Deploy docker Streamlit app

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.10-slim
+ENV PYTHONUNBUFFERED=1
+# HF Spaces sets PORT; default to 7860 for local dev
+ENV PORT=7860
+WORKDIR /app
+COPY requirements.txt /app/requirements.txt
+RUN apt-get update && apt-get install -y --no-install-recommends build-essential         && rm -rf /var/lib/apt/lists/*         && pip install --no-cache-dir -r /app/requirements.txt
+COPY app.py /app/app.py
+EXPOSE 7860
+# Use shell form so $PORT expands
+CMD streamlit run app.py --server.port $PORT --server.address 0.0.0.0

README.md

@@ -1,10 +1,11 @@
 ---
-title: Customer Prediction App
-emoji: 📈
-colorFrom: blue
-colorTo: indigo
+title: Tourism Prediction App
+emoji: 🏝️
+colorFrom: yellow
+colorTo: green
 sdk: docker
+app_port: 7860
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+<!-- redeploy 1756565971 -->

app.py

@@ -0,0 +1,78 @@
+import os, json, joblib
+import pandas as pd
+import streamlit as st
+from huggingface_hub import hf_hub_download
+
+st.set_page_config(page_title="Wellness Package Predictor", page_icon="🏝️", layout="centered")
+st.title("🏝️ Wellness Tourism Package — Purchase Propensity")
+
+def get_secret(name: str, default=None):
+    try:
+        return st.secrets[name]
+    except Exception:
+        return os.getenv(name, default)
+
+MODEL_REPO = get_secret("MODEL_REPO", "MBG0903/tourism_customer_xgb")
+HF_TOKEN   = get_secret("HF_TOKEN", None)
+
+@st.cache_resource(show_spinner=True)
+def load_artifacts(repo_id: str, token: str | None):
+    model_path = hf_hub_download(repo_id=repo_id, filename="model.joblib", token=token)
+    meta_path  = hf_hub_download(repo_id=repo_id, filename="metadata.json", token=token)
+    model = joblib.load(model_path)
+    with open(meta_path, "r") as f:
+        meta = json.load(f)
+    return model, meta
+
+try:
+    model, meta = load_artifacts(MODEL_REPO, HF_TOKEN)
+except Exception as e:
+    st.error(f"Failed to load model artifacts from {MODEL_REPO}. Details: {e}")
+    st.stop()
+
+st.caption("Model metrics (from training)")
+st.json(meta.get("metrics", {}))
+
+st.sidebar.header("Enter Customer Profile")
+def i_num(label, value, minv=None, maxv=None, step=1):
+    return st.sidebar.number_input(label, value=value, min_value=minv, max_value=maxv, step=step)
+
+inputs = {}
+inputs["CustomerID"] = st.sidebar.text_input("CustomerID", "CUST_000001")
+inputs["Age"] = i_num("Age", 32, 18, 90)
+inputs["TypeofContact"] = st.sidebar.selectbox("TypeofContact", ["Company Invited","Self Inquiry"])
+inputs["CityTier"] = st.sidebar.selectbox("CityTier", ["Tier 1","Tier 2","Tier 3"])
+inputs["Occupation"] = st.sidebar.selectbox("Occupation", ["Salaried","Freelancer","Self Employed","Student","Retired"])
+inputs["Gender"] = st.sidebar.selectbox("Gender", ["Male","Female"])
+inputs["NumberOfPersonVisiting"] = i_num("NumberOfPersonVisiting", 2, 1, 10)
+inputs["PreferredPropertyStar"] = i_num("PreferredPropertyStar", 4, 1, 5)
+inputs["MaritalStatus"] = st.sidebar.selectbox("MaritalStatus", ["Single","Married","Divorced"])
+inputs["NumberOfTrips"] = i_num("NumberOfTrips", 3, 0, 50)
+inputs["Passport"] = st.sidebar.selectbox("Passport", [0,1])
+inputs["OwnCar"] = st.sidebar.selectbox("OwnCar", [0,1])
+inputs["NumberOfChildrenVisiting"] = i_num("NumberOfChildrenVisiting", 0, 0, 10)
+inputs["Designation"] = st.sidebar.selectbox("Designation", ["Executive","Manager","Senior Manager","AVP","VP","Director"])
+inputs["MonthlyIncome"] = i_num("MonthlyIncome", 70000, 0, 1_000_000, 1000)
+inputs["PitchSatisfactionScore"] = i_num("PitchSatisfactionScore", 4, 1, 5)
+inputs["ProductPitched"] = st.sidebar.selectbox("ProductPitched", ["Basic","Deluxe","Super Deluxe","King","Queen"])
+inputs["NumberOfFollowups"] = i_num("NumberOfFollowups", 2, 0, 20)
+inputs["DurationOfPitch"] = i_num("DurationOfPitch", 15, 0, 120)
+
+df_in = pd.DataFrame([inputs])
+for junk in ["Unnamed: 0", "index"]:
+    if junk in df_in.columns: df_in = df_in.drop(columns=[junk])
+
+feature_order = meta.get("feature_order")
+if feature_order: df_in = df_in[[c for c in feature_order if c in df_in.columns]]
+
+threshold = float(meta.get("threshold", 0.5))
+
+if st.button("Predict"):
+    try:
+        proba = float(model.predict_proba(df_in)[:, 1][0])
+        pred = int(proba >= threshold)
+        st.metric("Purchase Probability", f"{proba:.3f}")
+        st.write("Prediction:", "Will Purchase (1)" if pred else "Will Not Purchase (0)")
+        with st.expander("Input snapshot"): st.dataframe(df_in)
+    except Exception as e:
+        st.error(f"Prediction failed: {e}")

