Update app.py

app.py

@@ -1,11 +1,11 @@
+```python
 import streamlit as st
 import pandas as pd
 from prophet import Prophet
 from datetime import datetime, timedelta
-import numpy as np
 
 # Prepare data for Prophet
-def prepare_prophet_data(usage_series):
+def prepare_data(usage_series):
     end_date = datetime.now()
     start_date = end_date - timedelta(days=len(usage_series) - 1)
     dates = [start_date + timedelta(days=i) for i in range(len(usage_series))]
@@ -13,28 +13,28 @@ def prepare_prophet_data(usage_series):
         'ds': dates,
         'y': usage_series
     })
-    prophet_df['cap'] = 60  # Max observed usage
+    prophet_df['cap'] = 30  # Lowered from 60 to 30
     prophet_df['floor'] = 0
     return prophet_df
 
-# Train or update Prophet model with user-provided usage series
-def train_model_with_usage(usage_series):
-    print("Training with changepoint_prior_scale=0.002, usage:", usage_series)  # Debug
-    prophet_df = prepare_prophet_data(usage_series)
+# Train or update Prophet model
+def train_model(usage_series):
+    print("Training with changepoint=0.001, usage:", usage_series)  # Debug
+    prophet_data = prepare_data(usage_series)
     model = Prophet(
         yearly_seasonality=False,
         weekly_seasonality=True,
         daily_seasonality=True,
-        changepoint_prior_scale=0.002,
+        changepoint_prior_scale=0.001,  # Lowered from 0.002
         growth='logistic'
     )
-    model.fit(prophet_df)
+    model.fit(prophet_data)
     return model
 
 # Function to make forecasts
 def make_forecast(model, periods):
     future = model.make_future_dataframe(periods=periods)
-    future['cap'] = 60
+    future['cap'] = 30
     future['floor'] = 0
     forecast = model.predict(future)
     daily_forecasts = forecast['yhat'].tail(periods).tolist()
@@ -42,7 +42,7 @@ def make_forecast(model, periods):
     return round(sum(max(0, y) for y in daily_forecasts))  # Clip negative values
 
 # Function to validate input
-def validate_usage_series(usage_str):
+def validate_usage(usage_str):
     try:
         usage_list = [float(x) for x in usage_str.split(',')]
         if len(usage_list) != 60:
@@ -66,14 +66,14 @@ def main():
     current_stock = st.number_input("Current Stock", min_value=0, value=0)
     
     if st.button("Generate Forecast"):
-        usage_list, error = validate_usage_series(usage_series)
+        usage_list, error = validate_usage(usage_series)
         if error:
             st.error(error)
             return
         st.write("Debug: Input usage series:", usage_list)  # Debug
         
         try:
-            model = train_model_with_usage(usage_list)
+            model = train_model(usage_list)
         except Exception as e:
             st.error(f"Error training model: {str(e)}")
             return
@@ -111,4 +111,5 @@ def main():
         st.write(f"**For 30 Days**: Order {order_30} additional units.")
 
 if __name__ == "__main__":
-    main()
+    main()
+```