Update app.py

app.py

@@ -1,21 +1,10 @@
 import streamlit as st
 import pandas as pd
-import pickle
 from prophet import Prophet
 from datetime import datetime, timedelta
 import numpy as np
 import plotly.graph_objects as go
 
-# Load the trained models (optional, for initialization or fallback)
-@st.cache_resource
-def load_model():
-    try:
-        with open('model.pkl', 'rb') as f:
-            models = pickle.load(f)
-        return models
-    except FileNotFoundError:
-        return None
-
 # Prepare data for Prophet
 def prepare_prophet_data(usage_series):
     end_date = datetime.now()
@@ -28,15 +17,24 @@ def prepare_prophet_data(usage_series):
     })
     return prophet_df
 
-# Train or update Prophet model with reduced sensitivity
-def train_model_with_usage(usage_series):
+# Train model with sensitivity option
+def train_model_with_usage(usage_series, sensitivity):
     prophet_df = prepare_prophet_data(usage_series)
+    
+    # Set changepoint_prior_scale based on selected sensitivity
+    if sensitivity == "Low":
+        cps = 0.01
+    elif sensitivity == "Medium":
+        cps = 0.1
+    else:  # High
+        cps = 0.5
+    
     model = Prophet(
         yearly_seasonality=False,
         weekly_seasonality=True,
         daily_seasonality=True,
-        changepoint_prior_scale=0.01,   # 👈 Reduced sensitivity to recent changes
-        changepoint_range=0.6           # 👈 Only look at early 60% of data for trend changes
+        changepoint_prior_scale=cps,
+        changepoint_range=0.6
     )
     model.fit(prophet_df)
     return model
@@ -45,7 +43,7 @@ def train_model_with_usage(usage_series):
 def make_forecast(model, periods):
     future = model.make_future_dataframe(periods=periods)
     forecast = model.predict(future)
-    return round(forecast['yhat'].tail(periods).sum())
+    return forecast, round(forecast['yhat'].tail(periods).sum())
 
