Add WhiskyDB tab to sample explorers

README.md

@@ -12,10 +12,11 @@ license: cc-by-nc-4.0
 
 # 🗂️ Dataset Sample Explorers
 
-One interactive explorer for the **free samples** of three curated commercial datasets:
+One interactive explorer for the **free samples** of four curated commercial datasets:
 
 * **☕ [RoasterDB](https://specialty-coffee-roasterdb.pages.dev)** — specialty coffee mapped to the SCA Flavor Wheel ([sample dataset](https://huggingface.co/datasets/Ichlibitiche/roasterdb-specialty-coffee-sample))
 * **🌿 [FloraDB](https://houseplants-botanical-floradb.pages.dev)** — quantitative houseplant care + ASPCA pet toxicity ([sample dataset](https://huggingface.co/datasets/Ichlibitiche/floradb-houseplants-care-sample))
 * **💊 [SuppDB](https://supplements-nootropics-suppdb.pages.dev)** — NIH DSLD supplement labels with mg-normalized doses + PubChem chemistry ([sample dataset](https://huggingface.co/datasets/Ichlibitiche/suppdb-supplements-sample))
+* **🥃 [WhiskyDB](https://github.com/WhiskyyDB/whisky-database)** — provenance-tracked fine spirits + open cask & flavor taxonomies ([sample dataset](https://huggingface.co/datasets/Ichlibitiche/whiskydb-fine-spirits-sample))
 
 Every record carries a source URL for re-verification. Full datasets are commercially licensed at each portal. Sample data CC BY-NC 4.0.

app.py

@@ -6,9 +6,15 @@ ROASTER_URL = "hf://datasets/Ichlibitiche/roasterdb-specialty-coffee-sample/roas
 FLORA_URL = "hf://datasets/Ichlibitiche/floradb-houseplants-care-sample/floradb_sample.csv"
 SUPP_URL = "hf://datasets/Ichlibitiche/suppdb-supplements-sample/suppdb_sample.csv"
 
+WHISKY_BASE = "hf://datasets/Ichlibitiche/whiskydb-fine-spirits-sample/"
+
 r_df = pd.read_csv(ROASTER_URL)
 f_df = pd.read_csv(FLORA_URL)
 s_df = pd.read_csv(SUPP_URL)
+w_df = pd.read_csv(WHISKY_BASE + "spirits.csv")
+w_dist_df = pd.read_csv(WHISKY_BASE + "distilleries.csv")
+w_casks_df = pd.read_csv(WHISKY_BASE + "casks_taxonomy.csv")
+w_flavors_df = pd.read_csv(WHISKY_BASE + "flavors_taxonomy.csv")
 
 
 def choices(df, col):
@@ -156,10 +162,34 @@ def s_explore(ingredient_query, brand, category, form, blend_filter):
     return summary, d[list(S_COLS)].rename(columns=S_COLS)
 
 
+# ── WhiskyDB ──
+W_COLS = {
+    "name": "Spirit",
+    "type": "Type",
+    "age": "Age (years)",
+    "abv": "ABV %",
+    "volume_ml": "Volume (ml)",
+    "source_name": "Source",
+    "source_url": "Source URL",
+}
+
+def w_explore(query, spirit_type):
+    d = w_df
+    if query and query.strip():
+        d = d[d["name"].fillna("").str.contains(query.strip(), case=False, regex=False)]
+    if spirit_type != "All":
+        d = d[d["type"] == spirit_type]
+    summary = (
+        f"**{len(d)} spirits** match — out of {len(w_df)} in the free sample. "
+        f"The full WhiskyDB has **1,290+ spirits, 3,200+ distilleries & 20,000+ monthly auction-price benchmarks (2005 → today)**."
+    )
+    return summary, d[list(W_COLS)].rename(columns=W_COLS)
+
+
 # ── UI ──
 with gr.Blocks(title="Dataset Sample Explorers") as demo:
     gr.Markdown("# 🗂️ Dataset Sample Explorers")
-    gr.Markdown("""Interactive explorers for the **free samples** of three curated commercial datasets. Every record carries a source URL so any fact can be re-verified. Full datasets are available at each official portal.""")
+    gr.Markdown("""Interactive explorers for the **free samples** of four curated commercial datasets. Every record carries a source URL so any fact can be re-verified. Full datasets are available at each official portal.""")
 
