Merge pull request #113 from javadr-forky/dev

feat(available_dataset): enable output redirection & fix typo

Author: abdoelsayed2016

README-PyPI.md

@@ -203,7 +203,7 @@ To see all available datasets:
 from rankify.dataset.dataset import Dataset 
 
 # Display available datasets
-Dataset.avaiable_dataset()
+Dataset.available_dataset()
 ```
 
 **BM25 Retriever**

README_zh.md

@@ -223,7 +223,7 @@ rm -rf ~/.cache/torch_extensions/*
 from rankify.dataset.dataset import Dataset 
 
 # 显示可用数据集
-Dataset.avaiable_dataset()
+Dataset.available_dataset()
 ```
 
 

docs/docs/tutorials/datasets/benchmark_datasets.md

@@ -23,7 +23,7 @@ Rankify provides easy access to standard QA benchmark datasets.
 from rankify.dataset.dataset import Dataset
 
 # List all available datasets
-Dataset.avaiable_dataset()
+Dataset.available_dataset()
 
 # Load NQ with BM25 retrieval
 dataset = Dataset(

docs/docs/tutorials/retrieval/prebuilt_corpora.md

@@ -63,7 +63,7 @@ For benchmarking, Rankify provides pre-retrieved datasets on Hugging Face:
 from rankify.dataset.dataset import Dataset
 
 # List available datasets
-Dataset.avaiable_dataset()
+Dataset.available_dataset()
 
 # Download a pre-retrieved dataset
 dataset = Dataset(

examples/retrieved_dataset.py

@@ -2,7 +2,7 @@
 os.environ["CUDA_VISIBLE_DEVICES"] = "0"
 from rankify.dataset.dataset import Dataset ,Document, Context, Question,Answer
 from rankify.metrics.metrics import Metrics
-#Dataset.avaiable_dataset()
+#Dataset.available_dataset()
 
 
 datasets = ["web_questions-test"]#, "ChroniclingAmericaQA-test" , "ArchivialQA-test"]#["nq-dev", "nq-test" , "squad1-test", "trivia-dev", "trivia-test", "webq-test", "squad1-dev" ] #

rankify/dataset/dataset.py

@@ -657,7 +657,7 @@ def __getitem__(self,idx) -> Document:
 
 
     @staticmethod
-    def avaiable_dataset() -> None:
+    def available_dataset(file=None) -> None:
         """
         Prints information about available datasets.
 
@@ -666,7 +666,7 @@ def avaiable_dataset() -> None:
             Dataset.available_dataset()
             ```
         """
-        get_datasets_info()
+        get_datasets_info(file=file)
 
 
 

rankify/utils/dataset/utils.py

@@ -2,7 +2,7 @@
 import pandas as pd
 from prettytable import PrettyTable
 
-def get_datasets_info():
+def get_datasets_info(file=None):
     table = PrettyTable(['Retriever', 'Dataset', 'Original ext', 'Compressed','Desc','URL'])
     for retriever, datasets in HF_PRE_DEFIND_DATASET.items():
         for dataset_name, dataset_info in datasets.items():
@@ -17,4 +17,4 @@ def get_datasets_info():
             }
             table.add_row(flattened_entry.values())
 
-    print(table)
+    print(table, file=file)