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.md

@@ -1,10 +1,19 @@
 ---
-title: D6-SE21 GROUP PROJECT2
-emoji: 👀
-colorFrom: pink
-colorTo: blue
-sdk: docker
+title: Restaurant Insight Dashboard
+emoji: 🍽️
+colorFrom: blue
+colorTo: green
+sdk: gradio
+sdk_version: 4.44.1
+app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Restaurant Insight Dashboard
+
+This Hugging Face Space lets users select a restaurant and view:
+- customer review metrics
+- sanitary reference level
+- average Google rating
+- revenue trend
+- a simple managerial recommendation

app.py

@@ -0,0 +1,202 @@
+import pandas as pd
+import gradio as gr
+import matplotlib.pyplot as plt
+from pathlib import Path
+
+BASE_DIR = Path(__file__).resolve().parent if '__file__' in globals() else Path('.')
+DATA_FILE = BASE_DIR / 'restaurants_synthetic_dataset.csv'
+SUMMARY_FILE = BASE_DIR / 'restaurants_synthetic_reviews_summary.csv'
+
+# Load data once at startup
+business_df = pd.read_csv(DATA_FILE, low_memory=False)
+summary_df = pd.read_csv(SUMMARY_FILE, low_memory=False)
+
+# Clean types
+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')
+
+numeric_cols = [
+    'nb_reviews', 'note_review_moyenne', 'note_review_min', 'note_review_max',
+    'part_reviews_positives', 'part_reviews_mitigees', 'part_reviews_negatives'
+]
+for col in numeric_cols:
+    summary_df[col] = pd.to_numeric(summary_df[col], errors='coerce')
+
+# Create restaurant choices
+restaurant_choices = sorted(summary_df['restaurant_nom'].dropna().astype(str).unique().tolist())
+
+
+def safe_str(value, fallback='N/A'):
+    if pd.isna(value):
+        return fallback
+    text = str(value).strip()
+    return text if text else fallback
+
+
+def recommendation_text(avg_review, neg_share, sanitary_level, google_rating):
+    issues = []
+    strengths = []
+
+    if pd.notna(avg_review):
+        if avg_review >= 4.3:
+            strengths.append('very strong customer satisfaction')
+        elif avg_review >= 3.8:
+            strengths.append('solid customer satisfaction')
+        else:
+            issues.append('customer satisfaction is below the target level')
+
+    if pd.notna(neg_share):
+        if neg_share >= 0.30:
+            issues.append('negative reviews are relatively high')
+        elif neg_share <= 0.10:
+            strengths.append('negative reviews remain low')
+
+    sanitary_text = safe_str(sanitary_level, '').lower()
+    if 'à améliorer' in sanitary_text or 'ameliorer' in sanitary_text:
+        issues.append('sanitary reference level suggests improvement is needed')
+    elif sanitary_text:
+        strengths.append(f'sanitary status is {safe_str(sanitary_level)}')
+
+    if pd.notna(google_rating):
+        if google_rating >= 4.3:
+            strengths.append('google rating is strong')
+        elif google_rating < 4.0:
+            issues.append('google rating could be improved')
+
+    if issues and strengths:
+        return (
+            'Recommendation: monitor this restaurant closely. It shows some positive signals, but the priority '
+            'should be to improve service consistency and reduce the sources of negative reviews. '
+            f"Strengths include {', '.join(strengths[:2])}. Main issues: {', '.join(issues[:2])}."
+        )
+    if issues:
+        return (
+            'Recommendation: improvement plan needed. Focus first on the most visible weaknesses in customer '
+            f"experience and operations. Main issues: {', '.join(issues[:3])}."
+        )
+    return (
+        'Recommendation: maintain current performance and continue monitoring quality. '
+        f"Main strengths: {', '.join(strengths[:3]) if strengths else 'overall stable performance'}."
+    )
+
+
+def build_chart(restaurant_name):
+    subset = business_df[business_df['restaurant_nom'] == restaurant_name].copy()
+    subset = subset.sort_values('date')
+    fig, ax = plt.subplots(figsize=(7, 4))
+    ax.plot(subset['date'], subset['chiffre_affaire_eur'], marker='o')
+    ax.set_title(f'Revenue trend - {restaurant_name}')
+    ax.set_xlabel('Date')
+    ax.set_ylabel('Revenue (EUR)')
+    plt.xticks(rotation=45)
+    plt.tight_layout()
+    return fig
+
+
+def analyze_restaurant(restaurant_name):
+    if not restaurant_name:
+        return 'Please choose a restaurant.', 'No data yet.', None
+
+    review_rows = summary_df[summary_df['restaurant_nom'] == restaurant_name].copy()
