Removing envs variables

src/populate.py

@@ -1,134 +1,13 @@
 import json
 import os
+from dataclasses import fields
 
 import pandas as pd
 
-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 has_no_nan_values
-
-'''
-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(eval_results_path, eval_requests_path, cols, benchmark_cols):
-    eval_results = get_raw_eval_results(eval_results_path, eval_requests_path)
-    rows = [e.to_dict() for e in eval_results]
-
-    # If nothing loaded, just return an empty DF (prevents KeyError)
-    if not rows:
-        print("No eval results found – returning empty leaderboard.")
-        return pd.DataFrame()
-
-    df = pd.DataFrame(rows)
-
-    # 1) Sort only if the Average column exists
-    avg_col = AutoEvalColumn.average.name  # usually "Average ⬆️"
-    if avg_col in df.columns:
-        df = df.sort_values(by=[avg_col], ascending=False)
-    else:
-        print("Average column not found in dataframe. Columns:", df.columns)
-
-    # 2) Only keep columns that actually exist in the DF
-    existing_cols = [c for c in cols if c in df.columns]
-    df = df[existing_cols].round(decimals=2)
-
-    # 3) Filter models that miss some benchmarks, but only for existing benchmarks
-    existing_benchmarks = [c for c in benchmark_cols if c in df.columns]
-    if existing_benchmarks:
-        df = df[has_no_nan_values(df, existing_benchmarks)]
-
-    return df
+from src.display.formatting import make_clickable_model
+from src.display.utils import AutoEvalColumn
 
 
-def get_leaderboard_df(eval_results_path, eval_requests_path, cols, benchmark_cols):
-    """
-    Build the leaderboard dataframe from the JSON eval results.
-
-    - Does NOT assume that an 'Average ⬆️' column already exists.
-    - Does NOT depend on has_no_nan_values.
-    - Is tolerant to missing columns.
-    """
-    # 1) Load EvalResult objects from results (and requests, if your get_raw_eval_results uses it)
-    eval_results = get_raw_eval_results(eval_results_path, eval_requests_path)
-    rows = [e.to_dict() for e in eval_results]
-
-    # If nothing loaded, return an empty DF with the expected column order
-    if not rows:
-        print("No eval results found – returning empty leaderboard.")
-        return pd.DataFrame(columns=cols)
-
-    df = pd.DataFrame(rows)
-
-    # 2) Sort by Average if that column exists
-    avg_col = AutoEvalColumn.average.name  # usually "Average ⬆️"
-    if avg_col in df.columns:
-        df = df.sort_values(by=[avg_col], ascending=False)
-    else:
-        print(f"Average column '{avg_col}' not found. Available columns:", list(df.columns))
-
-    # 3) Keep only the columns that actually exist in the dataframe
-    existing_cols = [c for c in cols if c in df.columns]
-    df = df[existing_cols]
-
-    # 4) Round numeric columns to 2 decimals
-    num_cols = df.select_dtypes(include="number").columns
-    if len(num_cols) > 0:
-        df[num_cols] = df[num_cols].round(2)
-
-    # 5) If you *want* to drop rows with NaNs in benchmark columns, do it directly with dropna
-    existing_benchmarks = [c for c in benchmark_cols if c in df.columns]
-    if existing_benchmarks:
-        df = df.dropna(subset=existing_benchmarks, how="any")
-
-    return df
-
-def get_evaluation_queue_df(save_path: str, cols: list) -> list[pd.DataFrame]:
-    """Creates the different dataframes for the evaluation queues requestes"""
-    entries = [entry for entry in os.listdir(save_path) if not entry.startswith(".")]
-    all_evals = []
-
-    for entry in entries:
-        if ".json" in entry:
-            file_path = os.path.join(save_path, entry)
-            with open(file_path) as fp:
-                data = json.load(fp)
-
-            data[EvalQueueColumn.model.name] = make_clickable_model(data["model"])
-            data[EvalQueueColumn.revision.name] = data.get("revision", "main")
-
-            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(".")]
-            for sub_entry in sub_entries:
-                file_path = os.path.join(save_path, entry, sub_entry)
-                with open(file_path) as fp:
-                    data = json.load(fp)
-
-                data[EvalQueueColumn.model.name] = make_clickable_model(data["model"])
-                data[EvalQueueColumn.revision.name] = data.get("revision", "main")
-                all_evals.append(data)
-
-    pending_list = [e for e in all_evals if e["status"] in ["PENDING", "RERUN"]]
-    running_list = [e for e in all_evals if e["status"] == "RUNNING"]
-    finished_list = [e for e in all_evals if e["status"].startswith("FINISHED") or e["status"] == "PENDING_NEW_EVAL"]
-    df_pending = pd.DataFrame.from_records(pending_list, columns=cols)
-    df_running = pd.DataFrame.from_records(running_list, columns=cols)
-    df_finished = pd.DataFrame.from_records(finished_list, columns=cols)
-    return df_finished[cols], df_running[cols], df_pending[cols]
-'''
 def get_leaderboard_df(eval_results_path, eval_requests_path, cols, benchmark_cols):
     """
     Build the leaderboard dataframe directly from JSON files in eval_results_path.
@@ -239,6 +118,7 @@ def get_leaderboard_df(eval_results_path, eval_requests_path, cols, benchmark_co
 
     return df
 
+
 def get_evaluation_queue_df(save_path: str, cols: list):
     """
     Stubbed evaluation queue.
@@ -248,7 +128,6 @@ def get_evaluation_queue_df(save_path: str, cols: list):
     - return three empty dataframes (finished, running, pending)
       with the expected columns.
     """
-    # Make sure the folder exists so nothing crashes on missing dir
     os.makedirs(save_path, exist_ok=True)
 
     empty_df = pd.DataFrame(columns=cols)
@@ -256,3 +135,4 @@ def get_evaluation_queue_df(save_path: str, cols: list):
     # The order here must match how app.py unpacks the result:
     # finished_df, running_df, pending_df = get_evaluation_queue_df(...)
     return empty_df, empty_df.copy(), empty_df.copy()
+