Upload 5 files

README.md

@@ -0,0 +1,45 @@
+---
+title: StayWise AI
+emoji: 🏠
+colorFrom: blue
+colorTo: indigo
+sdk: gradio
+sdk_version: 4.44.1
+app_file: app.py
+pinned: false
+python_version: 3.10
+---
+
+# StayWise AI
+
+AI-powered pricing and performance optimization for short-term rentals.
+
+## What the app does
+
+- Loads the Airbnb project datasets.
+- Lets the user enter property information.
+- Finds comparable listings.
+- Estimates occupancy, revenue, demand score, opportunity score, and pricing recommendation.
+- Optionally sends the pipeline output to n8n through a webhook.
+- Displays the n8n response inside the app.
+
+## n8n integration
+
+Create a Space secret called:
+
+`N8N_WEBHOOK_URL`
+
+The n8n workflow should use:
+
+Webhook Trigger → Set/Edit Fields → Google Sheets or Email → Respond to Webhook
+
+Recommended JSON response:
+
+```json
+{
+  "status": "success",
+  "insight": "This listing has high demand potential but is underpriced.",
+  "next_step": "Consider increasing price by 8% and improving review quality.",
+  "log": "Saved to database and flagged for monitoring."
+}
+```

airbnb_recommendation_output.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18cce6473679041361120d96e14af3742f994175b8387c9a90b5a65328f3fa14
+size 10814149

