feat: add anonymous submission option for public dataset

app.py

@@ -244,6 +244,17 @@ def create_gradio_interface():
                 "*Public: Will be added to our public dataset. By submitting, you are giving permission to be added to the dataset.*",
                 elem_id="public_exp"
             )
+            
+            anonymous_checkbox = gr.Checkbox(
+                value=False,
+                label="Submit Anonymously",
+                interactive=True,
+                elem_id="anonymous_cb"
+            )
+            anonymous_explanation = gr.Markdown(
+                "*If un-checked, your HF username will be appended next to your submission and you will be added to the leaderboard. If checked, your submission will be anonymous in the public dataset.*",
+                elem_id="anonymous_exp"
+            )
         
         with gr.Row(visible=False) as button_row:
             submit_btn = gr.Button("Submit", elem_id="submit_btn")
@@ -269,6 +280,7 @@ def create_gradio_interface():
             image: Image.Image,
             max_words: int,
             public_checkbox: bool,
+            anonymous_checkbox: bool,
             collector: OCRDataCollector | None = None,
             profile: gr.OAuthProfile | None = None,
             oauth_token: gr.OAuthToken | None = None,
@@ -282,6 +294,7 @@ def create_gradio_interface():
             print(f"Image type: {type(image)}")
             print(f"Max words: {max_words}")
             print(f"Public checkbox: {public_checkbox}")
+            print(f"Anonymous checkbox: {anonymous_checkbox}")
             print(f"Collector type: {type(collector)}")
             
             if collector is None:
@@ -318,7 +331,8 @@ def create_gradio_interface():
                 features = datasets.Features({
                     'text': datasets.Value('string'),
                     'image': datasets.Image(),
-                    'timestamp': datasets.Value('string')
+                    'timestamp': datasets.Value('string'),
+                    'user': datasets.Value('string')
                 })
 
                 try:
@@ -327,13 +341,15 @@ def create_gradio_interface():
                     dataset = datasets.Dataset.from_dict({
                         'text': [],
                         'image': [],
-                        'timestamp': []
+                        'timestamp': [],
+                        'user': []
                     }, features=features)
 
                 dataset = dataset.add_item({
                     'text': text,
                     'image': temp_path_public,
-                    'timestamp': timestamp
+                    'timestamp': timestamp,
+                    'user': 'anonymous' if anonymous_checkbox else user_state.username
                 })
 
                 dataset.push_to_hub(public_repo_id, split="train", token=master_token)
@@ -388,6 +404,7 @@ def create_gradio_interface():
                 image_input,       # Uploaded image
                 max_words_slider,  # Max words
                 public_checkbox,   # Public dataset option
+                anonymous_checkbox,
                 gr.State(collector),
                 gr.State(None),    # Profile will be filled by Gradio
                 gr.State(None)     # Token will be filled by Gradio

clear_dataset.py

@@ -0,0 +1,35 @@
+from datasets import load_dataset
+from huggingface_hub import HfApi
+import os
+
+# Load environment variables
+from dotenv import load_dotenv
+load_dotenv()
+
+# Get the token from environment variable
+token = os.getenv('PUBLIC_DATASET_TOKEN')
+if not token:
+    raise ValueError('PUBLIC_DATASET_TOKEN not found in environment')
+
+# Initialize the Hugging Face API client
+api = HfApi(token=token)
+
+# Create an empty dataset with the same schema
+features = {
+    'text': 'string',
+    'image': 'image',
+    'timestamp': 'string',
+    'user': 'string'
+}
+
+# Create and push empty dataset
+from datasets import Dataset
+empty_dataset = Dataset.from_dict({
+    'text': [], 
+    'image': [], 
+    'timestamp': [],
+    'user': []
+})
+
+# Push the empty dataset to hub
+empty_dataset.push_to_hub('rawwerks/handwriting-ocr-all', private=False, token=token)