Spaces:
Running
Running
File size: 25,624 Bytes
3e92a7d cdbf3c3 3e92a7d cdbf3c3 3e92a7d a7cae30 3e92a7d db5c9f8 57cca99 db5c9f8 57cca99 db5c9f8 57cca99 db5c9f8 57cca99 db5c9f8 57cca99 db5c9f8 57cca99 db5c9f8 57cca99 db5c9f8 57cca99 db5c9f8 57cca99 db5c9f8 57cca99 db5c9f8 57cca99 db5c9f8 57cca99 cdbf3c3 57cca99 a868a88 29fcacd 57cca99 cdbf3c3 57cca99 cdbf3c3 57cca99 3da301f a7cae30 cdbf3c3 a7cae30 cdbf3c3 a7cae30 cdbf3c3 a7cae30 76eb2d0 f9a8fe7 cdbf3c3 f9a8fe7 76eb2d0 f9a8fe7 76eb2d0 f9a8fe7 76eb2d0 f9a8fe7 76eb2d0 f9a8fe7 76eb2d0 f9a8fe7 76eb2d0 f9a8fe7 76eb2d0 f9a8fe7 7017256 76eb2d0 7017256 76eb2d0 7017256 76eb2d0 7017256 76eb2d0 7017256 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 |
# import streamlit as st
# import pandas as pd
# import altair as alt
# # Set page layout to wide mode
# st.set_page_config(
# page_title="PathVLM-Eval Leaderboard",
# page_icon="🏆",
# layout="wide"
# )
# # Load the leaderboard data
# df = pd.read_csv("leaderboard.csv")
# # Add title and description
# st.title("PathVLM-Eval Leaderboard 🏆")
# st.markdown("""
# Welcome to the **PathVLMs Leaderboard**! This leaderboard displays evaluation results for various Vision-Language Models (VLMs) in Pathology, focusing on multiple-choice questions (MCQs), answers, and explanations.
# You can search, filter, and visualize metrics for better insights.
# """)
# # Sidebar Filters
# with st.sidebar:
# st.subheader("Filters")
# # Search by model name (fuzzy search)
# search_query = st.text_input("Search for Model Name", value="", placeholder="e.g., llava")
# # Filter by model size
# model_sizes = df['Params (B)'].unique()
# selected_sizes = st.multiselect("Select Model Sizes", options=model_sizes, default=model_sizes)
# # Filter by model type
# if 'Language Model' in df.columns:
# model_types = df['Language Model'].unique()
# selected_types = st.multiselect("Select Model Types", options=model_types, default=model_types)
# else:
# selected_types = []
# # Apply Filters
# filtered_df = df[
# (df['Params (B)'].isin(selected_sizes)) &
# (df['Language Model'].isin(selected_types) if selected_types else True) &
# (df['Method'].str.contains(search_query, case=False, na=False))
# ]
# # Main Leaderboard Section
# st.subheader("Leaderboard Table")
# if filtered_df.empty:
# st.warning("No results found. Try adjusting the filters.")
# else:
# # Display table in wide layout
# st.dataframe(
# filtered_df,
# height=600, # Adjust table height
# width=1600 # Adjust table width
# )
# # Visualization of selected metric
# st.subheader("Performance Metrics Visualization")
# metric = st.selectbox("Select Metric to Visualize", options=filtered_df.columns[5:])
# # Visualization Chart
# chart = alt.Chart(filtered_df).mark_bar().encode(
# x=alt.X('Method', sort=alt.EncodingSortField(field=metric, order='descending'), title="Model"),
# y=alt.Y(metric, title=metric),
# color='Method',
# tooltip=['Method', metric]
# ).properties(
# width=1400, # Full width
# height=600 # Increased height
# )
# st.altair_chart(chart, use_container_width=True)
# # Highlight Top N Models
# st.subheader("Highlight Top N Models")
# top_n = st.slider("Number of Top Models", min_value=1, max_value=len(filtered_df), value=5)
# top_models_df = filtered_df.nlargest(top_n, metric)
# top_chart = alt.Chart(top_models_df).mark_bar().encode(
# x=alt.X('Method', title="Model"),
# y=alt.Y(metric, title=metric),
# color='Method',
# tooltip=['Method', metric]
# ).properties(
# width=1400, # Full width
# height=400 # Adjusted height for smaller chart
# )
# st.altair_chart(top_chart, use_container_width=True)
# # Download Button
# @st.cache
# def convert_df_to_csv(dataframe):
# return dataframe.to_csv(index=False).encode('utf-8')
# csv_data = convert_df_to_csv(filtered_df)
# st.download_button(
# label="Download Filtered Results",
# data=csv_data,
# file_name="filtered_leaderboard.csv",
# mime="text/csv"
# )
# interactive Bubble plot
# import streamlit as st
# import pandas as pd
# import altair as alt
# # Set page layout to wide mode
# st.set_page_config(
# page_title="PathVLMs Leaderboard",
# page_icon="🏆",
# layout="wide"
# )
# # Load the leaderboard data
# df = pd.read_csv("leaderboard.csv")
# # Add title and description
# st.title("PathVLMs Leaderboard 🏆")
# st.markdown("""
# Welcome to the **PathVLMs Leaderboard**! This leaderboard displays evaluation results for various Vision-Language Models (VLMs) in Pathology, focusing on multiple-choice questions (MCQs), answers, and explanations.
