From 9c53f8dfbd2c4b7dfef8ced0a2534a1fba9bc7d6 Mon Sep 17 00:00:00 2001
From: Roy Hvaara <roy@lightyear.no>
Date: Tue, 3 Sep 2024 23:20:04 +0200
Subject: [PATCH] Target v0.10.for task BigCodeBench/16

---
 tools/fix_020.py   | 59 ----------------------------------------------
 tools/fix_v0110.py |  8 ++++++-
 2 files changed, 7 insertions(+), 60 deletions(-)
 delete mode 100644 tools/fix_020.py

diff --git a/tools/fix_020.py b/tools/fix_020.py
deleted file mode 100644
index 82b48d7..0000000
--- a/tools/fix_020.py
+++ /dev/null
@@ -1,59 +0,0 @@
-from datasets import load_dataset, Dataset, DatasetDict
-from huggingface_hub import HfApi
-
-import json
-import copy
-
-BIGCODEBENCH_HF = "bigcode/bigcodebench"
-BIGCODEBENCH_HARD_HF = "bigcode/bigcodebench-hard"
-BIGCODEBENCH_VERSION = "v0.1.0_hf"
-BIGCODEBENCH_UPDATE = "bigcode/bcb_update"
-BIGCODEBENCH_NEW_VERSION = "v0.1.1"  # TODO(hvaara): [DO NOT MERGE] Figure out which version we're targeting
-
-
-def map_ds(sample):
-
-    if sample["task_id"] in ["BigCodeBench/16"]:
-        for k in sample.keys():
-            sample[k] = sample[k].replace(
-                "No logs found to backup.", "No logs found to backup"
-            )
-
-    return sample
-
-
-if __name__ == "__main__":
-    api = HfApi()
-    ds_dict = load_dataset(BIGCODEBENCH_HF)
-    hard_ds_dict = load_dataset(BIGCODEBENCH_HARD_HF)
-    ds = ds_dict[BIGCODEBENCH_VERSION]
-    hard_ds = hard_ds_dict[BIGCODEBENCH_VERSION]
-    function_id = [16]
-
-    new_ds = ds.map(map_ds)
-    new_ds.to_json("BigCodeBench.jsonl")
-    ds_dict[BIGCODEBENCH_NEW_VERSION] = new_ds
-    ds_dict.push_to_hub(BIGCODEBENCH_HF)
-
-    new_hard_ds = hard_ds.map(map_ds)
-    new_hard_ds.to_json("BigCodeBench-Hard.jsonl")
-    hard_ds_dict[BIGCODEBENCH_NEW_VERSION] = new_hard_ds
-    hard_ds_dict.push_to_hub(BIGCODEBENCH_HARD_HF)
-
-    for i in function_id:
-        old_sample = ds.select([i])
-        new_sample = new_ds.select([i])
-        old_sample.to_json("old.jsonl")
-        new_sample.to_json("new.jsonl")
-        api.upload_file(
-            path_or_fileobj="old.jsonl",
-            path_in_repo=f"{i}/old.jsonl",
-            repo_id=BIGCODEBENCH_UPDATE,
-            # repo_type="dataset"
-        )
-        api.upload_file(
-            path_or_fileobj="new.jsonl",
-            path_in_repo=f"{i}/new.jsonl",
-            repo_id=BIGCODEBENCH_UPDATE,
-            # repo_type="dataset"
-        )
diff --git a/tools/fix_v0110.py b/tools/fix_v0110.py
index d1d1300..a6aadac 100644
--- a/tools/fix_v0110.py
+++ b/tools/fix_v0110.py
@@ -11,6 +11,12 @@
 BIGCODEBENCH_NEW_VERSION = "v0.1.2"
 
 def map_ds(sample):
+    if sample["task_id"] in ["BigCodeBench/16"]:
+        for k in sample.keys():
+            sample[k] = sample[k].replace(
+                "No logs found to backup.", "No logs found to backup"
+            )
+
     if sample["task_id"] in ["BigCodeBench/37"]:
         for k in sample.keys():
             if "prompt" in k:
@@ -28,7 +34,7 @@ def map_ds(sample):
     hard_ds_dict = load_dataset(BIGCODEBENCH_HARD_HF)
     ds = ds_dict[BIGCODEBENCH_VERSION]
     hard_ds = hard_ds_dict[BIGCODEBENCH_VERSION]
-    function_id = [37]
+    function_id = [16, 37]
     
     new_ds = ds.map(map_ds)
     new_ds.to_json("BigCodeBench.jsonl")