+    business_rows = business_df[business_df['restaurant_nom'] == restaurant_name].copy()
+
+    if review_rows.empty and business_rows.empty:
+        return f'No data found for {restaurant_name}.', 'No data available.', None
+
+    review_row = review_rows.iloc[0] if not review_rows.empty else pd.Series(dtype=object)
+
+    city = safe_str(review_row.get('ville'))
+    price_range = safe_str(review_row.get('gamme_prix'))
+    sanitary = safe_str(review_row.get('niveau_sanitaire_reference'))
+    nb_reviews = review_row.get('nb_reviews')
+    avg_review = review_row.get('note_review_moyenne')
+    pos_share = review_row.get('part_reviews_positives')
+    mixed_share = review_row.get('part_reviews_mitigees')
+    neg_share = review_row.get('part_reviews_negatives')
+
+    type_restauration = safe_str(business_rows['type_restauration'].mode().iloc[0] if not business_rows.empty and not business_rows['type_restauration'].mode().empty else None)
+    avg_google_rating = business_rows['google_rating'].mean() if not business_rows.empty else None
+    avg_revenue = business_rows['chiffre_affaire_eur'].mean() if not business_rows.empty else None
+    latest_revenue = business_rows.sort_values('date')['chiffre_affaire_eur'].dropna().iloc[-1] if not business_rows.empty and business_rows['chiffre_affaire_eur'].notna().any() else None
+
+    overview = f"""
+## Restaurant Overview
+- **Name:** {restaurant_name}
+- **City:** {city}
+- **Type:** {type_restauration}
+- **Price range:** {price_range}
+- **Sanitary reference:** {sanitary}
+- **Number of reviews:** {int(nb_reviews) if pd.notna(nb_reviews) else 'N/A'}
+- **Average review score:** {avg_review:.2f}/5
+- **Average Google rating:** {avg_google_rating:.2f}/5 if pd.notna(avg_google_rating) else N/A
+- **Average monthly revenue:** {avg_revenue:,.0f} EUR if pd.notna(avg_revenue) else N/A
+- **Latest revenue observed:** {latest_revenue:,.0f} EUR if pd.notna(latest_revenue) else N/A
+"""
+
+    # Fix conditional formatting in markdown text
+    overview = overview.replace(
+        f"{avg_google_rating:.2f}/5 if pd.notna(avg_google_rating) else N/A",
+        f"{avg_google_rating:.2f}/5" if pd.notna(avg_google_rating) else 'N/A'
+    )
+    overview = overview.replace(
+        f"{avg_revenue:,.0f} EUR if pd.notna(avg_revenue) else N/A",
+        f"{avg_revenue:,.0f} EUR" if pd.notna(avg_revenue) else 'N/A'
+    )
+    overview = overview.replace(
+        f"{latest_revenue:,.0f} EUR if pd.notna(latest_revenue) else N/A",
+        f"{latest_revenue:,.0f} EUR" if pd.notna(latest_revenue) else 'N/A'
+    )
+
+    insight = f"""
+## Review Insight
+- **Positive reviews:** {pos_share * 100:.1f}%
+- **Mixed reviews:** {mixed_share * 100:.1f}%
+- **Negative reviews:** {neg_share * 100:.1f}%
+
+## Recommendation
+{recommendation_text(avg_review, neg_share, sanitary, avg_google_rating)}
+"""
+
+    fig = build_chart(restaurant_name) if not business_rows.empty else None
+    return overview, insight, fig
+
+
+DESCRIPTION = """
+Choose a restaurant to view its customer review profile, business indicators, and a simple managerial recommendation.
+This app combines review summary data and synthetic business performance data.
+"""
+
+with gr.Blocks() as demo:
+    gr.Markdown('# Restaurant Insight Dashboard')
+    gr.Markdown(DESCRIPTION)
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            restaurant_input = gr.Dropdown(
+                choices=restaurant_choices,
+                label='Restaurant name',
+                value=restaurant_choices[0] if restaurant_choices else None,
+                filterable=True,
+            )
+            analyze_btn = gr.Button('Analyze restaurant')
+        with gr.Column(scale=2):
+            overview_output = gr.Markdown(label='Overview')
+            insight_output = gr.Markdown(label='Insight')
+
+    revenue_plot = gr.Plot(label='Revenue trend')
+
+    analyze_btn.click(
+        fn=analyze_restaurant,
+        inputs=restaurant_input,
+        outputs=[overview_output, insight_output, revenue_plot],
+    )
+
+    demo.load(
+        fn=analyze_restaurant,
+        inputs=restaurant_input,
+        outputs=[overview_output, insight_output, revenue_plot],
+    )
+
+if __name__ == '__main__':
+    demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio>=4.0.0
+pandas>=2.0.0
+matplotlib>=3.7.0

restaurants_synthetic_dataset.csv

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