# You can search, filter, and visualize metrics for better insights.
# """)
# # Sidebar Filters
# with st.sidebar:
# st.subheader("Filters")
# # Search by model name (fuzzy search)
# search_query = st.text_input("Search for Model Name", value="", placeholder="e.g., llava")
# # Filter by model size
# model_sizes = df['Params (B)'].unique()
# selected_sizes = st.multiselect("Select Model Sizes", options=model_sizes, default=model_sizes)
# # Filter by model type
# if 'Language Model' in df.columns:
# model_types = df['Language Model'].unique()
# selected_types = st.multiselect("Select Model Types", options=model_types, default=model_types)
# else:
# selected_types = []
# # Apply Filters
# filtered_df = df[
# (df['Params (B)'].isin(selected_sizes)) &
# (df['Language Model'].isin(selected_types) if selected_types else True) &
# (df['Method'].str.contains(search_query, case=False, na=False))
# ]
# # Main Leaderboard Section
# st.subheader("Leaderboard Table")
# if filtered_df.empty:
# st.warning("No results found. Try adjusting the filters.")
# else:
# # Display table in wide layout
# st.dataframe(
# filtered_df,
# height=600, # Adjust table height
# width=1600 # Adjust table width
# )
# # Visualization of selected metric
# st.subheader("Performance Metrics Visualization")
# metric = st.selectbox("Select Metric to Visualize", options=filtered_df.columns[5:])
# # Visualization Chart
# chart = alt.Chart(filtered_df).mark_bar().encode(
# x=alt.X('Method', sort=alt.EncodingSortField(field=metric, order='descending'), title="Model"),
# y=alt.Y(metric, title=metric),
# color='Method',
# tooltip=['Method', metric]
# ).properties(
# width=1400, # Full width
# height=600 # Increased height
# )
# st.altair_chart(chart, use_container_width=True)
# # Interactive Bubble Plot: Metric vs. Model Size
# st.subheader("Interactive Bubble Plot: Metric vs. Model Size")
# bubble_metric = st.selectbox("Select Metric for Bubble Plot", options=filtered_df.columns[5:], index=0)
# if bubble_metric in filtered_df.columns and 'Params (B)' in filtered_df.columns:
# interactive_bubble_chart = alt.Chart(filtered_df).mark_circle(size=200).encode(
# x=alt.X('Params (B):Q', title="Model Size (in Billion Params)"),
# y=alt.Y(f'{bubble_metric}:Q', title=bubble_metric),
# size=alt.Size('Params (B):Q', legend=None),
# color=alt.Color('Method:N', title="Model"),
# tooltip=['Method', 'Params (B)', bubble_metric]
# ).properties(
# width=800,
# height=600
# )
# st.altair_chart(interactive_bubble_chart, use_container_width=True)
# else:
# st.warning(f"Columns '{bubble_metric}' and 'Params (B)' are required for the bubble plot.")
# # # Highlight Top N Models
# # st.subheader("Highlight Top N Models")
# # top_n = st.slider("Number of Top Models", min_value=1, max_value=len(filtered_df), value=5)
# # top_models_df = filtered_df.nlargest(top_n, metric)
# # top_chart = alt.Chart(top_models_df).mark_bar().encode(
# # x=alt.X('Method', title="Model"),
# # y=alt.Y(metric, title=metric),
# # color='Method',
# # tooltip=['Method', metric]
# # ).properties(
# # width=1400, # Full width
# # height=400 # Adjusted height for smaller chart
# # )
# # st.altair_chart(top_chart, use_container_width=True)
# # Highlight Top N Models
# st.subheader("Highlight Top N Models")
# top_n = st.slider("Number of Top Models", min_value=1, max_value=len(filtered_df), value=5)
# top_models_df = filtered_df.nlargest(top_n, metric)
# top_chart = alt.Chart(top_models_df).mark_bar().encode(
# x=alt.X('Method', title="Model"),
# y=alt.Y(metric, title=metric),
# color='Method',
# tooltip=['Method', metric]
# ).properties(
# width=1400, # Full width
# height=400 # Adjusted height for smaller chart
# )
# st.altair_chart(top_chart, use_container_width=True)
# # Download Button
# @st.cache
# def convert_df_to_csv(dataframe):
# return dataframe.to_csv(index=False).encode('utf-8')
# csv_data = convert_df_to_csv(filtered_df)
# st.download_button(
# label="Download Filtered Results",
# data=csv_data,
# file_name="filtered_leaderboard.csv",
# mime="text/csv"
# )
# inteactive bubble plot and pagination
import streamlit as st
