Update src/populate.py

src/populate.py

@@ -1,45 +1,43 @@
+# populate.py
+
 import json
 import os
-
 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
 
-
 def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchmark_cols: list) -> pd.DataFrame:
-    print("before get_raw_eval_results") # blz
+    print("get_leaderboard_df: Starting to process leaderboard data.")
     raw_data = get_raw_eval_results(results_path, requests_path)
-    print("after get_raw_eval_results") # blz
+    print("get_leaderboard_df: Raw eval results obtained.")
 
     all_data_json = [v.to_dict() for v in raw_data]
+    print(f"get_leaderboard_df: Converted raw data to JSON. Number of entries: {len(all_data_json)}")
 
     df = pd.DataFrame.from_records(all_data_json)
+    print("get_leaderboard_df: DataFrame created from records.")
+
     df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
     df = df[cols].round(decimals=2)
+    print("get_leaderboard_df: DataFrame sorted and columns rounded.")
 
-    print("after df things") # blz
-
-    
     # filter out if any of the benchmarks have not been produced
     df = df[has_no_nan_values(df, benchmark_cols)]
+    print("get_leaderboard_df: DataFrame filtered for NaN values in benchmarks.")
     return raw_data, df
 
-
 def get_evaluation_queue_df(save_path: str, cols: list) -> list[pd.DataFrame]:
+    print(f"get_evaluation_queue_df: Reading evaluation queue from {save_path}")
     entries = [entry for entry in os.listdir(save_path) if not entry.startswith(".")]
     all_evals = []
 
-    print("inside get_evaluation_queue_df") # blz
-
     for entry in entries:
         if ".json" in entry:
-            print(f"a json file {entry}") # blz
-            
             file_path = os.path.join(save_path, entry)
             with open(file_path) as fp:
                 data = json.load(fp)
+            print(f"get_evaluation_queue_df: Processing file {entry}")
 
             data[EvalQueueColumn.model.name] = make_clickable_model(data["model"])
             data[EvalQueueColumn.revision.name] = data.get("revision", "main")
@@ -52,6 +50,7 @@ def get_evaluation_queue_df(save_path: str, cols: list) -> list[pd.DataFrame]:
                 file_path = os.path.join(save_path, entry, sub_entry)
                 with open(file_path) as fp:
                     data = json.load(fp)
+                print(f"get_evaluation_queue_df: Processing file {sub_entry} in folder {entry}")
 
                 data[EvalQueueColumn.model.name] = make_clickable_model(data["model"])
                 data[EvalQueueColumn.revision.name] = data.get("revision", "main")
@@ -63,4 +62,6 @@ def get_evaluation_queue_df(save_path: str, cols: list) -> list[pd.DataFrame]:
     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)
+    print("get_evaluation_queue_df: Evaluation dataframes created.")
+
     return df_finished[cols], df_running[cols], df_pending[cols]