Spaces:

rajat5ranjan
/

StockMarketInsights

Runtime error

App Files Files Community

rajat5ranjan commited on Jul 16

Commit

1f5a9cd

verified ·

1 Parent(s): bb7fddb

Update app.py

Browse files

Files changed (1) hide show

app.py +340 -318

app.py CHANGED Viewed

@@ -39,345 +39,367 @@ gemini_embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
 llm = ChatGoogleGenerativeAI(model="gemini-2.5-pro",google_api_key = GOOGLE_API_KEY)
 #llm_vis = ChatGoogleGenerativeAI(model="gemini-pro-vision",google_api_key = GOOGLE_API_KEY)
-def get_tradingview_analysis(symbol, exchange, screener, interval):
-    try:
-        stock = TA_Handler(
-            symbol=symbol,
-            screener=screener,
-            exchange=exchange,
-            interval=interval,
-        )
-        analysis_summary = stock.get_analysis()
-        return analysis_summary
-    except Exception as e:
-        return {"error": str(e)}
-if ticker_user!="":
-    url1 = f"https://www.google.com/finance/quote/{ticker_user}:NSE?hl=en"
-    url2 = f"https://in.tradingview.com/symbols/NSE-{ticker_user}/"
-    url3 = f"https://in.tradingview.com/symbols/NSE-{ticker_user}/news/"
-    url4 = f"https://in.tradingview.com/symbols/NSE-{ticker_user}/minds/"
-    loader = WebBaseLoader([url1,url2,url3,url4])
-    docs = loader.load()
-    st.divider()
-    # llm_prompt_template = """You are an expert Stock Market Trader for stock market insights based on fundamental, analytical, profit based and company financials.
-    # Based on the context below
-    # {context}, Summarize the stock based on Historical data based on fundamental, price, news, sentiment , any red flags and suggest rating of the Stock in a 1 to 10 Scale"""
-    llm_prompt_template = """You are an expert Stock Market Trader specializing in stock market insights derived from fundamental analysis, analytical trends, profit-based evaluations, news indicators from different sites and detailed company financials.
-    Using your expertise, please analyze the stock based on the provided context below.
-    Context:
-    {input_documents}
-    Task:
-    Summarize the stock based on its historical and current data. Keep it CONCISE & BRIEF.
-    Evaluate the stock on the following parameters:
-    1. Company Fundamentals: Assess the stock's intrinsic value, growth potential, and financial health.
-    2. Current & Future Price Trends: Analyze historical price movements and current price trends.
-    3. News and Sentiment: Review recent news articles, press releases, and social media sentiment.
-    4. Red Flags: Identify any potential risks or warning signs.
-    5. Provide a rating for the stock on a scale of 1 to 10.
-    6. Advise if the stock is a good buy for the next 1,5, 10 weeks.
-    7. Suggest at what price we need to buy and hold or sell the stock
-    PROVIDE THE DETAILS based on just the FACTS present in the document
-    PROVIDE THE DETAILS IN an JSON Object. Stick to the below JSON object
-    {{
-      "stock_summary": {{
-        "company_name": "",
-        "ticker": "",
-        "exchange": "",
-        "description": "",
-        "current_price": "",
-        "market_cap": "",
-        "historical_performance": {{
-          "5_day": "",
-          "1_month": "",
-          "6_months": "",
-          "1_year": "",
-          "5_years": ""
-        }}
-      }},
-      "evaluation_parameters": {{
-        "company_fundamentals": {{
-          "assessment": "",
-          "key_metrics": {{
-            "pe_ratio": "",
-            "volume":"",
-            "revenue_growth_yoy": "",
-            "net_income_growth_yoy": "",
-            "eps_growth_yoy": "",
-            "dividend_yield": "",
-            "balance_sheet": "",
-            "return_on_capital": ""
-          }}
-        }},
-        "current_and_future_price_trends": {{
-          "assessment": "",
-          "historical_trends": "",
-          "current_trends": "",
-          "technical_analysis_notes": "",
-          "technical_indicators":""
-        }},
-        "news_and_sentiment": {{
-          "assessment": "",
-          "positive_sentiment": [
-            "",
-            "",
-            ""
-          ],
-          "negative_sentiment": [
-            "",
-            "",
-            ""
-          ]
-        }},
-        "red_flags": [
-          {{
-            "flag": "",
-            "details": ""
           }},
-          {{
-            "flag": "",
-            "details": ""
           }},
-          {{
-            "flag": "",
-            "details": ""
           }}
-        ]
-      }},
-      "overall_rating": {{
-        "rating": "X/10",
-        "justification": ""
-      }},
-      "investment_advice": {{
-        "next_1_weeks_outlook": "",
-        "next_5_weeks_outlook": "",
-        "next_10_weeks_outlook": "",
-        "price_action_suggestions": {{
-          "buy": "",
-          "hold": "",
-          "sell": ""
         }}
-      }}
-    }}
-    """
-    # st.sidebar.subheader('Prompt')
-    # user_prompt = st.sidebar.text_area("Enter Prompt",llm_prompt_template)
-    #https://huggingface.co/spaces/pradeepodela/Stock-Analyser/blob/main/app.py
-    interval = Interval.INTERVAL_1_DAY
-    analysis_summary = get_tradingview_analysis(
-            symbol=ticker_user,
-            exchange="NSE",
-            screener="india",
-            interval=interval,
-        )
-    # st.title("Analysis Summary")
-    # st.dataframe(analysis_summary.summary)
-    # query = f"{ticker_user} stock"
-    details = {
-        "symbol": ticker_user,
-        "exchange": "NSE",
-        "screener": "india",
-        "interval": interval,
-    }
-    # st.title("Details")
-    # st.dataframe(details)
-    # st.title("Oscillator Analysis")
-    # st.dataframe(analysis_summary.oscillators)
-    # st.title("Moving Averages")
-    # st.dataframe(analysis_summary.moving_averages)
-    # st.title("Summary")
-    # st.dataframe(analysis_summary.summary)
-    # st.title("Indicators")
-    # st.dataframe(analysis_summary.indicators)
-    # Page Title
-    st.header(f"📊 TradingView Analysis: {ticker_user}:{interval} ({details['exchange']})")
-    # --- Row 1: Details + Summary ---
-    col1, col2 = st.columns([1, 3])
-    with col1:
-        st.subheader("📝 Summary")
-        # st.write(analysis_summary.summary)
-        summary= analysis_summary.summary
-        # Prepare data for stacked bar chart: each category with its count
-        data = pd.DataFrame({
-            'category': ['BUY', 'SELL', 'NEUTRAL'],
-            'count': [summary['BUY'], summary['SELL'], summary['NEUTRAL']]
-        })
-        # Add a constant key to create a single stacked bar
-        data['key'] = 'Recommendations'
-        chart = alt.Chart(data).mark_bar().encode(
-            y=alt.Y('key:N', axis=None),  # single bar, no y axis
-            x=alt.X('count:Q'),
-            color=alt.Color('category:N', scale=alt.Scale(
-                domain=['BUY', 'SELL', 'NEUTRAL'],
-                range=['green', 'red', 'gold']
-            )),
-            tooltip=['category', 'count']
-        ).properties(
-            width=600,
-            height=50
-        )
-        st.altair_chart(chart, use_container_width=True)
-    # --- Row 2: Oscillators + Moving Averages ---
-    # col3, col4 = st.columns(2)
-    # with col3:
-    #     st.subheader("⚙️ Oscillator Analysis")
-    #     st.dataframe(analysis_summary.oscillators, use_container_width=True)
-    # with col4:
-    #     st.subheader("📈 Moving Averages")
-    #     st.dataframe(analysis_summary.moving_averages, use_container_width=True)
-    # # --- Row 3: Indicators ---
-    # st.subheader("🔍 Indicators")
-    # st.dataframe(analysis_summary.indicators, use_container_width=True)
-    # url = "https://api.chart-img.com/v2/tradingview/advanced-chart"
-    # api_key = "l0iUFRSeqC9z7nDPTd1hnafPh2RrdcEy6rl6tNqV"
-    # headers = {
-    #     "x-api-key": api_key,
-    #     "content-type": "application/json"
-    # }
-    # data = {
-    #     "height": 400,
-    #     "theme": "light",
-    #     "interval": "1D",
-    #     "session": "extended",
-    #     "symbol": f"NSE:{ticker_user}"
-    # }
-    # response = requests.post(url, headers=headers, json=data)
-    # if response.status_code == 200:
-    #     with open("chart_t1.jpg", "wb") as f:
-    #         f.write(response.content)
-    #     with col2:
-    #         st.image("chart_t1.jpg", caption='')
-    # else:
-    #     st.warning(f"Failed to retrieve image. Status code: {response.status_code}")
-    #     st.warning("Response:", response.text)
-    llm_prompt = PromptTemplate.from_template(llm_prompt_template)
-    llm_chain = LLMChain(llm=llm,prompt=llm_prompt)
-    stuff_chain = StuffDocumentsChain(llm_chain=llm_chain,document_variable_name="input_documents")
-    # res = stuff_chain.invoke(docs)
-    res = stuff_chain.invoke({"input_documents": docs})
-    try:
-        raw_text = res["output_text"]
-        # Remove markdown code block delimiters if present
-        if raw_text.startswith("```json"):
-            raw_text = raw_text[len("```json"):]
-        if raw_text.endswith("```"):
-            raw_text = raw_text[:-3]
-        # Also strip leading/trailing whitespace/newlines
-        raw_text = raw_text.strip()
-        data = json.loads(raw_text)
-        # data = res["output_text"]
-        # Header Info
-        st.markdown(f"### {data['stock_summary']['company_name']} ({data['stock_summary']['ticker']}) | {data['stock_summary']['exchange']}")
-        st.markdown(f"**Description**: {data['stock_summary']['description']}")
-        # === Row 1: Price and Market Cap ===
-        row1 = st.columns(3)
-        row1[0].metric("💰 Current Price", data["stock_summary"]["current_price"])
-        row1[1].metric("🏢 Market Cap", data["stock_summary"]["market_cap"])
-        row1[2].metric("⭐ Rating", data["overall_rating"]["rating"])
-        # === Row 2: Historical Performance ===
-        st.subheader("📊 Historical Performance")
-        perf_cols = st.columns(len(data["stock_summary"]["historical_performance"]))
-        for i, (k, v) in enumerate(data["stock_summary"]["historical_performance"].items()):
-            perf_cols[i].metric(k.replace("_", " ").title(), v)
-        # === Row 3: Fundamentals ===
-        st.subheader("📘 Company Fundamentals")
-        row3 = st.columns(4)
-        metrics = data["evaluation_parameters"]["company_fundamentals"]["key_metrics"]
-        row3[0].metric("P/E Ratio", metrics["pe_ratio"])
-        row3[1].metric("EPS YoY", metrics["eps_growth_yoy"])
-        row3[2].metric("Revenue YoY", metrics["revenue_growth_yoy"])
-        row3[3].metric("Dividend Yield", metrics["dividend_yield"])
-        row3b = st.columns(4)
-        row3b[0].metric("Net Income YoY", metrics["net_income_growth_yoy"])
-        row3b[1].metric("Volume", metrics["volume"])
-        row3b[2].metric("Return on Capital", metrics["return_on_capital"])
-        row3b[3].metric("Balance Sheet", metrics["balance_sheet"])
-        st.info(data["evaluation_parameters"]["company_fundamentals"]["assessment"])
-        # === Row 4: Trends and Technicals ===
-        st.subheader("📈 Trends & Technical Analysis")
-        row4 = st.columns(3)
-        row4[0].markdown(f"**Historical Trends:** {data['evaluation_parameters']['current_and_future_price_trends']['historical_trends']}")
-        row4[1].markdown(f"**Current Trends:** {data['evaluation_parameters']['current_and_future_price_trends']['current_trends']}")
-        row4[2].markdown(f"**Technical Indicators:** {data['evaluation_parameters']['current_and_future_price_trends']['technical_indicators']}")
-        st.success(data["evaluation_parameters"]["current_and_future_price_trends"]["assessment"])
-        st.caption(f"📝 Notes: {data['evaluation_parameters']['current_and_future_price_trends']['technical_analysis_notes']}")
-        # === Row 5: Sentiment ===
-        st.subheader("📰 News & Sentiment")
-        sentiment_cols = st.columns(2)
-        with sentiment_cols[0]:
-            st.success("👍 Positive Sentiment")
-            for s in data["evaluation_parameters"]["news_and_sentiment"]["positive_sentiment"]:
-                st.write(f"✅ {s}")
-        with sentiment_cols[1]:
-            st.error("👎 Negative Sentiment")
-            for s in data["evaluation_parameters"]["news_and_sentiment"]["negative_sentiment"]:
-                st.write(f"❌ {s}")
-        st.info(data["evaluation_parameters"]["news_and_sentiment"]["assessment"])
-        # === Row 6: Red Flags ===
-        st.subheader("🚩 Red Flags")
-        red_flag_cols = st.columns(3)
-        for i, flag in enumerate(data["evaluation_parameters"]["red_flags"]):
-            red_flag_cols[i].warning(f"**{flag['flag']}**\n{flag['details']}")
-        # === Row 7: Investment Advice ===
-        st.subheader("💡 Investment Advice")
-        advice_cols = st.columns(3)
-        advice = data["investment_advice"]
-        advice_cols[0].markdown(f"**Next 1 Week**\n{advice['next_1_weeks_outlook']}")
-        advice_cols[1].markdown(f"**Next 5 Weeks**\n{advice['next_5_weeks_outlook']}")
-        advice_cols[2].markdown(f"**Next 10 Weeks**\n{advice['next_10_weeks_outlook']}")
-        action_cols = st.columns(3)
-        action_cols[0].success(f"**Buy:** {advice['price_action_suggestions']['buy']}")
-        action_cols[1].info(f"**Hold:** {advice['price_action_suggestions']['hold']}")
-        action_cols[2].error(f"**Sell:** {advice['price_action_suggestions']['sell']}")
-        # === Footer ===
-        st.markdown("---")
-        st.caption("Generated by AI-powered financial analysis dashboard.")
-    except json.JSONDecodeError as e:
-        st.error(f"JSON decode error: {e}")
-        st.write("Raw text was:")
-        st.text(res["output_text"])

