Upload reg.py

pages/reg.py

@@ -0,0 +1,34 @@
+import streamlit as st
+from streamlit import session_state
+import joblib
+from io import StringIO
+import json
+import os
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+
+def find_optimal_price(data, model, buying_price):
+    start_price = data.PRICE.min() - 1              # start price
+    end_price = data.PRICE.min() + 10               # end price
+    test = pd.DataFrame(columns = ["PRICE", "QUANTITY"])  # choose required columns
+    test['PRICE'] = np.arange(start_price, end_price,0.01)
+    test['QUANTITY'] = model.predict(test['PRICE'])         # make predictions
+    test['PROFIT'] = (test["PRICE"] - buying_price) * test["QUANTITY"]
+    plt.plot(test['PRICE'],test['QUANTITY'])       # plot the results 
+    plt.plot(test['PRICE'],test['PROFIT']) 
+    plt.show()
+    ind = np.where(test['PROFIT'] == test['PROFIT'].max())[0][0]
+    values_at_max_profit = test.iloc[[ind]]
+    return values_at_max_profit
+model = joblib.load("burger_model.sav")
+uploaded_file = st.file_uploader("Choose a file")
+if uploaded_file:
+    # Read data from file
+    df = pd.read_csv(uploaded_file)
+    
+    # Clean data
+    df = df[df['PRICE'].notna()].reset_index(drop=True)
+    buying_price = st.slider("Select buying price", min_value=9, max_value=15, value=1, step=1)
+    result = find_optimal_price(df,model,buying_price)
+    st.text_area("PRICE Should be to achive maximum profit", value=list(result.to_dict()['PRICE'].values())[0])