import pandas as pd
import altair as alt
# Set page layout to wide mode
st.set_page_config(
page_title="PathVLM-Eval Leaderboard",
page_icon="🏆",
layout="wide"
)
# Load the leaderboard data
df = pd.read_csv("updated-leaderboard.csv")
print(df.columns)
# Add title and description
st.title("PathVLM-Eval Leaderboard 🏆")
st.markdown("""
Welcome to the **PathVLM-Eval Leaderboard**! This leaderboard displays evaluation results for various Vision-Language Models (VLMs) in Pathology, focusing on multiple-choice questions (MCQs), answers, and explanations.
You can search, filter, and sort the leaderboard dynamically by score for better insights.
""")
# Sidebar Filters
with st.sidebar:
st.subheader("Filters")
# Search by model name (fuzzy search)
search_query = st.text_input("Search for Model Name", value="", placeholder="e.g., llava")
# Filter by model size
model_sizes = df['Params (B)'].unique()
selected_sizes = st.multiselect("Select Model Sizes", options=model_sizes, default=model_sizes)
# Filter by model type
if 'Language Model' in df.columns:
model_types = df['Language Model'].unique()
selected_types = st.multiselect("Select Model Types", options=model_types, default=model_types)
else:
selected_types = []
# Apply Filters
filtered_df = df[
(df['Params (B)'].isin(selected_sizes)) &
(df['Language Model'].isin(selected_types) if selected_types else True) &
(df['Method'].str.contains(search_query, case=False, na=False))
]
# Add Sorting Option
st.subheader("Leaderboard Table with Dynamic Sorting")
if filtered_df.empty:
st.warning("No results found. Try adjusting the filters.")
else:
# Dropdown to select the score column to sort by
sort_column = st.selectbox(
"Sort by Score Column",
options=filtered_df.columns[5:], # Only score-related columns
index=0 # Default to the first score column
)
# Sort the dataframe by the selected column in descending order
sorted_df = filtered_df.sort_values(by=sort_column, ascending=False)
# Display the sorted table
st.dataframe(sorted_df, use_container_width=True)
# Visualization of selected metric
st.subheader("Performance Metrics Visualization")
metric = st.selectbox("Select Metric to Visualize", options=filtered_df.columns[5:])
# Visualization Chart
chart = alt.Chart(sorted_df).mark_bar().encode(
x=alt.X('Method', sort=alt.EncodingSortField(field=metric, order='descending'), title="Model"),
y=alt.Y(metric, title=metric),
color='Method',
tooltip=['Method', metric]
).properties(
width=1400, # Full width
height=600 # Increased height
)
st.altair_chart(chart, use_container_width=True)
# Bubble Plot: Metric vs. Model Size
st.subheader("Interactive Bubble Plot: Metric vs. Model Size")
bubble_metric = st.selectbox("Select Metric for Bubble Plot", options=filtered_df.columns[5:], index=0)
if bubble_metric in filtered_df.columns and 'Params (B)' in filtered_df.columns:
interactive_bubble_chart = alt.Chart(filtered_df).mark_circle(size=200).encode(
x=alt.X('Params (B):Q', title="Model Size (in Billion Params)"),
y=alt.Y(f'{bubble_metric}:Q', title=bubble_metric),
size=alt.Size('Params (B):Q', legend=None),
color=alt.Color('Method:N', title="Model"),
tooltip=['Method', 'Params (B)', bubble_metric]
).properties(
width=800,
height=600
)
st.altair_chart(interactive_bubble_chart, use_container_width=True)
else:
st.warning(f"Columns '{bubble_metric}' and 'Params (B)' are required for the bubble plot.")
