add basic static leaderboard

app.py

@@ -22,7 +22,7 @@ from src.display.utils import (
     ModelType,
     fields,
     WeightType,
-    Precision
+    Precision,
 )
 from src.envs import API, EVAL_REQUESTS_PATH, EVAL_RESULTS_PATH, QUEUE_REPO, REPO_ID, RESULTS_REPO, TOKEN
 from src.populate import get_evaluation_queue_df, get_leaderboard_df
@@ -32,24 +32,40 @@ from src.submission.submit import add_new_eval
 def restart_space():
     API.restart_space(repo_id=REPO_ID)
 
+
 ### Space initialisation
 try:
     print(EVAL_REQUESTS_PATH)
     snapshot_download(
-        repo_id=QUEUE_REPO, local_dir=EVAL_REQUESTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
+        repo_id=QUEUE_REPO,
+        local_dir=EVAL_REQUESTS_PATH,
+        repo_type="dataset",
+        tqdm_class=None,
+        etag_timeout=30,
+        token=TOKEN,
     )
 except Exception:
     restart_space()
 try:
     print(EVAL_RESULTS_PATH)
     snapshot_download(
-        repo_id=RESULTS_REPO, local_dir=EVAL_RESULTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
+        repo_id=RESULTS_REPO,
+        local_dir=EVAL_RESULTS_PATH,
+        repo_type="dataset",
+        tqdm_class=None,
+        etag_timeout=30,
+        token=TOKEN,
     )
 except Exception:
     restart_space()
 
 
-LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS)
+LEADERBOARD_DF = get_leaderboard_df(
+    EVAL_RESULTS_PATH + "/" + "BOOM_leaderboard.csv", EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS
+)
+LEADERBOARD_DF_DOMAIN = get_leaderboard_df(
+    EVAL_RESULTS_PATH + "/" + "BOOM_leaderboard.csv", EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS
+)
 
 (
     finished_eval_queue_df,
@@ -57,7 +73,9 @@ LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS,
     pending_eval_queue_df,
 ) = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_COLS)
 
+
 def init_leaderboard(dataframe):
+    # TODO: merge results df with model info df
     if dataframe is None or dataframe.empty:
         raise ValueError("Leaderboard DataFrame is empty or None.")
     return Leaderboard(
@@ -68,21 +86,10 @@ def init_leaderboard(dataframe):
             cant_deselect=[c.name for c in fields(AutoEvalColumn) if c.never_hidden],
             label="Select Columns to Display:",
         ),
-        search_columns=[AutoEvalColumn.model.name, AutoEvalColumn.license.name],
+        search_columns=[AutoEvalColumn.model.name],
         hide_columns=[c.name for c in fields(AutoEvalColumn) if c.hidden],
         filter_columns=[
             ColumnFilter(AutoEvalColumn.model_type.name, type="checkboxgroup", label="Model types"),
-            ColumnFilter(AutoEvalColumn.precision.name, type="checkboxgroup", label="Precision"),
-            ColumnFilter(
-                AutoEvalColumn.params.name,
-                type="slider",
-                min=0.01,
-                max=150,
-                label="Select the number of parameters (B)",
-            ),
-            ColumnFilter(
-                AutoEvalColumn.still_on_hub.name, type="boolean", label="Deleted/incomplete", default=True
-            ),
         ],
         bool_checkboxgroup_label="Hide models",
         interactive=False,
@@ -95,98 +102,15 @@ with demo:
     gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
 
     with gr.Tabs(elem_classes="tab-buttons") as tabs:
-        with gr.TabItem("🏅 LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0):
+        with gr.TabItem("🏅 Overall", elem_id="boom-benchmark-tab-table", id=0):
             leaderboard = init_leaderboard(LEADERBOARD_DF)
 
-        with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):
-            gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
+        # TODO - add other tabs if needed
+        with gr.TabItem("🏅 By Domain - TODO", elem_id="boom-benchmark-tab-table", id=1):
+            leaderboard = init_leaderboard(LEADERBOARD_DF_DOMAIN)  # TODO - update table data
 
-        with gr.TabItem("🚀 Submit here! ", elem_id="llm-benchmark-tab-table", id=3):
-            with gr.Column():
-                with gr.Row():
-                    gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")
-
-                with gr.Column():
-                    with gr.Accordion(
-                        f"✅ Finished Evaluations ({len(finished_eval_queue_df)})",
-                        open=False,
-                    ):
-                        with gr.Row():
-                            finished_eval_table = gr.components.Dataframe(
-                                value=finished_eval_queue_df,
-                                headers=EVAL_COLS,
-                                datatype=EVAL_TYPES,
-                                row_count=5,
-                            )
-                    with gr.Accordion(
-                        f"🔄 Running Evaluation Queue ({len(running_eval_queue_df)})",
-                        open=False,
-                    ):
-                        with gr.Row():
-                            running_eval_table = gr.components.Dataframe(
-                                value=running_eval_queue_df,
-                                headers=EVAL_COLS,
-                                datatype=EVAL_TYPES,
-                                row_count=5,
-                            )
-
-                    with gr.Accordion(
-                        f"⏳ Pending Evaluation Queue ({len(pending_eval_queue_df)})",
-                        open=False,
-                    ):
-                        with gr.Row():
-                            pending_eval_table = gr.components.Dataframe(
-                                value=pending_eval_queue_df,
-                                headers=EVAL_COLS,
-                                datatype=EVAL_TYPES,
-                                row_count=5,
-                            )
-            with gr.Row():
-                gr.Markdown("# ✉️✨ Submit your model here!", elem_classes="markdown-text")
-
-            with gr.Row():
-                with gr.Column():
-                    model_name_textbox = gr.Textbox(label="Model name")
-                    revision_name_textbox = gr.Textbox(label="Revision commit", placeholder="main")
-                    model_type = gr.Dropdown(
-                        choices=[t.to_str(" : ") for t in ModelType if t != ModelType.Unknown],
-                        label="Model type",
-                        multiselect=False,
-                        value=None,
-                        interactive=True,
-                    )
-
-                with gr.Column():
-                    precision = gr.Dropdown(
-                        choices=[i.value.name for i in Precision if i != Precision.Unknown],
-                        label="Precision",
-                        multiselect=False,
-                        value="float16",
-                        interactive=True,
-                    )
-                    weight_type = gr.Dropdown(
-                        choices=[i.value.name for i in WeightType],
-                        label="Weights type",
-                        multiselect=False,
-                        value="Original",
-                        interactive=True,
-                    )
-                    base_model_name_textbox = gr.Textbox(label="Base model (for delta or adapter weights)")
-
-            submit_button = gr.Button("Submit Eval")
-            submission_result = gr.Markdown()
-            submit_button.click(
-                add_new_eval,
-                [
-                    model_name_textbox,
-                    base_model_name_textbox,
-                    revision_name_textbox,
-                    precision,
-                    weight_type,
-                    model_type,
-                ],
-                submission_result,
-            )
+        with gr.TabItem("📝 About - TODO", elem_id="boom-benchmark-tab-table", id=2):
+            gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
 
