From 4798866969c1e464d35a4f0f3d7f9c8c14cd42d5 Mon Sep 17 00:00:00 2001
From: Prikshit7766 <prikshitsharma8024@gmail.com>
Date: Wed, 8 Nov 2023 16:48:39 +0530
Subject: [PATCH] updated datasource.py

---
 langtest/datahandler/datasource.py | 31 +++++++++++++++---------------
 1 file changed, 16 insertions(+), 15 deletions(-)

diff --git a/langtest/datahandler/datasource.py b/langtest/datahandler/datasource.py
index 40585e4eb..0a2804345 100644
--- a/langtest/datahandler/datasource.py
+++ b/langtest/datahandler/datasource.py
@@ -386,21 +386,21 @@ def _load_dataset(cls, custom_label: dict) -> str:
         if "split" not in dataset_info:
             if subset is None:
                 subset = list(dataset_info.keys())[0]
-                logging.warning(
-                    f"You haven't provided the subset. Loading the default subset: {subset}"
-                )
+                logging.warning(Warnings.W012.format(var1="subset", var2=subset))
             if split is None:
                 split = dataset_info[subset]["split"][0]
-                logging.warning(
-                    f"You haven't provided the split. Loading the default split: {split}"
-                )
+                logging.warning(Warnings.W012.format(var1="split", var2=split))
 
             if subset not in dataset_info or split not in dataset_info[subset]["split"]:
-                available_subset_splits = ", ".join(
-                    [f"{s}: {info['split']}" for s, info in dataset_info.items()]
-                )
                 raise ValueError(
-                    f"Either subset: {subset} or split: {split} is not valid for {dataset_name}. Available subsets and their corresponding splits: {available_subset_splits}"
+                    Errors.E082.format(
+                        subset=subset,
+                        split=split,
+                        dataset_name=dataset_name,
+                        available_subset_splits=", ".join(
+                            [f"{s}: {info['split']}" for s, info in dataset_info.items()]
+                        ),
+                    )
                 )
             extension = dataset_info[subset].get("extension", "jsonl")
             return (
@@ -416,14 +416,15 @@ def _load_dataset(cls, custom_label: dict) -> str:
         else:
             if split is None:
                 split = dataset_info["split"][0]
-                logging.warning(
-                    f"You haven't provided the split. Loading the default split: {split}"
-                )
+                logging.warning(Warnings.W012.format(var1="split", var2=split))
 
             if split not in dataset_info["split"]:
-                available_splits = ", ".join(dataset_info["split"])
                 raise ValueError(
-                    f"split: {split} is not valid for {dataset_name}. Available splits: {available_splits}"
+                    Errors.E083.format(
+                        split=split,
+                        dataset_name=dataset_name,
+                        available_splits=", ".join(dataset_info["split"]),
+                    )
                 )
 
             extension = dataset_info.get("extension", "jsonl")