# Highlight Top N Models
st.subheader("Highlight Top N Models")
top_n = st.slider("Number of Top Models", min_value=1, max_value=len(filtered_df), value=5)
top_models_df = sorted_df.nlargest(top_n, metric)
top_chart = alt.Chart(top_models_df).mark_bar().encode(
x=alt.X('Method', title="Model"),
y=alt.Y(metric, title=metric),
color='Method',
tooltip=['Method', metric]
).properties(
width=1400, # Full width
height=400 # Adjusted height for smaller chart
)
st.altair_chart(top_chart, use_container_width=True)
# Download Button
@st.cache
def convert_df_to_csv(dataframe):
return dataframe.to_csv(index=False).encode('utf-8')
csv_data = convert_df_to_csv(sorted_df)
st.download_button(
label="Download Sorted Results",
data=csv_data,
file_name="sorted_leaderboard.csv",
mime="text/csv"
)
# with bubble plot
# import streamlit as st
# import pandas as pd
# import altair as alt
# # Set page layout to wide mode
# st.set_page_config(
# page_title="PathVLM-Eval Leaderboard",
# page_icon="🏆",
# layout="wide"
# )
# # Load the leaderboard data
# df = pd.read_csv("leaderboard.csv")
# # Add title and description
# st.title("PathVLM-Eval Leaderboard 🏆")
# st.markdown("""
# Welcome to the **PathVLM-Eval Leaderboard**! This leaderboard displays evaluation results for various Vision-Language Models (VLMs) in Pathology, focusing on multiple-choice questions (MCQs), answers, and explanations.
