Upload Deployment

.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
+src/hotel_bookings.csv filter=lfs diff=lfs merge=lfs -text

src/best_model_rf_clean.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7077b3c1db0a8338a4cd7b9736c88cfa2aacac4fb9209db9b8cde0c16de776dc
+size 224368818

src/hotel_bookings.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2ae42a7353905ea136e5c2287f17c92c5435826598bfbb8491c6f0c7b1fc06
+size 16855599

src/prediction.py

@@ -0,0 +1,23 @@
+import pandas as pd
+
+def predict(data, model, prep):
+    df = pd.DataFrame([data])
+
+    # Handle country
+    top_country = ['PRT', 'GBR', 'FRA', 'ESP', 'DEU', 'ITA', 'IRL', 'BEL', 'BRA', 'NLD']
+    df['country'] = df['country'].apply(lambda x: x if x in top_country else 'Other')
+
+    # Fix missing columns
+    if 'agent' not in df.columns:
+        df['agent'] = 0
+
+    if 'company' not in df.columns:
+        df['company'] = 0
+
+    # Transform
+    df_processed = prep.transform(df)
+
+    # Predict
+    result = model.predict(df_processed)
+
+    return result[0]

src/preprocessor.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4176c338877593df7ae282fe0f0d14d5bd9a30b4b7d8b5294f9143f8d3f0aec2
+size 8806

src/rf_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a49baba7cadec2ed9f6582887771b89fd05f082febc8f7b5d1c1211c4468522
+size 224350553

src/streamlit_app.py

@@ -1,40 +1,136 @@
-import altair as alt
-import numpy as np
-import pandas as pd
-import streamlit as st
-
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+import streamlit as st
+import joblib
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+from prediction import predict
+
+# ================================
+# Load model & preprocessor
+# ================================
+model = joblib.load('rf_model.pkl')
+prep = joblib.load('preprocessor.pkl')
+
+# ================================
+# Sidebar Navigation
+# ================================
+st.sidebar.title("Navigation")
+page = st.sidebar.selectbox("Choose Page", ["Prediction", "EDA"])
+
+st.sidebar.markdown("### Created by Fernando Brian")
+st.sidebar.markdown("### Deployed on Hugging Face")
+
+# ================================
+# 📊 PAGE 1: PREDICTION
+# ================================
+if page == "Prediction":
+
+    st.title("Hotel Booking Cancellation Prediction")
+
+    st.write("Masukkan data booking untuk memprediksi kemungkinan pembatalan.")
+
+    # ================================
+    # Input User
+    # ================================
+    lead_time = st.slider("Lead Time", 0, 365, 50)
+    hotel = st.selectbox("Hotel Type", ["City Hotel", "Resort Hotel"])
+    deposit_type = st.selectbox("Deposit Type", ["No Deposit", "Non Refund", "Refundable"])
+    market_segment = st.selectbox("Market Segment", ["Online TA", "Offline TA/TO", "Direct", "Corporate"])
+    country = st.text_input("Country (contoh: PRT, GBR)", "PRT")
+
+    # ================================
+    # Prediction Button
+    # ================================
+    if st.button("Predict"):
+
+        data = {
+            'hotel': hotel,
+            'lead_time': lead_time,
+            'arrival_date_year': 2017,
+            'arrival_date_month': 'July',
+            'arrival_date_week_number': 27,
+            'arrival_date_day_of_month': 1,
+            'stays_in_weekend_nights': 1,
+            'stays_in_week_nights': 2,
+            'adults': 2,
+            'children': 0,
+            'babies': 0,
+            'meal': 'BB',
+            'country': country,
+            'market_segment': market_segment,
+            'distribution_channel': 'TA/TO',
+            'is_repeated_guest': 0,
+            'previous_cancellations': 0,
+            'previous_bookings_not_canceled': 0,
+            'reserved_room_type': 'A',
+            'assigned_room_type': 'A',
+            'booking_changes': 0,
+            'deposit_type': deposit_type,
+            'days_in_waiting_list': 0,
+            'customer_type': 'Transient',
+            'adr': 100.0,
+            'required_car_parking_spaces': 0,
+            'total_of_special_requests': 1,
+            'agent': 0,
+            'company': 0
+        }
+
+        # Predict
+        result = predict(data, model, prep)
+
+        # Output
+        if result == 1:
+            st.error("❌ Booking kemungkinan akan dibatalkan")
+        else:
+            st.success("✅ Booking kemungkinan tidak dibatalkan")
+
+# ================================
+# 📈 PAGE 2: EDA
+# ================================
+elif page == "EDA":
+
+    st.title("Exploratory Data Analysis")
+
+    # Load dataset
+    df = pd.read_csv("hotel_bookings.csv")
+
+    # ================================
+    # Dataset Preview
+    # ================================
+    st.subheader("Dataset Preview")
+    st.dataframe(df.head())
+
+    # ================================
+    # Plot 1 - Cancellation Distribution
+    # ================================
+    st.subheader("Distribusi Pembatalan")
+
+    fig, ax = plt.subplots()
+    sns.countplot(x='is_canceled', data=df, ax=ax)
+    ax.set_title("Cancellation Distribution")
+    st.pyplot(fig)
+
+    # ================================
+    # Plot 2 - Lead Time vs Cancellation
+    # ================================
+    st.subheader("Lead Time vs Cancellation")
+
+    fig, ax = plt.subplots()
+    sns.boxplot(x='is_canceled', y='lead_time', data=df, ax=ax)
+    ax.set_title("Lead Time vs Cancellation")
+    st.pyplot(fig)
+
+    # ================================
+    # Plot 3 - Market Segment Distribution
+    # ================================
+    st.subheader("Market Segment Distribution")
+
+    fig, ax = plt.subplots()
+    sns.countplot(
+        y='market_segment',
+        data=df,
+        order=df['market_segment'].value_counts().index,
+        ax=ax
+    )
+    ax.set_title("Market Segment Distribution")
+    st.pyplot(fig)