update column names from metadata file

app.py

@@ -31,7 +31,7 @@ hf_hub_download(repo_id="imageomics/demo-data",
 METADATA_PATH = "components/bioclip-2/metadata.parquet"
 # Read page IDs as int
 metadata_df = pl.read_parquet(METADATA_PATH, low_memory = False)
-metadata_df = metadata_df.with_columns(pl.col(["eol_page_id", "taxonID"]).cast(pl.Int64))
+metadata_df = metadata_df.with_columns(pl.col(["eol_page_id", "gbif_id"]).cast(pl.Int64))
 
 MODEL_STR = "hf-hub:imageomics/bioclip-2"
 TOKENIZER_STR = "ViT-L-14"

components/query.py

@@ -42,7 +42,7 @@ def get_sample(df, pred_taxon, rank):
     '''
     logger.info(f"Getting sample for taxon: {pred_taxon} at rank: {rank}")
     try:
-        filepath, taxonID, eol_page_id, full_name, is_exact = get_sample_data(df, pred_taxon, rank)
+        filepath, gbif_id, eol_page_id, full_name, is_exact = get_sample_data(df, pred_taxon, rank)
     except Exception as e:
         logger.error(f"Error retrieving sample data: {e}")
         return None, f"We encountered the following error trying to retrieve a sample image: {e}."
@@ -58,8 +58,8 @@ def get_sample(df, pred_taxon, rank):
                                                    )
         img_resp = requests.get(img_src)
         img = Image.open(io.BytesIO(img_resp.content))
-        if taxonID:
-            gbif_url = GBIF_URL + taxonID
+        if gbif_id:
+            gbif_url = GBIF_URL + gbif_id
             if eol_page_id:
                 eol_url = EOL_URL + eol_page_id
                 if is_exact:
@@ -100,7 +100,7 @@ def get_sample_data(df, pred_taxon, rank):
     --------
     filepath : str
         Filepath of selected sample image for predicted taxon.
-    taxonID: str
+    gbif_id: str
         GBIF page ID associated with predicted taxon for more information.
     eol_page_id : str
         EOL page ID associated with predicted taxon for more information.
@@ -125,9 +125,9 @@ def get_sample_data(df, pred_taxon, rank):
     if exact_df.shape[0] > 0:
         df_filtered = exact_df.sample()
         full_name = " ".join(df_filtered.select(RANKS[:rank+1]).row(0))
-        return df_filtered["file_path"][0], df_filtered["taxonID"].cast(pl.String)[0], df_filtered["eol_page_id"].cast(pl.String)[0], full_name, True
+        return df_filtered["file_path"][0], df_filtered["gbif_id"].cast(pl.String)[0], df_filtered["eol_page_id"].cast(pl.String)[0], full_name, True
 
     # If no exact matches, return any entry with the specified rank
     df_filtered = df.sample()
     full_name = " ".join(df_filtered.select(RANKS[:rank+1]).row(0)) + " " + " ".join(df_filtered.select(RANKS[rank+1:]).row(0))
-    return df_filtered["file_path"][0], df_filtered["taxonID"].cast(pl.String)[0], df_filtered["eol_page_id"].cast(pl.String)[0], full_name, False
+    return df_filtered["file_path"][0], df_filtered["gbif_id"].cast(pl.String)[0], df_filtered["eol_page_id"].cast(pl.String)[0], full_name, False