Upload 5 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+restaurants_synthetic_dataset.csv filter=lfs diff=lfs merge=lfs -text

README_minimal.md

@@ -0,0 +1,15 @@
+---
+title: Restaurant Insight Dashboard
+emoji: "🍽️"
+colorFrom: blue
+colorTo: indigo
+sdk: gradio
+sdk_version: "4.44.1"
+python_version: "3.10"
+app_file: app.py
+pinned: false
+---
+
+# Restaurant Insight Dashboard
+
+Select a restaurant and view review metrics, business indicators, and a simple recommendation.

app_minimal.py

@@ -0,0 +1,149 @@
+import pandas as pd
+import gradio as gr
+from pathlib import Path
+
+BASE_DIR = Path(__file__).resolve().parent
+BUSINESS_FILE = BASE_DIR / "restaurants_synthetic_dataset.csv"
+SUMMARY_FILE = BASE_DIR / "restaurants_synthetic_reviews_summary.csv"
+
+business_df = pd.read_csv(BUSINESS_FILE)
+summary_df = pd.read_csv(SUMMARY_FILE)
+
+business_df["date"] = pd.to_datetime(business_df["date"], errors="coerce")
+business_df["chiffre_affaire_eur"] = pd.to_numeric(business_df["chiffre_affaire_eur"], errors="coerce")
+business_df["google_rating"] = pd.to_numeric(business_df["google_rating"], errors="coerce")
+
+for col in [
+    "nb_reviews",
+    "note_review_moyenne",
+    "part_reviews_positives",
+    "part_reviews_mitigees",
+    "part_reviews_negatives",
+]:
+    if col in summary_df.columns:
+        summary_df[col] = pd.to_numeric(summary_df[col], errors="coerce")
+
+restaurant_choices = sorted(summary_df["restaurant_nom"].dropna().astype(str).unique().tolist())
+
+
+def fmt_pct(x):
+    return "N/A" if pd.isna(x) else f"{x * 100:.1f}%"
+
+
+def fmt_num(x, suffix=""):
+    return "N/A" if pd.isna(x) else f"{x:,.2f}{suffix}"
+
+
+def get_recommendation(avg_review, neg_share, sanitary, avg_google):
+    sanitary_text = "" if pd.isna(sanitary) else str(sanitary).lower()
+
+    if pd.notna(avg_review) and avg_review >= 4.3 and pd.notna(neg_share) and neg_share <= 0.10:
+        return "Strong performance. Keep quality consistent and maintain customer satisfaction."
+    if pd.notna(neg_share) and neg_share >= 0.30:
+        return "Priority improvement needed. Negative reviews are high and may hurt revenue and reputation."
+    if "à améliorer" in sanitary_text or "ameliorer" in sanitary_text:
+        return "Operational attention needed. Sanitary compliance may affect customer trust and performance."
+    if pd.notna(avg_google) and avg_google < 4.0:
+        return "Moderate performance. Improve service and customer experience to strengthen ratings."
+    return "Overall stable performance. Continue monitoring reviews, hygiene, and business indicators."
+
+
+def analyze_restaurant(restaurant_name):
+    if not restaurant_name:
+        return "Please select a restaurant.", "", ""
+
+    s = summary_df[summary_df["restaurant_nom"] == restaurant_name]
+    b = business_df[business_df["restaurant_nom"] == restaurant_name]
+
+    if s.empty and b.empty:
+        return f"No data found for {restaurant_name}.", "", ""
+
+    srow = s.iloc[0] if not s.empty else pd.Series(dtype=object)
+
+    city = srow.get("ville", "N/A")
+    price_range = srow.get("gamme_prix", "N/A")
+    sanitary = srow.get("niveau_sanitaire_reference", "N/A")
+    nb_reviews = srow.get("nb_reviews", pd.NA)
+    avg_review = srow.get("note_review_moyenne", pd.NA)
+    pos = srow.get("part_reviews_positives", pd.NA)
+    mixed = srow.get("part_reviews_mitigees", pd.NA)
+    neg = srow.get("part_reviews_negatives", pd.NA)
+
+    rest_type = "N/A"
+    if not b.empty and "type_restauration" in b.columns:
+        mode_vals = b["type_restauration"].mode()
+        if not mode_vals.empty:
+            rest_type = mode_vals.iloc[0]
+
+    avg_google = b["google_rating"].mean() if not b.empty else pd.NA
+    avg_revenue = b["chiffre_affaire_eur"].mean() if not b.empty else pd.NA
+
+    overview = f"""# Restaurant Overview
+
+**Name:** {restaurant_name}
+
+**City:** {city}
+
+**Type:** {rest_type}
+
+**Price range:** {price_range}
+
+**Sanitary reference:** {sanitary}
+
+**Average Google rating:** {fmt_num(avg_google, '/5')}
+
+**Average revenue:** {fmt_num(avg_revenue, ' EUR')}
+"""
+
+    review_insight = f"""# Review Insight
+
+**Number of reviews:** {"N/A" if pd.isna(nb_reviews) else int(nb_reviews)}
+
+**Average review score:** {fmt_num(avg_review, '/5')}
+
+**Positive reviews:** {fmt_pct(pos)}
+
+**Mixed reviews:** {fmt_pct(mixed)}
+
+**Negative reviews:** {fmt_pct(neg)}
+"""
+
+    recommendation = f"""# Recommendation
+
+{get_recommendation(avg_review, neg, sanitary, avg_google)}
+"""
+
+    return overview, review_insight, recommendation
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Restaurant Insight Dashboard")
+    gr.Markdown(
+        "Select a restaurant to view its review metrics, business indicators, and a simple recommendation."
+    )
+
+    restaurant_input = gr.Dropdown(
+        choices=restaurant_choices,
+        label="Restaurant",
+        value=restaurant_choices[0] if restaurant_choices else None,
+    )
+    analyze_btn = gr.Button("Analyze")
+
+    overview_output = gr.Markdown()
+    review_output = gr.Markdown()
+    recommendation_output = gr.Markdown()
+
+    analyze_btn.click(
+        fn=analyze_restaurant,
+        inputs=restaurant_input,
+        outputs=[overview_output, review_output, recommendation_output],
+    )
+
+    demo.load(
+        fn=analyze_restaurant,
+        inputs=restaurant_input,
+        outputs=[overview_output, review_output, recommendation_output],
+    )
+
+
+demo.launch(share=True)

requirements_minimal.txt

@@ -0,0 +1,3 @@
+gradio==4.44.1
+huggingface_hub==0.25.2
+pandas==2.2.2

restaurants_synthetic_dataset.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5281618241706cf2c016d102b1841f09f08083c37332daf6e022e2a86ea6a62
+size 41403049