app.py

@@ -0,0 +1,328 @@
+
+import os
+import json
+import math
+import requests
+import pandas as pd
+import gradio as gr
+
+APP_NAME = "StayWise AI"
+
+DATA_FILE = "synthetic_airbnb_project_data.csv"
+OUTPUT_FILE = "airbnb_recommendation_output.csv"
+
+# Optional: set this in Hugging Face Space Secrets as N8N_WEBHOOK_URL
+N8N_WEBHOOK_URL = os.getenv("N8N_WEBHOOK_URL", "").strip()
+
+def load_data():
+    data = pd.read_csv(DATA_FILE)
+    output = pd.read_csv(OUTPUT_FILE) if os.path.exists(OUTPUT_FILE) else data.copy()
+    return data, output
+
+df, output_df = load_data()
+
+def safe_mean(series, default=0):
+    series = pd.to_numeric(series, errors="coerce").dropna()
+    if len(series) == 0:
+        return default
+    return float(series.mean())
+
+def get_choices(column):
+    if column in df.columns:
+        return sorted([str(x) for x in df[column].dropna().unique().tolist()])
+    return []
+
+neighbourhood_groups = get_choices("neighbourhood_group")
+room_types = get_choices("room_type")
+neighbourhoods = get_choices("neighbourhood")
+seasons = get_choices("season") if "season" in df.columns else ["Low Season", "Shoulder Season", "High Season"]
+
+def estimate_pipeline(neighbourhood_group, neighbourhood, room_type, price, availability_365, season, local_event_score, synthetic_rating, customer_sentiment_score, send_to_n8n):
+    price = float(price)
+    availability_365 = float(availability_365)
+    local_event_score = float(local_event_score)
+    synthetic_rating = float(synthetic_rating)
+    customer_sentiment_score = float(customer_sentiment_score)
+
+    comparable = df.copy()
+
+    if "neighbourhood_group" in comparable.columns:
+        comparable = comparable[comparable["neighbourhood_group"].astype(str) == str(neighbourhood_group)]
+
+    if "room_type" in comparable.columns:
+        comparable = comparable[comparable["room_type"].astype(str) == str(room_type)]
+
+    if "neighbourhood" in comparable.columns and neighbourhood:
+        local_comp = comparable[comparable["neighbourhood"].astype(str) == str(neighbourhood)]
+        if len(local_comp) >= 5:
+            comparable = local_comp
+
+    if len(comparable) < 5:
+        comparable = df[df["room_type"].astype(str) == str(room_type)] if "room_type" in df.columns else df.copy()
+
+    competitor_avg_price = safe_mean(comparable.get("price", pd.Series(dtype=float)), default=price)
+    avg_occupancy = safe_mean(comparable.get("occupancy_rate", pd.Series(dtype=float)), default=0.50)
+    avg_demand = safe_mean(comparable.get("demand_score", pd.Series(dtype=float)), default=50)
+    avg_revenue = safe_mean(comparable.get("monthly_revenue", pd.Series(dtype=float)), default=price * 15)
+
+    if competitor_avg_price == 0:
+        price_vs_competitor_pct = 0
+    else:
+        price_vs_competitor_pct = ((price - competitor_avg_price) / competitor_avg_price) * 100
+
+    # Occupancy estimate: base from comparable listings, adjusted for price gap, events, season, rating and sentiment
+    season_boost = {
+        "Low": -0.08,
+        "Low Season": -0.08,
+        "Medium": 0.00,
+        "Shoulder Season": 0.00,
+        "High": 0.08,
+        "High Season": 0.08,
+        "Peak": 0.12,
+        "Peak Season": 0.12
+    }.get(str(season), 0.00)
+
+    price_penalty = max(min(price_vs_competitor_pct / 100, 0.35), -0.35) * 0.30
+    event_boost = (local_event_score / 100) * 0.12
+    rating_boost = (synthetic_rating - 4.0) * 0.06
+    sentiment_boost = customer_sentiment_score * 0.08
+
+    occupancy_estimate = avg_occupancy + season_boost + event_boost + rating_boost + sentiment_boost - price_penalty
+    occupancy_estimate = max(0.05, min(0.95, occupancy_estimate))
+
+    booked_nights_month = round(occupancy_estimate * 30)
+    monthly_revenue = round(price * booked_nights_month, 2)
+
+    demand_score = (
+        0.45 * avg_demand
+        + 0.25 * (occupancy_estimate * 100)
+        + 0.15 * local_event_score
+        + 0.10 * ((synthetic_rating / 5) * 100)
+        + 0.05 * ((customer_sentiment_score + 1) / 2 * 100)
+    )
+    demand_score = round(max(0, min(100, demand_score)), 1)
+
+    if demand_score >= 70:
+        demand_level = "High"
+    elif demand_score >= 45:
+        demand_level = "Medium"
+    else:
+        demand_level = "Low"
+
+    if price_vs_competitor_pct > 15 and demand_level != "High":
+        pricing_recommendation = "Consider lowering price"
+        suggested_price = round(competitor_avg_price * 1.05, 2)
+    elif price_vs_competitor_pct < -10 and demand_level in ["Medium", "High"]:
+        pricing_recommendation = "Consider raising price"
+        suggested_price = round(min(competitor_avg_price * 0.98, price * 1.12), 2)
+    else:
+        pricing_recommendation = "Keep price stable"
+        suggested_price = round(price, 2)
+
+    opportunity_score = round(
+        (demand_score * 0.45)
+        + (occupancy_estimate * 100 * 0.25)
+        + (synthetic_rating / 5 * 100 * 0.15)
+        + ((customer_sentiment_score + 1) / 2 * 100 * 0.15),
+        2
+    )
+
+    if pricing_recommendation == "Consider lowering price":
+        insight = "The listing appears overpriced compared with similar properties, which may limit occupancy."
+        next_step = f"Test a lower price around ${suggested_price} and monitor occupancy changes."
+    elif pricing_recommendation == "Consider raising price":
+        insight = "The listing appears underpriced relative to demand and comparable properties."
+        next_step = f"Consider increasing the price toward ${suggested_price} while maintaining review quality."
+    else:
+        insight = "The current price is broadly aligned with the comparable market."
+        next_step = "Keep the price stable and focus on improving visibility, reviews, and conversion."
+
+    final_recommendation = f"{pricing_recommendation}. {next_step}"
+
+    result = {
+        "app_name": APP_NAME,
+        "neighbourhood_group": neighbourhood_group,
+        "neighbourhood": neighbourhood,
+        "room_type": room_type,
+        "current_price": price,
+        "suggested_price": suggested_price,
+        "competitor_avg_price": round(competitor_avg_price, 2),
+        "price_vs_competitor_pct": round(price_vs_competitor_pct, 2),
+        "occupancy_estimate": round(occupancy_estimate, 3),
+        "booked_nights_month": booked_nights_month,
+        "monthly_revenue": monthly_revenue,
+        "demand_score": demand_score,
+        "demand_level": demand_level,
+        "opportunity_score": opportunity_score,
+        "pricing_recommendation": pricing_recommendation,
+        "insight": insight,
+        "next_step": next_step,
