fix: clean push all observations

src/classifier/classifier_image.py

@@ -7,7 +7,6 @@ g_logger = logging.getLogger(__name__)
 g_logger.setLevel(LOG_LEVEL)
 
 import whale_viewer as viewer
-from dataset.hf_push_observations import push_observations
 from utils.grid_maker import gridder
 from utils.metadata_handler import metadata2md
 from input.input_observation import InputObservation
@@ -113,7 +112,6 @@ def cetacean_show_results_and_review() -> None:
             observation = _observation.to_dict()
             st.session_state.public_observations[hash] = observation
             
-            #st.button(f"Upload observation {str(o)} to THE INTERNET!", on_click=push_observations)
             # TODO: the metadata only fills properly if `validate` was clicked.
             # TODO put condition on the debug
             st.markdown(metadata2md(hash, debug=False))

src/dataset/hf_push_observations.py

@@ -7,6 +7,7 @@ from streamlit.delta_generator import DeltaGenerator
 import streamlit as st
 from huggingface_hub import HfApi, CommitInfo
 
+from dataset.download import dataset_id
 
 # get a global var for logger accessor in this module
 LOG_LEVEL = logging.DEBUG
@@ -48,7 +49,7 @@ def push_observation(image_hash:str, api:HfApi, enable_push:False) -> CommitInfo
         rv = api.upload_file(
             path_or_fileobj=f.name,
             path_in_repo=path_in_repo,
-            repo_id="Saving-Willy/temp_dataset",
+            repo_id=dataset_id,
             repo_type="dataset",
         )
         print(rv)
@@ -73,50 +74,4 @@ def push_all_observations(enable_push:bool=False):
 
     # iterate over the list of observations
     for hash in st.session_state.public_observations.keys():
-        rv = push_observation(hash, api, enable_push=enable_push)
-
-    
-
-def push_observations(tab_log:DeltaGenerator=None):
-    """
-    Push the observations to the Hugging Face dataset
-    
-    Args:
-        tab_log (streamlit.container): The container to log messages to. If not provided,
-            log messages are in any case written to the global logger (TODO: test - didn't 
-            push any observation since generating the logger)
-    
-    """
-    raise DeprecationWarning("This function is deprecated. Use push_all_observations instead.")
-
-    # we get the observation from session state: 1 is the dict 2 is the image.
-    # first, lets do an info display (popup)
-    metadata_str = json.dumps(st.session_state.public_observation)
-    
-    st.toast(f"Uploading observations: {metadata_str}", icon="🦭")
-    g_logger.info(f"Uploading observations: {metadata_str}")
-        
-    # get huggingface api
-    token = os.environ.get("HF_TOKEN", None)
-    api = HfApi(token=token)
-
-    f = tempfile.NamedTemporaryFile(mode="w", suffix=".json", delete=False)
-    f.write(metadata_str)
-    f.close()
-    st.info(f"temp file: {f.name} with metadata written...")
-
-    path_in_repo= f"metadata/{st.session_state.public_observation['author_email']}/{st.session_state.public_observation['image_md5']}.json"
-    msg = f"fname: {f.name} | path: {path_in_repo}"
-    print(msg)
-    st.warning(msg)
-    # rv = api.upload_file(
-    #     path_or_fileobj=f.name,
-    #     path_in_repo=path_in_repo,
-    #     repo_id="Saving-Willy/temp_dataset",
-    #     repo_type="dataset",
-    # )
-    # print(rv)
-    # msg = f"observation attempted tx to repo happy walrus: {rv}"
-    g_logger.info(msg)
-    st.info(msg)
-    
+        rv = push_observation(hash, api, enable_push=enable_push)

src/pages/4_🔥_classifiers.py

@@ -28,8 +28,6 @@ from classifier.classifier_hotdog import hotdog_classify
 classifier_name = "Saving-Willy/cetacean-classifier"
 #classifier_revision = '0f9c15e2db4d64e7f622ade518854b488d8d35e6'
 classifier_revision = 'main' # default/latest version
-dataset_id = "Saving-Willy/temp_dataset"
-data_files = "data/train-00000-of-00001.parquet"
 ############################################################
 
 g_logger = logging.getLogger(__name__)