Spaces:
Runtime error
Runtime error
Commit
·
af40751
1
Parent(s):
8256554
Show plots on click
Browse files
app.py
CHANGED
|
@@ -318,40 +318,53 @@ def create_leaderboard_from_results(elo_results, model_table_df, show_plot, show
|
|
| 318 |
""",
|
| 319 |
elem_id="leaderboard_markdown"
|
| 320 |
)
|
|
|
|
|
|
|
| 321 |
fig_id = 1
|
| 322 |
if show_language_plot:
|
| 323 |
gr.Markdown(
|
| 324 |
f"#### Figure {fig_id}: Battle counts for the Top 15 Languages"
|
| 325 |
)
|
| 326 |
-
plot_0 = gr.Plot(
|
| 327 |
fig_id += 1
|
| 328 |
with gr.Row():
|
| 329 |
with gr.Column():
|
| 330 |
gr.Markdown(
|
| 331 |
f"#### Figure {fig_id}: Fraction of Model A Wins for All Non-tied A vs. B Battles"
|
| 332 |
)
|
| 333 |
-
plot_1 = gr.Plot(
|
| 334 |
fig_id += 1
|
| 335 |
with gr.Column():
|
| 336 |
gr.Markdown(
|
| 337 |
f"#### Figure {fig_id}: Battle Count for Each Combination of Models (without Ties)"
|
| 338 |
)
|
| 339 |
-
plot_2 = gr.Plot(
|
| 340 |
fig_id += 1
|
| 341 |
with gr.Row():
|
| 342 |
with gr.Column():
|
| 343 |
gr.Markdown(
|
| 344 |
f"#### Figure {fig_id}: Confidence Intervals on Model Strength (via Bootstrapping)"
|
| 345 |
)
|
| 346 |
-
plot_3 = gr.Plot(
|
| 347 |
fig_id += 1
|
| 348 |
with gr.Column():
|
| 349 |
gr.Markdown(
|
| 350 |
f"#### Figure {fig_id}: Average Win Rate Against All Other Models (Assuming Uniform Sampling and No Ties)"
|
| 351 |
)
|
| 352 |
-
plot_4 = gr.Plot(
|
| 353 |
fig_id += 1
|
| 354 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 355 |
return p1, p2, p3, p4, plot_1, plot_2, plot_3, plot_4
|
| 356 |
|
| 357 |
def build_leaderboard_tab(elo_results_file, leaderboard_table_file, show_plot=False):
|
|
|
|
| 318 |
""",
|
| 319 |
elem_id="leaderboard_markdown"
|
| 320 |
)
|
| 321 |
+
|
| 322 |
+
show_plot_btn = gr.Button("Show plots")
|
| 323 |
fig_id = 1
|
| 324 |
if show_language_plot:
|
| 325 |
gr.Markdown(
|
| 326 |
f"#### Figure {fig_id}: Battle counts for the Top 15 Languages"
|
| 327 |
)
|
| 328 |
+
plot_0 = gr.Plot()
|
| 329 |
fig_id += 1
|
| 330 |
with gr.Row():
|
| 331 |
with gr.Column():
|
| 332 |
gr.Markdown(
|
| 333 |
f"#### Figure {fig_id}: Fraction of Model A Wins for All Non-tied A vs. B Battles"
|
| 334 |
)
|
| 335 |
+
plot_1 = gr.Plot()
|
| 336 |
fig_id += 1
|
| 337 |
with gr.Column():
|
| 338 |
gr.Markdown(
|
| 339 |
f"#### Figure {fig_id}: Battle Count for Each Combination of Models (without Ties)"
|
| 340 |
)
|
| 341 |
+
plot_2 = gr.Plot()
|
| 342 |
fig_id += 1
|
| 343 |
with gr.Row():
|
| 344 |
with gr.Column():
|
| 345 |
gr.Markdown(
|
| 346 |
f"#### Figure {fig_id}: Confidence Intervals on Model Strength (via Bootstrapping)"
|
| 347 |
)
|
| 348 |
+
plot_3 = gr.Plot()
|
| 349 |
fig_id += 1
|
| 350 |
with gr.Column():
|
| 351 |
gr.Markdown(
|
| 352 |
f"#### Figure {fig_id}: Average Win Rate Against All Other Models (Assuming Uniform Sampling and No Ties)"
|
| 353 |
)
|
| 354 |
+
plot_4 = gr.Plot()
|
| 355 |
fig_id += 1
|
| 356 |
|
| 357 |
+
def get_plots(*args):
|
| 358 |
+
if show_language_plot:
|
| 359 |
+
return p0, p1, p2, p3, p4
|
| 360 |
+
else:
|
| 361 |
+
return p1, p2, p3, p4
|
| 362 |
+
|
| 363 |
+
if show_language_plot:
|
| 364 |
+
show_plot_btn.click(fn=get_plots, outputs=[plot_0, plot_1, plot_2, plot_3, plot_4])
|
| 365 |
+
else:
|
| 366 |
+
show_plot_btn.click(fn=get_plots, outputs=[plot_1, plot_2, plot_3, plot_4])
|
| 367 |
+
|
| 368 |
return p1, p2, p3, p4, plot_1, plot_2, plot_3, plot_4
|
| 369 |
|
| 370 |
def build_leaderboard_tab(elo_results_file, leaderboard_table_file, show_plot=False):
|