+        "final_recommendation": final_recommendation
+    }
+
+    n8n_result = call_n8n(result) if send_to_n8n else {
+        "status": "not_sent",
+        "insight": "n8n automation was not triggered.",
+        "next_step": "Turn on the checkbox and add your N8N_WEBHOOK_URL secret to activate automation.",
+        "log": "Local pipeline only."
+    }
+
+    summary_md = f"""
+# {APP_NAME} — Pipeline Result
+
+## Pricing recommendation
+**{pricing_recommendation}**
+
+| Metric | Result |
+|---|---:|
+| Current price | ${price:,.2f} |
+| Suggested price | ${suggested_price:,.2f} |
+| Comparable average price | ${competitor_avg_price:,.2f} |
+| Price vs competitors | {price_vs_competitor_pct:.2f}% |
+| Estimated occupancy | {occupancy_estimate * 100:.1f}% |
+| Estimated booked nights/month | {booked_nights_month} |
+| Estimated monthly revenue | ${monthly_revenue:,.2f} |
+| Demand score | {demand_score}/100 |
+| Demand level | {demand_level} |
+| Opportunity score | {opportunity_score}/100 |
+
+## Business insight
+{insight}
+
+## Next step
+{next_step}
+"""
+
+    n8n_md = f"""
+# Automation Output
+
+**Status:** {n8n_result.get("status", "unknown")}
+
+**Insight:** {n8n_result.get("insight", "No insight returned.")}
+
+**Next step:** {n8n_result.get("next_step", "No next step returned.")}
+
+**Log:** {n8n_result.get("log", "No log returned.")}
+"""
+
+    comp_cols = [c for c in ["id", "name", "neighbourhood_group", "neighbourhood", "room_type", "price", "occupancy_rate", "monthly_revenue", "demand_score", "demand_level", "pricing_recommendation"] if c in comparable.columns]
+    comparable_preview = comparable[comp_cols].head(10).copy() if comp_cols else comparable.head(10).copy()
+
+    return summary_md, n8n_md, comparable_preview, json.dumps(result, indent=2)
+
+def call_n8n(payload):
+    if not N8N_WEBHOOK_URL:
+        return {
+            "status": "not_configured",
+            "insight": "No n8n webhook URL has been configured in the Space secrets.",
+            "next_step": "Add N8N_WEBHOOK_URL in Hugging Face Space Settings → Secrets.",
+            "log": "Pipeline calculated locally, but automation was not sent."
+        }
+
+    try:
+        response = requests.post(N8N_WEBHOOK_URL, json=payload, timeout=15)
+        if response.status_code >= 200 and response.status_code < 300:
+            try:
+                data = response.json()
+                return {
+                    "status": data.get("status", "success"),
+                    "insight": data.get("insight", "n8n received and processed the recommendation."),
+                    "next_step": data.get("next_step", "Review the stored record or report generated by n8n."),
+                    "log": data.get("log", "Automation completed.")
+                }
+            except Exception:
+                return {
+                    "status": "success",
+                    "insight": "n8n received the recommendation.",
+                    "next_step": "Check the connected output in n8n.",
+                    "log": response.text[:500]
+                }
+
+        return {
+            "status": "error",
+            "insight": f"n8n returned HTTP {response.status_code}.",
+            "next_step": "Check the webhook URL and the Respond to Webhook node.",
+            "log": response.text[:500]
+        }
+
+    except Exception as e:
+        return {
+            "status": "error",
+            "insight": "The app could not reach the n8n workflow.",
+            "next_step": "Verify that the production webhook URL is active and public.",
+            "log": str(e)
+        }
+
+custom_css = """
+.gradio-container {
+    max-width: 1200px !important;
+    margin: auto !important;
+}
+#hero {
+    background: linear-gradient(135deg, #0f172a 0%, #1e3a8a 55%, #0284c7 100%);
+    padding: 28px;
+    border-radius: 22px;
+    color: white;
+    margin-bottom: 20px;
+}
+#hero h1 {
+    font-size: 42px;
+    margin-bottom: 6px;
+}
+#hero p {
+    font-size: 17px;
+    opacity: 0.92;
+}
+.card {
+    border-radius: 18px;
+}
+"""
+
+with gr.Blocks(css=custom_css, title=APP_NAME, theme=gr.themes.Soft()) as demo:
+    gr.HTML(f"""
+    <div id="hero">
+        <h1>{APP_NAME}</h1>
+        <p>AI-powered pricing and performance optimization for short-term rentals.</p>
+    </div>
+    """)
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            gr.Markdown("## Property Inputs")
+            neighbourhood_group = gr.Dropdown(neighbourhood_groups, label="Neighbourhood Group", value=neighbourhood_groups[0] if neighbourhood_groups else None)
+            neighbourhood = gr.Dropdown(neighbourhoods, label="Neighbourhood", value=neighbourhoods[0] if neighbourhoods else None)
+            room_type = gr.Dropdown(room_types, label="Room Type", value=room_types[0] if room_types else None)
+            price = gr.Slider(20, 1000, value=150, step=5, label="Current Nightly Price ($)")
+            availability_365 = gr.Slider(0, 365, value=180, step=1, label="Availability per Year")
+            season = gr.Dropdown(seasons, label="Season", value=seasons[0] if seasons else None)
+            local_event_score = gr.Slider(0, 100, value=50, step=1, label="Local Event Demand Score")
+            synthetic_rating = gr.Slider(1, 5, value=4.4, step=0.1, label="Guest Rating")
+            customer_sentiment_score = gr.Slider(-1, 1, value=0.2, step=0.05, label="Customer Sentiment Score")
+            send_to_n8n = gr.Checkbox(label="Send pipeline output to n8n", value=False)
+            run_btn = gr.Button("Run Full Pipeline", variant="primary")
+
+        with gr.Column(scale=2):
+            pipeline_output = gr.Markdown(label="Pipeline Result")
+            n8n_output = gr.Markdown(label="Automation Output")
+            comparable_table = gr.Dataframe(label="Comparable Listings", interactive=False)
+            json_output = gr.Code(label="Pipeline JSON Output", language="json")
+
+    run_btn.click(
+        estimate_pipeline,
+        inputs=[
+            neighbourhood_group,
+            neighbourhood,
+            room_type,
+            price,
+            availability_365,
+            season,
+            local_event_score,
+            synthetic_rating,
+            customer_sentiment_score,
+            send_to_n8n
+        ],
+        outputs=[pipeline_output, n8n_output, comparable_table, json_output]
+    )
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio==4.44.1
+pandas==2.2.3
+requests==2.32.3

synthetic_airbnb_project_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e63f75596406a07ad35fb85e63a803708244e352792c6dcdf323bf788c00b19
+size 17968855