Upload 3 files

Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.13.5-slim
+
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt ./
+COPY src/ ./src/
+
+RUN pip3 install -r requirements.txt
+
+EXPOSE 8501
+
+HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
+
+ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]

requirements.txt

@@ -0,0 +1,4 @@
+streamlit
+requests
+pandas
+numpy

src/streamlit_app.py

@@ -0,0 +1,169 @@
+import os
+import datetime as dt
+import numpy as np
+import pandas as pd
+import requests
+import streamlit as st
+
+# --- CONFIG ---
+API_URL = os.getenv("API_URL", "https://rjuro-hotel-cancel-api.hf.space/predict_batch")
+
+NUMERIC_FEATURES = [
+    'lead_time','arrival_date_week_number','arrival_date_day_of_month',
+    'stays_in_weekend_nights','stays_in_week_nights','adults','children',
+    'babies','is_repeated_guest','previous_cancellations',
+    'previous_bookings_not_canceled','booking_changes','agent',
+    'days_in_waiting_list','adr','required_car_parking_spaces',
+    'total_of_special_requests','total_guests','total_nights','is_summer',
+    'previous_cancellation_rate'
+]
+CATEGORICAL_FEATURES = [
+    'hotel','meal','market_segment','distribution_channel',
+    'reserved_room_type','deposit_type','customer_type'
+]
+ALL_FEATURES = NUMERIC_FEATURES + CATEGORICAL_FEATURES
+
+st.set_page_config(page_title="Weekly Cancellation Predictions", layout="wide")
+
+# --- SIMPLE SYNTH GENERATOR ---
+def synth_week(n_per_day=300, seed=42):
+    rng = np.random.default_rng(seed)
+    today = dt.date.today()
+    all_rows = []
+    for i in range(1, 8):
+        arr = today + dt.timedelta(days=i)
+        week = int(arr.isocalendar().week)
+        dom = arr.day
+        is_summer = int(arr.month in [6,7,8])
+
+        n = n_per_day
+        lead_time = np.clip(rng.gamma(2.0, 60.0, n).astype(int), 1, 365)
+        wkd = rng.poisson(1.0, n)
+        wk = rng.poisson(3.0, n)
+        adults = np.maximum(1, rng.poisson(1.5, n)+1)
+        children = rng.binomial(2, 0.15, n)
+        babies = rng.binomial(1, 0.05, n)
+        is_repeated_guest = rng.binomial(1, 0.12, n)
+        prev_canc = rng.binomial(2, 0.05, n)
+        prev_notc = rng.binomial(3, 0.15, n)
+        booking_changes = rng.poisson(0.2, n)
+        agent = rng.integers(0, 5, n)  # 0≈direct
+        wait_list = rng.binomial(5, 0.05, n)
+        adr = np.clip(rng.normal(120, 35, n), 30, 450)
+        parking = rng.binomial(1, 0.12, n)
+        special_req = rng.poisson(0.6, n)
+        total_nights = (wkd + wk).astype(int)
+        total_guests = (adults + children + babies).astype(int)
+        prev_rate = prev_canc / np.maximum(1e-6, (prev_canc + prev_notc + 1e-6))
+
+        def choice(vals, probs):
+            p = np.array(probs, dtype=float); p = p / p.sum()
+            return rng.choice(vals, p=p, size=n)
+
+        hotel = choice(['City Hotel','Resort Hotel'], [0.7, 0.3])
+        meal = choice(['BB','HB','FB','SC'], [0.75,0.15,0.03,0.07])
+        market = choice(['Online TA','Direct','Corporate','Offline TA/TO'], [0.45,0.30,0.15,0.10])
+        channel = choice(['TA/TO','Direct','Corporate','GDS'], [0.5,0.3,0.15,0.05])
+        roomtype = choice(list("ABCDEFG"), [0.35,0.25,0.15,0.1,0.08,0.05,0.02])
+        deposit = choice(['No Deposit','Non Refund','Refundable'], [0.75,0.15,0.10])
+        cust = choice(['Transient','Contract','Group','Transient-Party'], [0.7,0.15,0.08,0.07])
+
+        df = pd.DataFrame({
+            'lead_time': lead_time,
+            'arrival_date_week_number': week,
+            'arrival_date_day_of_month': dom,
+            'stays_in_weekend_nights': wkd,
+            'stays_in_week_nights': wk,
+            'adults': adults,
+            'children': children,