requirements.txt

@@ -0,0 +1,5 @@
+streamlit>=1.33
+pandas
+scikit-learn
+joblib
+huggingface_hub>=0.23

streamlit_app.py

@@ -0,0 +1,91 @@
+import os, json, joblib
+import pandas as pd
+import streamlit as st
+from huggingface_hub import hf_hub_download
+
+st.set_page_config(page_title="Wellness Package Predictor", page_icon="🏝️", layout="centered")
+st.title("🏝️ Wellness Tourism Package — Purchase Propensity")
+
+def get_secret(name: str, default=None):
+    try:
+        return st.secrets[name]
+    except Exception:
+        return os.getenv(name, default)
+
+# ---- Model location & token ----
+MODEL_REPO = get_secret("MODEL_REPO", "MBG0903/tourism_customer_xgb")
+HF_TOKEN   = get_secret("HF_TOKEN", None)  # only needed if the model repo is private
+
+@st.cache_resource(show_spinner=True)
+def load_artifacts(repo_id: str, token: str | None):
+    model_path = hf_hub_download(repo_id=repo_id, filename="model.joblib", token=token)
+    meta_path  = hf_hub_download(repo_id=repo_id, filename="metadata.json", token=token)
+    model = joblib.load(model_path)
+    with open(meta_path, "r") as f:
+        meta = json.load(f)
+    return model, meta
+
+try:
+    model, meta = load_artifacts(MODEL_REPO, HF_TOKEN)
+except Exception as e:
+    st.error(f"Failed to load model artifacts from {MODEL_REPO}. Details: {e}")
+    st.stop()
+
+st.caption("Model metrics (from training)")
+st.json(meta.get("metrics", {}))
+
+# ---- Inputs ----
+st.sidebar.header("Enter Customer Profile")
+
+def i_num(label, value, minv=None, maxv=None, step=1):
+    return st.sidebar.number_input(label, value=value, min_value=minv, max_value=maxv, step=step)
+
+inputs = {}
+inputs["CustomerID"] = st.sidebar.text_input("CustomerID", "CUST_000001")
+inputs["Age"] = i_num("Age", 32, 18, 90)
+inputs["TypeofContact"] = st.sidebar.selectbox("TypeofContact", ["Company Invited","Self Inquiry"])
+inputs["CityTier"] = st.sidebar.selectbox("CityTier", ["Tier 1","Tier 2","Tier 3"])
+inputs["Occupation"] = st.sidebar.selectbox("Occupation", ["Salaried","Freelancer","Self Employed","Student","Retired"])
+inputs["Gender"] = st.sidebar.selectbox("Gender", ["Male","Female"])
+inputs["NumberOfPersonVisiting"] = i_num("NumberOfPersonVisiting", 2, 1, 10)
+inputs["PreferredPropertyStar"] = i_num("PreferredPropertyStar", 4, 1, 5)
+inputs["MaritalStatus"] = st.sidebar.selectbox("MaritalStatus", ["Single","Married","Divorced"])
+inputs["NumberOfTrips"] = i_num("NumberOfTrips", 3, 0, 50)
+inputs["Passport"] = st.sidebar.selectbox("Passport", [0,1])
+inputs["OwnCar"] = st.sidebar.selectbox("OwnCar", [0,1])
+inputs["NumberOfChildrenVisiting"] = i_num("NumberOfChildrenVisiting", 0, 0, 10)
+inputs["Designation"] = st.sidebar.selectbox("Designation", ["Executive","Manager","Senior Manager","AVP","VP","Director"])
+inputs["MonthlyIncome"] = i_num("MonthlyIncome", 70000, 0, 1_000_000, 1000)
+inputs["PitchSatisfactionScore"] = i_num("PitchSatisfactionScore", 4, 1, 5)
+inputs["ProductPitched"] = st.sidebar.selectbox("ProductPitched", ["Basic","Deluxe","Super Deluxe","King","Queen"])
+inputs["NumberOfFollowups"] = i_num("NumberOfFollowups", 2, 0, 20)
+inputs["DurationOfPitch"] = i_num("DurationOfPitch", 15, 0, 120)
+
+df_in = pd.DataFrame([inputs])
+
+# Defensive cleanup (if any junk cols appear)
+for junk in ["Unnamed: 0", "index"]:
+    if junk in df_in.columns:
+        df_in = df_in.drop(columns=[junk])
+
+# Respect training feature order if provided
+feature_order = meta.get("feature_order")
+if feature_order:
+    missing = [c for c in feature_order if c not in df_in.columns]
+    if missing:
+        st.warning(f"Input missing expected columns: {missing}")
+    df_in = df_in[[c for c in feature_order if c in df_in.columns]]
+
+threshold = float(meta.get("threshold", 0.5))
+
+if st.button("Predict"):
+    try:
+        proba = float(model.predict_proba(df_in)[:, 1][0])
+        pred = int(proba >= threshold)
+        st.metric("Purchase Probability", f"{proba:.3f}")
+        st.write("Prediction:", "Will Purchase (1)" if pred == 1 else "Will Not Purchase (0)")
+        with st.expander("Input snapshot"):
+            st.dataframe(df_in)
+    except Exception as e:
+        st.error(f"Prediction failed: {e}")
+