RoasterDB tab: full dataset 13,000+ products from 270+ roasters
Browse filesThe tab text and the explore summary said 12,000+ products. Edition 2026.11 holds 13,670 products from 278 roasters; the floor now matches roasterdb.dataengineered.io and the dataset README (RoasterDB/specialty-coffee-roasterdb#33). Only these two strings change.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
app.py
CHANGED
|
@@ -68,7 +68,7 @@ def r_explore(roaster, country, process, roast, flavor, currency, max_price):
|
|
| 68 |
d = d[d["price_value"].notna() & (d["price_value"] <= max_price)]
|
| 69 |
summary = (
|
| 70 |
f"**{len(d)} coffees** from **{d['source_roaster'].nunique()} roasters** match β "
|
| 71 |
-
f"out of {len(r_df)} in the free sample. The full RoasterDB has **
|
| 72 |
)
|
| 73 |
return summary, d[list(R_COLS)].rename(columns=R_COLS).sort_values(["Currency", "Price"])
|
| 74 |
|
|
@@ -208,7 +208,7 @@ with gr.Blocks(title="Dataset Sample Explorers") as demo:
|
|
| 208 |
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.""")
|
| 209 |
|
| 210 |
with gr.Tab("β RoasterDB β Specialty Coffee"):
|
| 211 |
-
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: **
|
| 212 |
with gr.Row():
|
| 213 |
r_roaster = gr.Dropdown(choices=choices(r_df, "source_roaster"), value="All", label="Roaster")
|
| 214 |
r_country = gr.Dropdown(choices=choices(r_df, "origin_country"), value="All", label="Origin Country")
|
|
|
|
| 68 |
d = d[d["price_value"].notna() & (d["price_value"] <= max_price)]
|
| 69 |
summary = (
|
| 70 |
f"**{len(d)} coffees** from **{d['source_roaster'].nunique()} roasters** match β "
|
| 71 |
+
f"out of {len(r_df)} in the free sample. The full RoasterDB has **13,000+ products from 270+ roasters**."
|
| 72 |
)
|
| 73 |
return summary, d[list(R_COLS)].rename(columns=R_COLS).sort_values(["Currency", "Price"])
|
| 74 |
|
|
|
|
| 208 |
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.""")
|
| 209 |
|
| 210 |
with gr.Tab("β RoasterDB β Specialty Coffee"):
|
| 211 |
+
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: **13,000+ products, 270+ roasters** β [roasterdb.dataengineered.io](https://roasterdb.dataengineered.io) Β· [π€ sample dataset](https://huggingface.co/datasets/Ichlibitiche/roasterdb-specialty-coffee-sample) Β· [π Kaggle](https://www.kaggle.com/datasets/dataengineered/roasterdb-specialty-coffee-sample) Β· [π Apify scraper](https://apify.com/dataengineered/specialty-coffee-roaster-scraper)""")
|
| 212 |
with gr.Row():
|
| 213 |
r_roaster = gr.Dropdown(choices=choices(r_df, "source_roaster"), value="All", label="Roaster")
|
| 214 |
r_country = gr.Dropdown(choices=choices(r_df, "origin_country"), value="All", label="Origin Country")
|