
-                WHEN org_country_single = 'HF' THEN 'United States of America'
-                WHEN org_country_single = 'International' THEN 'International/Online'
-                WHEN org_country_single = 'Online' THEN 'International/Online'
+                WHEN org_country_single IN ('HF', 'United States of America') THEN 'United States of America'
+                WHEN org_country_single IN ('International', 'Online') THEN 'International/Online'
                 ELSE org_country_single
             END AS org_country_single,
             author,
+            derived_author,
             merged_country_groups_single,
             merged_modality,
             downloads,
@@ -457,6 +460,7 @@ def get_top_n_from_duckdb(con, group_col, top_n=10, time_filter=None, view="all_
             -- Pick first non-null metadata values for reference
             ANY_VALUE(b.org_country_single) AS org_country_single,
             ANY_VALUE(b.author) AS author,
+            ANY_VALUE(b.derived_author) AS derived_author,
             ANY_VALUE(b.merged_country_groups_single) AS merged_country_groups_single,
             ANY_VALUE(b.merged_modality) AS merged_modality,
             ANY_VALUE(b.model) AS model