# You can search, filter, and visualize metrics for better insights.
# """)
# # Sidebar Filters
# with st.sidebar:
# st.subheader("Filters")
# # Search by model name (fuzzy search)
# search_query = st.text_input("Search for Model Name", value="", placeholder="e.g., llava")
# # Filter by model size
# model_sizes = df['Params (B)'].unique()
# selected_sizes = st.multiselect("Select Model Sizes", options=model_sizes, default=model_sizes)
# # Filter by model type
# if 'Language Model' in df.columns:
# model_types = df['Language Model'].unique()
# selected_types = st.multiselect("Select Model Types", options=model_types, default=model_types)
# else:
# selected_types = []
# # Apply Filters
# filtered_df = df[
# (df['Params (B)'].isin(selected_sizes)) &
# (df['Language Model'].isin(selected_types) if selected_types else True) &
# (df['Method'].str.contains(search_query, case=False, na=False))
# ]
# # Main Leaderboard Section
# st.subheader("Leaderboard Table")
# if filtered_df.empty:
# st.warning("No results found. Try adjusting the filters.")
# else:
# # Display table in wide layout
# st.dataframe(
# filtered_df,
# height=600, # Adjust table height
# width=1600 # Adjust table width
# )
# # Visualization of selected metric
# st.subheader("Performance Metrics Visualization")
# metric = st.selectbox("Select Metric to Visualize", options=filtered_df.columns[5:])
# # Visualization Chart
# chart = alt.Chart(filtered_df).mark_bar().encode(
# x=alt.X('Method', sort=alt.EncodingSortField(field=metric, order='descending'), title="Model"),
# y=alt.Y(metric, title=metric),
# color='Method',
# tooltip=['Method', metric]
# ).properties(
# width=1400, # Full width
# height=600 # Increased height
# )
# st.altair_chart(chart, use_container_width=True)
# # Bubble Plot for Accuracy vs. Model Size
# st.subheader("Bubble Plot: Accuracy vs. Model Size")
# if 'Avg score' in filtered_df.columns and 'Params (B)' in filtered_df.columns:
# bubble_chart = alt.Chart(filtered_df).mark_circle(size=200).encode(
# x=alt.X('Params (B):Q', title="Model Size (in Billion Params)"),
# y=alt.Y('Avg score:Q', title="Avg score"),
# size=alt.Size('Params (B):Q', legend=None),
# color=alt.Color('Method:N', title="Model"),
# tooltip=['Method', 'Avg score', 'Params (B)']
# ).properties(
# width=800,
# height=600
# )
# st.altair_chart(bubble_chart, use_container_width=True)
# else:
# st.warning("Columns 'Accuracy' and 'Params (B)' are required for the bubble plot.")
# # Highlight Top N Models
# st.subheader("Highlight Top N Models")
# top_n = st.slider("Number of Top Models", min_value=1, max_value=len(filtered_df), value=5)
# top_models_df = filtered_df.nlargest(top_n, metric)
# top_chart = alt.Chart(top_models_df).mark_bar().encode(
# x=alt.X('Method', title="Model"),
# y=alt.Y(metric, title=metric),
# color='Method',
# tooltip=['Method', metric]
# ).properties(
# width=1400, # Full width
# height=400 # Adjusted height for smaller chart
# )
# st.altair_chart(top_chart, use_container_width=True)
# # Download Button
# @st.cache
# def convert_df_to_csv(dataframe):
# return dataframe.to_csv(index=False).encode('utf-8')
# csv_data = convert_df_to_csv(filtered_df)
# st.download_button(
# label="Download Filtered Results",
# data=csv_data,
# file_name="filtered_leaderboard.csv",
# mime="text/csv"
# )
# with all bubble plot
# import streamlit as st
# import pandas as pd
# import altair as alt
# # Set page layout to wide mode
# st.set_page_config(
# page_title="PathVLM-Eval Leaderboard",
# page_icon="🏆",
# layout="wide"
# )
# # Load the leaderboard data
# df = pd.read_csv("leaderboard.csv") # Replace with the actual filename
# # Add title and description
# st.title("PathVLMs Leaderboard 🏆")
# st.markdown("""
# Welcome to the **PathVLMs Leaderboard**! This leaderboard displays evaluation results for various Vision-Language Models (VLMs) in Pathology, focusing on multiple-choice questions (MCQs), answers, and explanations.
# You can search, filter, and visualize metrics for better insights.
# """)
# # Sidebar Filters
# with st.sidebar:
# st.subheader("Filters")
# # Search by model name
# search_query = st.text_input("Search for Model Name", value="", placeholder="e.g., llava")
# # Filter by model size
# model_sizes = df['Params (B)'].unique()
# selected_sizes = st.multiselect("Select Model Sizes", options=model_sizes, default=model_sizes)
# # Filter by model type
# if 'Language Model' in df.columns:
# model_types = df['Language Model'].unique()
# selected_types = st.multiselect("Select Model Types", options=model_types, default=model_types)
# else:
# selected_types = []
# # Apply Filters
# filtered_df = df[
# (df['Params (B)'].isin(selected_sizes)) &
# (df['Language Model'].isin(selected_types) if selected_types else True) &
# (df['Method'].str.contains(search_query, case=False, na=False))
# ]
# # Main Leaderboard Section
# st.subheader("Leaderboard Table")
# if filtered_df.empty:
# st.warning("No results found. Try adjusting the filters.")
# else:
# # Display the filtered table
# st.dataframe(filtered_df)
# # Dataset columns to plot
# dataset_columns = ['Socialpath Tiny', 'Socialpath All', 'Education Content Tiny', 'Education Content All', 'Pubmed Tiny', 'Pubmed All', 'Avg score']
# # Generate Bubble Plots for each dataset column
# for dataset in dataset_columns:
# st.subheader(f"Bubble Plot: {dataset}")
# bubble_chart = alt.Chart(filtered_df).mark_circle(size=200).encode(
# x=alt.X('Params (B):Q', title="Model Size (in Billion Params)"),
# y=alt.Y(f'{dataset}:Q', title=dataset),
# size=alt.Size('Params (B):Q', legend=None),
# color=alt.Color('Method:N', title="Model"),
# tooltip=['Method', 'Params (B)', dataset]
# ).properties(
# width=800,
# height=600
# )
# st.altair_chart(bubble_chart, use_container_width=True)
# # Download Button
# @st.cache
# def convert_df_to_csv(dataframe):
# return dataframe.to_csv(index=False).encode('utf-8')
# csv_data = convert_df_to_csv(filtered_df)
# st.download_button(
# label="Download Filtered Results",
# data=csv_data,
# file_name="filtered_leaderboard.csv",
# mime="text/csv"
# )
# this also with bubble
# import streamlit as st
# import pandas as pd
# import altair as alt
# # Set page layout to wide mode
# st.set_page_config(
# page_title="PathVLMs Leaderboard",
# page_icon="🏆",
# layout="wide"
# )
# # Load the leaderboard data
# df = pd.read_csv("leaderboard.csv") # Replace with your actual CSV file name
# # Add title and description
# st.title("PathVLMs Leaderboard 🏆")
# st.markdown("""
# Welcome to the **PathVLMs Leaderboard**! This leaderboard displays evaluation results for various Vision-Language Models (VLMs) in Pathology, focusing on multiple-choice questions (MCQs), answers, and explanations.