     with gr.Tab("☕ RoasterDB — Specialty Coffee"):
         gr.Markdown(f"""**{len(r_df)} verified coffees from {r_df['source_roaster'].nunique()} artisan roasters**, tasting notes normalized to the **SCA Flavor Wheel**. Full dataset: **8,000+ products, 280+ roasters** — [roasterdb.net](https://specialty-coffee-roasterdb.pages.dev) · [🤗 sample dataset](https://huggingface.co/datasets/Ichlibitiche/roasterdb-specialty-coffee-sample) · [🏆 Kaggle](https://www.kaggle.com/datasets/ahtiticheamine/roasterdb-specialty-coffee-sample) · [🔄 Apify scraper](https://apify.com/dataengineered/specialty-coffee-roaster-scraper)""")
@@ -210,7 +240,25 @@ with gr.Blocks(title="Dataset Sample Explorers") as demo:
         s_btn.click(fn=s_explore, inputs=s_inputs, outputs=[s_text, s_table])
         demo.load(fn=s_explore, inputs=s_inputs, outputs=[s_text, s_table])
 
+    with gr.Tab("🥃 WhiskyDB — Fine Spirits"):
+        gr.Markdown(f"""**{len(w_df)} spirits + {len(w_dist_df)} distilleries**, provenance-tracked from open public sources, with **fully open cask & flavor taxonomies** (CC BY 4.0). Full dataset: **1,290+ spirits, 3,200+ distilleries, 20,000+ monthly auction-price benchmarks (Nov 2005 → today)** — [🤗 sample dataset](https://huggingface.co/datasets/Ichlibitiche/whiskydb-fine-spirits-sample) · [🐙 GitHub](https://github.com/WhiskyyDB/whisky-database) · [📧 get the full dataset](mailto:whiskeydn.kite979@simplelogin.com)""")
+        with gr.Row():
+            w_query = gr.Textbox(label="Spirit Search", placeholder="e.g. Lagavulin, Eagle Rare, Yamazaki...")
+            w_type = gr.Dropdown(choices=choices(w_df, "type"), value="All", label="Spirit Type")
+        w_btn = gr.Button("Explore Spirits", variant="primary")
+        w_text = gr.Markdown()
+        w_table = gr.Dataframe(label="Matching Spirits", wrap=True)
+        w_inputs = [w_query, w_type]
+        w_btn.click(fn=w_explore, inputs=w_inputs, outputs=[w_text, w_table])
+        demo.load(fn=w_explore, inputs=w_inputs, outputs=[w_text, w_table])
+        with gr.Accordion(f"🏭 Sample Distilleries ({len(w_dist_df)})", open=False):
+            gr.Dataframe(value=w_dist_df.rename(columns={"name": "Distillery", "country": "Country", "region": "Region", "source_url": "Source URL"})[["Distillery", "Country", "Region", "Source URL"]], wrap=True)
+        with gr.Accordion(f"🛢️ Open Cask Taxonomy ({len(w_casks_df)} styles, CC BY 4.0)", open=False):
+            gr.Dataframe(value=w_casks_df, wrap=True)
+        with gr.Accordion(f"👃 Open Flavor Taxonomy ({len(w_flavors_df)} descriptors, CC BY 4.0)", open=False):
+            gr.Dataframe(value=w_flavors_df, wrap=True)
+
     gr.Markdown("""---
-*Sample data CC BY-NC 4.0 (per-dataset attribution on each tab). FloraDB toxicity data is informational, not veterinary advice; SuppDB is factual label data, not medical advice. Full datasets commercially licensed at each portal. Sister project: [🔬 INCIDB Skincare Dupe Finder](https://huggingface.co/spaces/Ichlibitiche/incidb-skincare-dupe-finder).*""")
+*Sample data CC BY-NC 4.0 (per-dataset attribution on each tab); WhiskyDB taxonomies CC BY 4.0. FloraDB toxicity data is informational, not veterinary advice; SuppDB is factual label data, not medical advice. Full datasets commercially licensed at each portal. Sister project: [🔬 INCIDB Skincare Dupe Finder](https://huggingface.co/spaces/Ichlibitiche/incidb-skincare-dupe-finder).*""")
 
 demo.launch()