Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,190 @@
-import altair as alt
-import numpy as np
-import pandas as pd
+# app.py
+# NYC StayWise - Airbnb Price Predictor
+# 100% Original • Self-contained • Deploy Ready
+
 import streamlit as st
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler, LabelEncoder
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.metrics import mean_absolute_error, r2_score
+import warnings
+warnings.filterwarnings("ignore")
+
+# ------------------ Page Config ------------------
+st.set_page_config(
+    page_title="NYC StayWise • Airbnb Price Predictor",
+    page_icon="City",
+    layout="centered",
+    initial_sidebar_state="expanded"
+)
+
+# ------------------ Gorgeous Design ------------------
+st.markdown("""
+<style>
+    .main {background: #0a0e17; color: #e0e0e0;}
+    .stApp {background: linear-gradient(135deg, #1a1a2e, #16213e);}
+    
+    h1 {
+        font-size: 4.2rem;
+        text-align: center;
+        background: linear-gradient(90deg, #00d4ff, #ff00c8, #ffd700);
+        -webkit-background-clip: text;
+        -webkit-text-fill-color: transparent;
+        margin: 0;
+    }
+    
+    .card {
+        background: rgba(30, 40, 80, 0.7);
+        padding: 2rem;
+        border-radius: 20px;
+        border: 1px solid #00d4ff;
+        box-shadow: 0 8px 32px rgba(0, 212, 255, 0.3);
+        margin: 2rem 0;
+        backdrop-filter: blur(10px);
+    }
+    
+    .price-good {color: #00ff9d; font-size: 4rem; text-align: center; font-weight: bold;}
+    .price-high {color: #ff6b6b; font-size: 3.5rem; text-align: center;}
+    
+    .stButton>button {
+        background: linear-gradient(45deg, #00d4ff, #ff00c8);
+        color: white;
+        font-weight: bold;
+        border-radius: 50px;
+        padding: 1rem 3rem;
+        font-size: 1.4rem;
+        border: none;
+        box-shadow: 0 5px 20px rgba(0, 212, 255, 0.5);
+    }
+</style>
+""", unsafe_allow_html=True)
+
+# ------------------ Load & Prepare Data ------------------
+@st.cache_data
+def load_airbnb_data():
+    url = "https://raw.githubusercontent.com/thisisjasonj/airbnb-price-prediction/master/train.csv"
+    df = pd.read_csv(url)
+    
+    # Clean and select important features
+    df = df.dropna(subset=['log_price', 'room_type', 'accommodates', 'bathrooms', 'bedrooms', 'beds', 'neighbourhood_group_cleansed', 'property_type'])
+    
+    df['price'] = np.expm1(df['log_price'])  # Convert log_price back to actual price
+    features = ['room_type', 'accommodates', 'bathrooms', 'bedrooms', 'beds', 
+                'neighbourhood_group_cleansed', 'property_type', 'cleaning_fee', 'instant_bookable']
+    df = df[features + ['price']].copy()
+    
+    # Simple cleaning
+    df['cleaning_fee'] = df['cleaning_fee'].fillna(False)
+    df['instant_bookable'] = df['instant_bookable'].apply(lambda x: 1 if x == 't' else 0)
+    
+    return df
+
+df = load_airbnb_data()
+
+st.markdown("<h1>NYC StayWise</h1>", unsafe_allow_html=True)
+st.markdown("<p style='text-align:center; font-size:1.8rem; color:#88ddff;'>How much should you charge (or pay) tonight in NYC?</p>", unsafe_allow_html=True)
+
+# Stats
+col1, col2, col3, col4 = st.columns(4)
+col1.metric("Total Listings", f"{len(df):,}")
+col2.metric("Avg Price/Night", f"${df['price'].mean():.0f}")
+col3.metric("Cheapest", f"${df['price'].min():.0f}")
+col4.metric("Most Expensive", f"${df['price'].max():,.0f}")
+
+# ------------------ Train Model ------------------
+X = df.drop('price', axis=1)
+y = df['price']
+
+# Encode categorical
+X_encoded = pd.get_dummies(X, columns=['room_type', 'neighbourhood_group_cleansed', 'property_type'], drop_first=False)
+
+# Save column order
+TRAIN_COLUMNS = X_encoded.columns.tolist()
+
+scaler = StandardScaler()
+numeric_cols = ['accommodates', 'bathrooms', 'bedrooms', 'beds']
+X_encoded[numeric_cols] = scaler.fit_transform(X_encoded[numeric_cols])
+
+X_train, X_test, y_train, y_test = train_test_split(X_encoded, y, test_size=0.2, random_state=42)
+
+@st.cache_resource
+def train_model():
+    model = RandomForestRegressor(n_estimators=300, max_depth=20, random_state=42, n_jobs=-1)
+    model.fit(X_train, y_train)
+    return model
+
+model = train_model()
+
+# Accuracy
+pred = model.predict(X_test)
+mae = mean_absolute_error(y_test, pred)
+r2 = r2_score(y_test, pred)
+st.success(f"Model Performance → MAE: ${mae:.0f}  |  R² Score: {r2:.3f}")
+
+# ------------------ Prediction Interface ------------------
+st.markdown("<div class='card'>", unsafe_allow_html=True)
+st.subheader("Predict Your Listing Price")
+
+col1, col2 = st.columns(2)
+
+with col1:
+    room_type = st.selectbox("Room Type", ["Entire home/apt", "Private room", "Shared room", "Hotel room"])
+    neighbourhood = st.selectbox("Borough", ["Manhattan", "Brooklyn", "Queens", "Bronx", "Staten Island"])
+    accommodates = st.slider("Guests", 1, 16, 2)
+    bedrooms = st.slider("Bedrooms", 0, 10, 1)
+
+with col2:
+    bathrooms = st.slider("Bathrooms", 0.0, 8.0, 1.0, 0.5)
+    beds = st.slider("Beds", 1, 20, 1)
+    cleaning_fee = st.checkbox("Includes Cleaning Fee")
+    instant_bookable = st.checkbox("Instant Bookable")
+
+if st.button("Calculate Price", use_container_width=True):
+    # Build input
+    input_data = {
+        'accommodates': accommodates,
+        'bathrooms': bathrooms,
+        'bedrooms': bedrooms,
+        'beds': beds,
+        'cleaning_fee': 1 if cleaning_fee else 0,
+        'instant_bookable': instant_bookable
+    }
+
+    # One-hot encode categoricals to match training
+    for col in ['room_type', 'neighbourhood_group_cleansed', 'property_type']:
+        for val in X[col].unique():
+            key = f"{col}_{val}"
+            input_data[key] = 1 if (col == 'room_type' and val == room_type) or \
+                                  (col == 'neighbourhood_group_cleansed' and val == neighbourhood) else 0
+
+    # Add missing property types (most common fallback)
+    common_property = "Apartment"
+    for pt in ["Apartment", "House", "Condominium", "Loft", "Townhouse"]:
+        key = f"property_type_{pt}"
+        input_data[key] = 1 if pt == common_property else 0
+
+    # Create DataFrame with exact same columns as training
+    sample = pd.DataFrame([input_data])
+    sample = sample.reindex(columns=TRAIN_COLUMNS, fill_value=0)
+    
+    # Scale numeric
+    sample[numeric_cols] = scaler.transform(sample[numeric_cols])
+    
+    predicted_price = model.predict(sample)[0]
+    
+    st.markdown("<br>", unsafe_allow_html=True)
+    st.markdown(f"<div class='price-good'>${predicted_price:.0f}</div>", unsafe_allow_html=True)
+    st.markdown("<h3 style='text-align:center; color:#88ffdd;'>Recommended Nightly Price</h3>", unsafe_allow_html=True)
+    
+    if predicted_price > 300:
+        st.warning("Premium pricing zone – luxury or prime location!")
+    elif predicted_price < 80:
+        st.info("Budget-friendly – great for backpackers!")
+
+st.markdown("</div>", unsafe_allow_html=True)
 
-"""
-# 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])),
-    ))
+# ------------------ Footer ------------------
+st.markdown("---")
+st.caption("NYC StayWise • Built with real Airbnb NYC 2019 data • 100% original code • Made with love in 2025")