+            'babies': babies,
+            'is_repeated_guest': is_repeated_guest,
+            'previous_cancellations': prev_canc,
+            'previous_bookings_not_canceled': prev_notc,
+            'booking_changes': booking_changes,
+            'agent': agent,
+            'days_in_waiting_list': wait_list,
+            'adr': adr,
+            'required_car_parking_spaces': parking,
+            'total_of_special_requests': special_req,
+            'total_guests': total_guests,
+            'total_nights': total_nights,
+            'is_summer': is_summer,
+            'previous_cancellation_rate': prev_rate,
+            'hotel': hotel,
+            'meal': meal,
+            'market_segment': market,
+            'distribution_channel': channel,
+            'reserved_room_type': roomtype,
+            'deposit_type': deposit,
+            'customer_type': cust
+        })
+        df.insert(0, "arrival_date", pd.Timestamp(arr))
+        all_rows.append(df)
+    return pd.concat(all_rows, ignore_index=True)
+
+def call_api(df: pd.DataFrame) -> np.ndarray:
+    payload = {"data": df[ALL_FEATURES].to_dict(orient="records")}
+    r = requests.post(API_URL, json=payload, timeout=60)
+    r.raise_for_status()
+    return np.array(r.json()["probabilities"])
+
+# --- UI ---
+st.title("Weekly Booking Predictions")
+st.caption("API: " + API_URL)
+
+with st.sidebar:
+    st.header("Simulation")
+    n_per_day = st.slider("Synthetic bookings per day", 50, 2000, 400, 50)
+    t_low = st.slider("Reminder threshold", 0.05, 0.60, 0.30, 0.01)
+    t_high = st.slider("Perk (prepay upgrade) threshold", 0.30, 0.95, 0.65, 0.01)
+    seed = st.number_input("Random seed", 0, 99999, 42, 1)
+    st.caption("Rules: p ≥ t_high → Perk; t_low ≤ p < t_high → Reminder; else → None.")
+
+cols = st.columns(2)
+with cols[0]:
+    if st.button("Generate & Predict", use_container_width=True):
+        df = synth_week(n_per_day=n_per_day, seed=int(seed))
+        probs = call_api(df)
+        df['pred_cancel_prob'] = probs
+        df['action'] = np.where(
+            probs >= t_high, "Perk-Upgrade (Prepay)",
+            np.where(probs >= t_low, "Reminder", "None")
+        )
+
+        daily = (
+            df.groupby(df['arrival_date'].dt.date)
+              .agg(n_bookings=('arrival_date','count'),
+                   mean_risk=('pred_cancel_prob','mean'),
+                   p75=('pred_cancel_prob', lambda x: np.quantile(x, 0.75)),
+                   n_perk=('action', lambda s: (s=="Perk-Upgrade (Prepay)").sum()),
+                   n_reminder=('action', lambda s: (s=="Reminder").sum()),
+                   n_none=('action', lambda s: (s=="None").sum()))
+              .reset_index()
+              .rename(columns={'arrival_date':'date'})
+        )
+
+        st.subheader("Daily Summary (Next 7 Days)")
+        st.dataframe(daily, use_container_width=True, hide_index=True)
+
+        st.subheader("Preview: First 200 Bookings with Suggested Actions")
+        st.dataframe(
+            df[['arrival_date','hotel','market_segment','deposit_type','lead_time',
+                'total_nights','total_guests','pred_cancel_prob','action']].head(200),
+            use_container_width=True, hide_index=True
+        )
+
+        st.download_button(
+            "Download Full Weekly Predictions (CSV)",
+            df.to_csv(index=False).encode("utf-8"),
+            file_name="weekly_predictions_with_actions.csv",
+            mime="text/csv"
+        )
+
+with cols[1]:
+    st.subheader("How it works")
+    st.markdown(
+        "- Synthetic bookings for the next 7 days\n"
+        "- Calls the public FastAPI to get cancellation probabilities\n"
+        "- Simple rules pick suggested actions"
+    )