Restructure to use src/ folder and Docker with hotel booking prediction

.gitignore

@@ -1 +1,4 @@
 .env
+*.pkl
+__pycache__/
+*.pyc

Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.11-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", "--server.enableXsrfProtection=false"]

README.md

@@ -1,14 +1,23 @@
 ---
-title: Simple Input Output App
-emoji: 🚀
+title: Hotel Booking Prediction
+emoji: 🏨
 colorFrom: blue
 colorTo: green
-sdk: streamlit
-sdk_version: 1.28.0
-app_file: app.py
+sdk: docker
+app_port: 8501
+tags:
+  - streamlit
+  - machine-learning
+  - hotel-booking
 pinned: false
+short_description: 'Predict hotel booking cancellation using ML'
 ---
 
-# Simple Input/Output Streamlit App
+# Hotel Booking Prediction
 
-A simple Streamlit application that takes text input and displays output with character and word count.
+A Streamlit application that predicts hotel booking cancellations using machine learning.
+
+## Features
+- Predict booking cancellation probability
+- Interactive form interface
+- Real-time predictions

app.py

@@ -1,11 +0,0 @@
-import streamlit as st
-
-st.title("Simple Input/Output App")
-
-user_input = st.text_input("Enter your text:", placeholder="Type something here...")
-
-if user_input:
-    st.write("### Output:")
-    st.write(f"You entered: **{user_input}**")
-    st.write(f"Character count: {len(user_input)}")
-    st.write(f"Word count: {len(user_input.split())}")

requirements.txt

@@ -1 +1,6 @@
 streamlit
+pandas
+numpy
+scikit-learn
+gdown
+pickle5

ziko.py → src/streamlit_app.py

@@ -1,6 +1,6 @@
 import pandas as pd
 import pickle
-import numpy as py
+import numpy as np
 import streamlit as st
 import gdown
 
@@ -28,11 +28,38 @@ def load_top_country():
 
 model = load_model()
 top_country = load_top_country()
-# Load
 
+st.set_page_config(page_title="Hotel Booking Prediction", layout="wide")
 
-def run():
-    with st.form(key="hotel_bookings"):
+st.markdown("""
+<div style="
+    background-color: white;
+    padding: 50px;
+    border-radius: 20px;
+    box-shadow: 0 4px 20px rgba(0,0,0,0.1);
+    max-width: 800px;
+    margin: auto;
+    text-align: center;
+">
+    <h1 style="font-size:60px; font-weight:bold; color:black; margin-bottom:20px;">
+        Hotel Booking Prediction
+    </h1>
+    <p style="font-size:20px; color:gray; margin-bottom:30px;">
+        Welcome to Hotel Booking Prediction System
+    </p>
+    <p style="font-size:15px; color:black;">
+        Fill in the form below to predict hotel booking!
+    </p>
+</div>
+""", unsafe_allow_html=True)
+
+st.write("")
+st.write("")
+
+with st.form(key="hotel_bookings"):
+    col1, col2 = st.columns(2)
+    
+    with col1:
         name = st.selectbox("Hotel Type", ("city_hotel", "resort_hotel"), index=0)
         lead = st.number_input(
             "Lead Time",
@@ -61,6 +88,8 @@ def run():
             ),
             index=0,
         )
+    
+    with col2:
         arrival_week = st.number_input(
             "Arrival Weeks",
             min_value=1,
@@ -78,8 +107,30 @@ def run():
             help="tanggal kedatangan",
         )
 
-        submitted = st.form_submit_button("Predict")
-
-
-if __name__ == "_main_":
-    run()
+    submitted = st.form_submit_button("Predict", use_container_width=True)
+    
+    if submitted:
+        # Prepare data for prediction
+        data = {
+            'hotel': name,
+            'lead_time': lead,
+            'arrival_date_year': int(arrival_year),
+            'arrival_date_month': arrival_month,
+            'arrival_date_week_number': arrival_week,
+            'arrival_date_day_of_month': arrival_day
+        }
+        
+        df = pd.DataFrame([data])
+        
+        try:
+            prediction = model.predict(df)
+            
+            st.success("Prediction Complete!")
+            
+            if prediction[0] == 1:
+                st.error("⚠️ This booking is likely to be CANCELLED")
+            else:
+                st.success("✅ This booking is likely to be CONFIRMED")
+                
+        except Exception as e:
+            st.error(f"Error making prediction: {str(e)}")