# You can search, filter, and visualize metrics for better insights.
# """)
# # Sidebar Filters
# with st.sidebar:
# st.subheader("Filters")
# # Search by model name
# search_query = st.text_input("Search for Model Name", value="", placeholder="e.g., llava")
# # Filter by model size
# model_sizes = df['Params (B)'].unique()
# selected_sizes = st.multiselect("Select Model Sizes", options=model_sizes, default=model_sizes)
# # Filter by model type
# if 'Language Model' in df.columns:
# model_types = df['Language Model'].unique()
# selected_types = st.multiselect("Select Model Types", options=model_types, default=model_types)
# else:
# selected_types = []
# # Apply Filters
# filtered_df = df[
# (df['Params (B)'].isin(selected_sizes)) &
# (df['Language Model'].isin(selected_types) if selected_types else True) &
# (df['Method'].str.contains(search_query, case=False, na=False))
# ]
# # Main Leaderboard Section
# st.subheader("Leaderboard Table")
# if filtered_df.empty:
# st.warning("No results found. Try adjusting the filters.")
# else:
# # Display table in wide layout
# st.dataframe(
# filtered_df,
# height=600, # Adjust table height
# width=1600 # Adjust table width
# )
# # Visualization of selected metric
# st.subheader("Performance Metrics Visualization")
# metric = st.selectbox("Select Metric to Visualize", options=filtered_df.columns[5:])
# # Visualization Chart
# chart = alt.Chart(filtered_df).mark_bar().encode(
# x=alt.X('Method', sort=alt.EncodingSortField(field=metric, order='descending'), title="Model"),
# y=alt.Y(metric, title=metric),
# color='Method',
# tooltip=['Method', metric]
# ).properties(
# width=1400, # Full width
# height=600 # Increased height
# )
# st.altair_chart(chart, use_container_width=True)
# # Dataset columns to plot
# dataset_columns = ['Socialpath Tiny', 'Socialpath All', 'Education Content Tiny', 'Education Content All', 'Pubmed Tiny', 'Pubmed All', 'Avg score']
# # Generate Bubble Plots for each dataset column
# for dataset in dataset_columns:
# st.subheader(f"Bubble Plot: {dataset}")
# bubble_chart = alt.Chart(filtered_df).mark_circle(size=200).encode(
# x=alt.X('Params (B):Q', title="Model Size (in Billion Params)"),
# y=alt.Y(f'{dataset}:Q', title=dataset),
# size=alt.Size('Params (B):Q', legend=None),
# color=alt.Color('Method:N', title="Model"),
# tooltip=['Method', 'Params (B)', dataset]
# ).properties(
# width=800,
# height=600
# )
# st.altair_chart(bubble_chart, use_container_width=True)
# # Highlight Top N Models
# st.subheader("Highlight Top N Models")
# top_n = st.slider("Number of Top Models", min_value=1, max_value=len(filtered_df), value=5)
# top_models_df = filtered_df.nlargest(top_n, metric)
# top_chart = alt.Chart(top_models_df).mark_bar().encode(
# x=alt.X('Method', title="Model"),
# y=alt.Y(metric, title=metric),
# color='Method',
# tooltip=['Method', metric]
# ).properties(
# width=1400, # Full width
# height=400 # Adjusted height for smaller chart
# )
# st.altair_chart(top_chart, use_container_width=True)
# # Download Button
# @st.cache
# def convert_df_to_csv(dataframe):
# return dataframe.to_csv(index=False).encode('utf-8')
# csv_data = convert_df_to_csv(filtered_df)
# st.download_button(
# label="Download Filtered Results",
# data=csv_data,
# file_name="filtered_leaderboard.csv",
# mime="text/csv"
# )
|