start tree map

app.py

@@ -3,6 +3,7 @@ import pandas as pd
 from graphs.model_market_share import create_stacked_area_chart, create_world_map, create_range_slider
 from graphs.leaderboard import create_leaderboard
 from graphs.model_characteristics import create_concentration_chart, create_line_plot
+from graphs.tree import generate_model_treemap
 
 # Initialize the app
 app = Dash()
@@ -105,6 +106,10 @@ download_arch_cumsum_line = create_line_plot(
     download_arch_cumsum_df, ARCHITECTURE_PLOT_CHOICES, PALETTE_0
 )
 
+tree_map = generate_model_treemap(
+    filtered_df
+)
+
 # App layout
 app.layout = html.Div(
     [
@@ -181,6 +186,9 @@ app.layout = html.Div(
                             filtered_df, country_concentration_df, author_concentration_df, model_concentration_df
                         )
                     ]),
+                    dcc.Tab(label='Model Tree Map', children=[
+                        dcc.Graph(figure=tree_map)
+                    ]),
                     dcc.Tab(label='Model Characteristics', children=[
                         dcc.Graph(id='language-concentration-chart'),
                         html.Div([

graphs/leaderboard.py

@@ -35,7 +35,7 @@ def create_leaderboard(filtered_df, country_df, developer_df, model_df, start_ti
 
     # Merge country info for developers/models
     developer_df = developer_df.merge(
-        filtered_df[["country", "author", "org_or_user", "model"]].drop_duplicates(subset=["author"]),
+        filtered_df[["country", "author", "org_or_user", "model", "downloads"]].drop_duplicates(subset=["author"]),
         left_on="metric", right_on="author", how="left"
     ).drop(columns=["metric"])
 
@@ -45,7 +45,11 @@ def create_leaderboard(filtered_df, country_df, developer_df, model_df, start_ti
     ).drop(columns=["metric"])
 
     # Rename metric columns
-    country_df = country_df.rename(columns={"metric": "country"})
+    # country_df = country_df.rename(columns={"metric": "country"})
+    country_df = country_df.merge(
+        filtered_df[["country", "downloads"]].drop_duplicates(subset=["country"]),
+        left_on="metric", right_on="country", how="left"
+    ).drop(columns=["metric"])
 
     # Filter by time
     start_time = start_time or country_df["time"].min()

graphs/tree.py

@@ -0,0 +1,15 @@
+import plotly.express as px
+import pandas as pd
+
+def generate_model_treemap(df, parent_col='merged_derived_from', child_col='model', value_col='downloads'):
+    df[parent_col] = str(df[parent_col][0])
+
+    fig = px.treemap(
+        df,
+        path=[parent_col, child_col],
+        values=value_col,
+        hover_data=['author', 'estimated_parameters', 'created'],
+        color=value_col,
+        color_continuous_scale='Viridis'
+    )
+    return fig