Update app.py

app.py

@@ -1,6 +1,5 @@
 import pandas as pd
 import streamlit as st
-import numpy as np
 import pickle
 from sklearn.preprocessing import MinMaxScaler
 
@@ -12,6 +11,7 @@ with open('model_and_scaler.pkl', 'rb') as file:
 scaler = model_and_scaler['scaler']
 rf_model = model_and_scaler['model']
 
+# Define app title and description
 st.image("https://pbs.twimg.com/media/DywhyJiXgAIUZej?format=jpg&name=medium")
 st.title("Store Sales Prediction App")
 st.caption("This app predicts sales patterns in different stores based on the inputs.")
@@ -27,7 +27,7 @@ st.sidebar.markdown("**Day**: Day the product was purchased.")
 st.sidebar.markdown("**Month**: Month the product was purchased.")
 st.sidebar.markdown("**Year**: Year the product was purchased.")
 
- # Create the input fields
+# Create the input fields
 input_data = {}
 col1, col2 = st.columns(2)
 with col1:
@@ -38,8 +38,8 @@ with col1:
 
 with col2:
     input_data['day'] = st.slider("Day", 1, 31)
-    input_data['month'] = st.slider("Month", 1, 12)
-    input_data['year'] = st.number_input("Year", 2018, 2020)
+    input_data['month'] = st.slider("Month", 1, 12, value=6)
+    input_data['year'] = st.number_input("Year", 2018, 2020, value=2020)
 
 # Create a button to make a prediction
 if st.button("Predict"):
@@ -50,13 +50,6 @@ if st.button("Predict"):
     input_df_scaled = scaler.fit_transform(input_df[numerical_cols])
     input_df_scaled = pd.DataFrame(input_df_scaled, columns=numerical_cols)
     
-    # Load the scaler and model
-    with open('model_and_scaler.pkl', 'rb') as file:
-        model_and_scaler = pickle.load(file)
-    
-    # Extract the model
-    rf_model = model_and_scaler['model']
-    
     # Make predictions using the trained model
     predictions = rf_model.predict(input_df_scaled)