     with gr.Row():
         with gr.Accordion("📙 Citation", open=False):
@@ -201,4 +125,4 @@ with demo:
 scheduler = BackgroundScheduler()
 scheduler.add_job(restart_space, "interval", seconds=1800)
 scheduler.start()
-demo.queue(default_concurrency_limit=40).launch()
+demo.queue(default_concurrency_limit=40).launch()

src/populate.py

@@ -2,23 +2,65 @@ import json
 import os
 
 import pandas as pd
-
+from dataclasses import fields
 from src.display.formatting import has_no_nan_values, make_clickable_model
 from src.display.utils import AutoEvalColumn, EvalQueueColumn
 from src.leaderboard.read_evals import get_raw_eval_results
+from src.display.utils import ModelType
+
+
+# def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchmark_cols: list) -> pd.DataFrame:
+#     """Creates a dataframe from all the individual experiment results"""
+#     raw_data = get_raw_eval_results(results_path, requests_path)
+#     all_data_json = [v.to_dict() for v in raw_data]
+
+#     df = pd.DataFrame.from_records(all_data_json)
+#     df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
+#     df = df[cols].round(decimals=2)
+
+#     # filter out if any of the benchmarks have not been produced
+#     df = df[has_no_nan_values(df, benchmark_cols)]
+#     return df
 
 
 def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchmark_cols: list) -> pd.DataFrame:
-    """Creates a dataframe from all the individual experiment results"""
-    raw_data = get_raw_eval_results(results_path, requests_path)
-    all_data_json = [v.to_dict() for v in raw_data]
+    """
+    Processes a STATIC results CSV file to generate a leaderboard DataFrame with formatted columns and sorted values.
+    Args:
+        results_path (str): The file path to the results CSV file.
+    Returns:
+        pd.DataFrame: A processed DataFrame with renamed columns, additional formatting, and sorted values.
+    Notes:
+        - The function reads a CSV file from the given `results_path`.
+        - Internal column names are mapped to display names using `AutoEvalColumn`.
+        - A new column for model type symbols is created by parsing the `model_type` column.
+        - The `model_type` column is updated to prepend the model type symbol.
+        - The DataFrame is sorted by the `Rank_6750_scaled` column in ascending order.
+    """
+
+    df = pd.read_csv(results_path)
+    # Create the mapping from internal column name to display name
+
+    column_mapping = {field.name: getattr(AutoEvalColumn, field.name).name for field in fields(AutoEvalColumn)}
+    # Assuming `df` is your DataFrame:
+    df.rename(columns=column_mapping, inplace=True)
+
+    # Create a new column for model type symbol by parsing the model_type column
+    df[AutoEvalColumn.model_type_symbol.name] = df[AutoEvalColumn.model_type.name].apply(
+        lambda x: ModelType.from_str(x).value.symbol
+    )
+    # Prepend the value of model_type_symbol to the value of model_type
+    df[AutoEvalColumn.model_type.name] = (
+        df[AutoEvalColumn.model_type_symbol.name] + " " + df[AutoEvalColumn.model_type.name]
+    )
 
-    df = pd.DataFrame.from_records(all_data_json)
-    df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
-    df = df[cols].round(decimals=2)
+    # Move the model_type_symbol column to the beginning
+    cols = [AutoEvalColumn.model_type_symbol.name] + [
+        col for col in df.columns if col != AutoEvalColumn.model_type_symbol.name
+    ]
+    df = df[cols]
 
-    # filter out if any of the benchmarks have not been produced
-    df = df[has_no_nan_values(df, benchmark_cols)]
+    df = df.sort_values(by=[AutoEvalColumn.Rank_6750_scaled.name], ascending=True)
     return df
 
 
@@ -39,7 +81,9 @@ def get_evaluation_queue_df(save_path: str, cols: list) -> list[pd.DataFrame]:
             all_evals.append(data)
         elif ".md" not in entry:
             # this is a folder
-            sub_entries = [e for e in os.listdir(f"{save_path}/{entry}") if os.path.isfile(e) and not e.startswith(".")]
+            sub_entries = [
+                e for e in os.listdir(f"{save_path}/{entry}") if os.path.isfile(e) and not e.startswith(".")
+            ]
             for sub_entry in sub_entries:
                 file_path = os.path.join(save_path, entry, sub_entry)
                 with open(file_path) as fp: