Update app.py

app.py

@@ -5,33 +5,25 @@ import requests
 import os
 import datetime
 import tempfile
-import numpy as np  # Added for smoothing historical prices
+import numpy as np
 
-# Your Hugging Face API Token (set this safely)
+# Your Hugging Face API Token
 HF_TOKEN = os.getenv("HUGGINGFACE_TOKEN")
 
-# Mistral Inference API URL
 API_URL = "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.3"
 
-# Headers for authentication
 headers = {
     "Authorization": f"Bearer {HF_TOKEN}"
 }
 
-# Function to query Mistral API
 def query_mistral(question):
-    payload = {
-        "inputs": question,
-        "parameters": {"max_length": 256}
-    }
+    payload = {"inputs": question, "parameters": {"max_length": 256}}
     response = requests.post(API_URL, headers=headers, json=payload)
     output = response.json()
     return output[0]["generated_text"]
 
-# API Key
 POLYGON_API_KEY = os.getenv("POLYGON_API_KEY")
 
-# Sector Averages
 sector_averages = {
     "Technology": {"P/E Ratio": 25, "P/S Ratio": 5, "P/B Ratio": 6},
     "Healthcare": {"P/E Ratio": 20, "P/S Ratio": 4, "P/B Ratio": 3},
@@ -39,8 +31,6 @@ sector_averages = {
     "Energy": {"P/E Ratio": 12, "P/S Ratio": 1.2, "P/B Ratio": 1.3},
 }
 
-
-# Safe Request Function
 def safe_request(url):
     try:
         response = requests.get(url)
@@ -49,21 +39,16 @@ def safe_request(url):
     except:
         return None
 
-# Fetch Functions
-
-
-# Financial Calculations
 def calculate_ratios(market_cap, total_revenue, price, dividend_amount, eps=5.0, growth=0.1, book_value=500000000):
     pe = price / eps if eps else 0
     ps = market_cap / total_revenue if total_revenue else 0
     pb = market_cap / book_value if book_value else 0
     peg = pe / (growth * 100) if growth else 0
     div_yield = (dividend_amount / price) * 100 if price else 0
-    # New Financial Health Metrics
-    debt_equity = np.random.uniform(0.2, 2.0)  # Placeholder: random for now
-    roe = np.random.uniform(5, 25)  # Placeholder: random for now
-    free_cash_flow = np.random.uniform(50000000, 500000000)  # Placeholder: random for now
-    beta = np.random.uniform(0.8, 1.5)  # Placeholder: random for now
+    debt_equity = np.random.uniform(0.2, 2.0)
+    roe = np.random.uniform(5, 25)
+    free_cash_flow = np.random.uniform(50000000, 500000000)
+    beta = np.random.uniform(0.8, 1.5)
     return {
         'P/E Ratio': pe,
         'P/S Ratio': ps,
@@ -100,15 +85,12 @@ def stock_research(symbol, eps=5.0, growth=0.1, book=500000000):
     ratios_table = pd.DataFrame(ratios.items(), columns=["Metric", "Value"])
     financial_health = ratios_table[ratios_table["Metric"].isin(["Debt/Equity Ratio", "Return on Equity (%)", "Free Cash Flow ($)", "Beta (Volatility)"])]
 
-    # New Recommendation Section
     recommendation = "Hold"
     if ratios['P/E Ratio'] < 15 and ratios['Debt/Equity Ratio'] < 1.0 and ratios['Return on Equity (%)'] > 10 and ratios['Beta (Volatility)'] < 1.2:
         recommendation = "Buy"
     elif ratios['P/E Ratio'] > 30 or ratios['Debt/Equity Ratio'] > 2.0 or ratios['Return on Equity (%)'] < 5:
         recommendation = "Sell"
 
-        # Detailed report for summarization
-        # Build a full report
     report = (
         f"Company Overview:\n"
         f"Name: {info['Name']}\n"
@@ -126,18 +108,15 @@ def stock_research(symbol, eps=5.0, growth=0.1, book=500000000):
         f"Free Cash Flow: ${ratios['Free Cash Flow ($)']:,.2f}\n"
         f"Beta (Volatility): {ratios['Beta (Volatility)']}\n"
     )
-    
-    # Summarize using Mistral
+
     summary_prompt = f"Summarize this financial report clearly and briefly:\n\n{report}"
     ai_summary = query_mistral(summary_prompt)
-    
-    # Add recommendation into financial health table
+
     financial_health = pd.concat([
         financial_health,
-        pd.DataFrame([{\"Metric\": \"Recommendation\", \"Value\": recommendation}])
+        pd.DataFrame([{"Metric": "Recommendation", "Value": recommendation}])
     ], ignore_index=True)
-    
-    # Return everything
+
     return ai_summary, info_table, ratios_table, financial_health, sector_comp, fig