Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,112 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import pandas as pd
+import numpy as np
+import joblib
+import holidays
+import xgboost as xgb
+from datetime import date
+
+# Load the model
+@st.cache_resource
+def load_artifacts():
+    model = joblib.load('src/xgb_model.joblib')
+    encoders = joblib.load('src/encoders.joblib')
+    return model, encoders
+
+try:
+    model, encoders = load_artifacts()
+except FileNotFoundError:
+    st.error("Model files not found. Please upload 'xgb_model.joblib' and 'encoders.joblib'.")
+    st.stop()
+
+# Feature Engineering 
+def create_features(df):
+    df = df.copy()
+    df['date'] = pd.to_datetime(df['date'])
+    df['year'] = df['date'].dt.year
+    df['month'] = df['date'].dt.month
+    df['day'] = df['date'].dt.day
+    df['day_of_week'] = df['date'].dt.dayofweek
+    df['day_of_year'] = df['date'].dt.dayofyear
+    df['week_of_year'] = df['date'].dt.isocalendar().week.astype(int)
+    df['is_weekend'] = (df['day_of_week'] >= 5).astype(int)
+    
+    # Cyclical Encoding
+    df['day_sin'] = np.sin(2 * np.pi * df['day_of_year'] / 365.0)
+    df['day_cos'] = np.cos(2 * np.pi * df['day_of_year'] / 365.0)
+    df['month_sin'] = np.sin(2 * np.pi * df['month'] / 12.0)
+    df['month_cos'] = np.cos(2 * np.pi * df['month'] / 12.0)
+    
+    return df
+
+def add_holiday_features(df, encoders):
+    df = df.copy()
+    # Inverse transform to get country names for holiday library
+    df['country_name'] = encoders['country'].inverse_transform(df['country'])
+    years = df['date'].dt.year.unique()
+    country_codes = {'Canada': 'CA','Finland': 'FI','Italy': 'IT','Kenya': 'KE','Norway': 'NO','Singapore': 'SG'}
+    
+    df['is_holiday'] = 0
+    
+    for country_name, code in country_codes.items():
+        try:
+            country_holidays = holidays.Country(code, years=years)
+            mask = (df['country_name'] == country_name) & (df['date'].isin(country_holidays))
+            df.loc[mask, 'is_holiday'] = 1
+        except:
+            continue
+    df = df.drop(columns=['country_name'])
+    return df
+
+# UI
+st.title("🛒 Sticker Sales Prediction")
+st.write("Enter the details below to predict the number of items sold.")
+
+# Input
+col1, col2 = st.columns(2)
+
+with col1:
+    country_options = list(encoders['country'].classes_)
+    store_options = list(encoders['store'].classes_)
+    product_options = list(encoders['product'].classes_)
+    
+    selected_date = st.date_input("Select Date", value=date(2025, 1, 1))
+    selected_country = st.selectbox("Select Country", country_options)
+
+with col2:
+    selected_store = st.selectbox("Select Store", store_options)
+    selected_product = st.selectbox("Select Product", product_options)
 
-"""
-# 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])),
-    ))
+# 4. Prediction Button
+if st.button("Predict Sales"):
+    input_data = pd.DataFrame({
+        'date': [pd.to_datetime(selected_date)],
+        'country': [selected_country],
+        'store': [selected_store],
+        'product': [selected_product]})
+    
+    processed_data = create_features(input_data)
+    categorical_cols = ['country', 'store', 'product']
+    for col in categorical_cols:
+        processed_data[col] = encoders[col].transform(processed_data[col])
+    processed_data = add_holiday_features(processed_data, encoders)
+    
+    features = ['country', 'store', 'product', 'year', 'month', 'day', 'day_of_week', 'day_of_year', 'is_weekend', 
+                'day_sin', 'day_cos', 'month_sin', 'month_cos', 'is_holiday']
+    
+    X_input = processed_data[features]
+    
+    # Prediction
+    try:
+        pred_log = model.predict(X_input)
+        
+        final_prediction = np.expm1(pred_log)[0]
+        final_prediction = max(0, final_prediction) # Ensure no negative sales
+        
+        st.success(f"Predicted Num Sold: **{final_prediction:.2f}**")
+        
+        with st.expander("See processed features"):
+            st.dataframe(X_input)
+            
+    except Exception as e:
+        st.error(f"An error occurred during prediction: {e}")