 # Function to validate input
 def validate_usage_series(usage_str):
@@ -62,99 +60,81 @@ def validate_usage_series(usage_str):
 # Main Streamlit app
 def main():
     st.title("SmartLab Consumables Forecast")
-    
-    models = load_model()
-    
+
     st.header("Input Parameters")
     consumable_type = st.selectbox("Consumable Type", ['Filters', 'Reagents', 'Vials'])
     usage_series = st.text_input("Last 60 Days Usage (comma-separated)", "")
     current_stock = st.number_input("Current Stock", min_value=0, value=0)
-    
+    sensitivity = st.selectbox("Forecast Sensitivity", ['Low', 'Medium', 'High'])
+
     if st.button("Generate Forecast"):
         usage_list, error = validate_usage_series(usage_series)
         if error:
             st.error(error)
             return
-        
+
         try:
-            model = train_model_with_usage(usage_list)
+            model = train_model_with_usage(usage_list, sensitivity)
         except Exception as e:
             st.error(f"Error training model: {str(e)}")
             return
-        
-        forecast_7 = make_forecast(model, 7)
-        forecast_14 = make_forecast(model, 14)
-        forecast_30 = make_forecast(model, 30)
-        
+
+        forecast_df, forecast_7 = make_forecast(model, 7)
+        _, forecast_14 = make_forecast(model, 14)
+        _, forecast_30 = make_forecast(model, 30)
+
         st.header("Forecast Results")
         st.write(f"**7-Day Forecast**: {forecast_7} units")
         st.write(f"**14-Day Forecast**: {forecast_14} units")
         st.write(f"**30-Day Forecast**: {forecast_30} units")
-        
+
         st.header("Threshold Alerts")
         if current_stock < forecast_7:
-            st.warning(f"Alert: Current stock ({current_stock}) is below 7-day forecast ({forecast_7}). 🚩")
+            st.warning(f"⚠️ Stock ({current_stock}) is below 7-day forecast ({forecast_7})")
         if current_stock < forecast_14:
-            st.warning(f"Alert: Current stock ({current_stock}) is below 14-day forecast ({forecast_14}). 🚩")
+            st.warning(f"⚠️ Stock ({current_stock}) is below 14-day forecast ({forecast_14})")
         if current_stock < forecast_30:
-            st.warning(f"Alert: Current stock ({current_stock}) is below 30-day forecast ({forecast_30}). 🚩")
-        
+            st.warning(f"⚠️ Stock ({current_stock}) is below 30-day forecast ({forecast_30})")
+
         st.header("Order Suggestions")
-        order_7 = max(0, forecast_7 - current_stock)
-        order_14 = max(0, forecast_14 - current_stock)
-        order_30 = max(0, forecast_30 - current_stock)
-        st.write(f"**For 7 Days**: Order {order_7} additional units.")
-        st.write(f"**For 14 Days**: Order {order_14} additional units.")
-        st.write(f"**For 30 Days**: Order {order_30} additional units.")
-        
-        st.header("Forecast Visualization")
-        forecast_data = pd.DataFrame({
-            'Period': ['7 Days', '14 Days', '30 Days'],
-            'Units': [forecast_7, forecast_14, forecast_30]
-        })
-        fig_forecast = go.Figure()
-        fig_forecast.add_trace(go.Scatter(
-            x=forecast_data['Period'],
-            y=forecast_data['Units'],
-            mode='lines+markers',
-            name='Forecasted Units',
-            line=dict(color='blue'),
-            marker=dict(size=10)
+        st.write(f"🛒 **Order for 7 Days**: {max(0, forecast_7 - current_stock)} units")
+        st.write(f"🛒 **Order for 14 Days**: {max(0, forecast_14 - current_stock)} units")
+        st.write(f"🛒 **Order for 30 Days**: {max(0, forecast_30 - current_stock)} units")
+
+        # Forecast Trend Visualization
+        st.header("Forecast Curve")
+        fig_curve = go.Figure()
+        fig_curve.add_trace(go.Scatter(
+            x=forecast_df['ds'],
+            y=forecast_df['yhat'],
+            mode='lines',
+            name='Forecasted Usage',
+            line=dict(color='royalblue')
         ))
-        fig_forecast.update_layout(
-            title='Consumable Usage Forecast',
-            xaxis_title='Time Period',
-            yaxis_title='Units',
+        fig_curve.update_layout(
+            title='Forecast Trend (yhat)',
+            xaxis_title='Date',
+            yaxis_title='Predicted Usage',
             template='plotly_white'
         )
-        st.plotly_chart(fig_forecast)
-        
-        st.header("Threshold Alerts Visualization")
-        alert_data = pd.DataFrame({
-            'Category': ['Current Stock', '7-Day Forecast', '14-Day Forecast', '30-Day Forecast'],
-            'Units': [current_stock, forecast_7, forecast_14, forecast_30],
-            'Alert': [
-                False,
-                current_stock < forecast_7,
-                current_stock < forecast_14,
-                current_stock < forecast_30
-            ]
+        st.plotly_chart(fig_curve)
+
+        # Summary Bar Chart
+        st.header("Forecast Summary")
+        bar_data = pd.DataFrame({
+            'Period': ['7 Days', '14 Days', '30 Days'],
+            'Forecast Units': [forecast_7, forecast_14, forecast_30]
         })
-        fig_alerts = go.Figure()
-        fig_alerts.add_trace(go.Bar(
-            x=alert_data['Category'],
-            y=alert_data['Units'],
-            marker_color=['green'] + ['red' if alert else 'blue' for alert in alert_data['Alert'][1:]],
-            text=[f"🚩" if alert else "" for alert in alert_data['Alert']],
-            textposition='auto'
-        ))
-        fig_alerts.update_layout(
-            title='Stock vs Forecast with Alerts (🚩 indicates low stock)',
-            xaxis_title='Category',
-            yaxis_title='Units',
+        fig_bar = go.Figure(data=[
+            go.Bar(x=bar_data['Period'], y=bar_data['Forecast Units'], marker_color='blue')
+        ])
+        fig_bar.update_layout(
+            title="Forecast Summary",
+            xaxis_title="Forecast Period",
+            yaxis_title="Units",
             template='plotly_white'
         )
-        st.plotly_chart(fig_alerts)
+        st.plotly_chart(fig_bar)
 
 if __name__ == "__main__":
     main()