 llm = ChatGoogleGenerativeAI(model="gemini-2.5-pro",google_api_key = GOOGLE_API_KEY)
 #llm_vis = ChatGoogleGenerativeAI(model="gemini-pro-vision",google_api_key = GOOGLE_API_KEY)
+activities = ["Symbol Analysis","News Sentiment"]
+if activities=="Symbol Analysis":
+    def get_tradingview_analysis(symbol, exchange, screener, interval):
+        try:
+            stock = TA_Handler(
+                symbol=symbol,
+                screener=screener,
+                exchange=exchange,
+                interval=interval,
+            )
+            analysis_summary = stock.get_analysis()
+            return analysis_summary
+        except Exception as e:
+            return {"error": str(e)}
+    if ticker_user!="":
+        url1 = f"https://www.google.com/finance/quote/{ticker_user}:NSE?hl=en"
+        url2 = f"https://in.tradingview.com/symbols/NSE-{ticker_user}/"
+        url3 = f"https://in.tradingview.com/symbols/NSE-{ticker_user}/news/"
+        url4 = f"https://in.tradingview.com/symbols/NSE-{ticker_user}/minds/"
+        loader = WebBaseLoader([url1,url2,url3,url4])
+        docs = loader.load()
+        st.divider()
+        # llm_prompt_template = """You are an expert Stock Market Trader for stock market insights based on fundamental, analytical, profit based and company financials.
+        # Based on the context below
+        # {context}, Summarize the stock based on Historical data based on fundamental, price, news, sentiment , any red flags and suggest rating of the Stock in a 1 to 10 Scale"""
+        llm_prompt_template = """You are an expert Stock Market Trader specializing in stock market insights derived from fundamental analysis, analytical trends, profit-based evaluations, news indicators from different sites and detailed company financials.
+        Using your expertise, please analyze the stock based on the provided context below.
+        Context:
+        {input_documents}
+        Task:
+        Summarize the stock based on its historical and current data. Keep it CONCISE & BRIEF.
+        Evaluate the stock on the following parameters:
+        1. Company Fundamentals: Assess the stock's intrinsic value, growth potential, and financial health.
+        2. Current & Future Price Trends: Analyze historical price movements and current price trends.
+        3. News and Sentiment: Review recent news articles, press releases, and social media sentiment.
+        4. Red Flags: Identify any potential risks or warning signs.
+        5. Provide a rating for the stock on a scale of 1 to 10.
+        6. Advise if the stock is a good buy for the next 1,5, 10 weeks.
+        7. Suggest at what price we need to buy and hold or sell the stock
+        PROVIDE THE DETAILS based on just the FACTS present in the document
+        PROVIDE THE DETAILS IN an JSON Object. Stick to the below JSON object
+        {{
+          "stock_summary": {{
+            "company_name": "",
+            "ticker": "",
+            "exchange": "",
+            "description": "",
+            "current_price": "",
+            "market_cap": "",
+            "historical_performance": {{
+              "5_day": "",
+              "1_month": "",
+              "6_months": "",
+              "1_year": "",
+              "5_years": ""
+            }}
+          }},
+          "evaluation_parameters": {{
+            "company_fundamentals": {{
+              "assessment": "",
+              "key_metrics": {{
+                "pe_ratio": "",
+                "volume":"",
+                "revenue_growth_yoy": "",
+                "net_income_growth_yoy": "",
+                "eps_growth_yoy": "",
+                "dividend_yield": "",
+                "balance_sheet": "",
+                "return_on_capital": ""
+              }}
+            }},
+            "current_and_future_price_trends": {{
+              "assessment": "",
+              "historical_trends": "",
+              "current_trends": "",
+              "technical_analysis_notes": "",
+              "technical_indicators":""
+            }},
+            "news_and_sentiment": {{
+              "assessment": "",
+              "positive_sentiment": [
+                "",
+                "",
+                ""
+              ],
+              "negative_sentiment": [
+                "",
+                "",
+                ""
+              ]
+            }},
+            "red_flags": [
+              {{
+                "flag": "",
+                "details": ""
+              }},
+              {{
+                "flag": "",
+                "details": ""
+              }},
+              {{
+                "flag": "",
+                "details": ""
+              }}
+            ]
           }},
+          "overall_rating": {{
+            "rating": "X/10",
+            "justification": ""
           }},
+          "investment_advice": {{
+            "next_1_weeks_outlook": "",
+            "next_5_weeks_outlook": "",
+            "next_10_weeks_outlook": "",
+            "price_action_suggestions": {{
+              "buy": "",
+              "hold": "",
+              "sell": ""
+            }}
           }}
         }}
+        """
+        # st.sidebar.subheader('Prompt')
+        # user_prompt = st.sidebar.text_area("Enter Prompt",llm_prompt_template)
+        #https://huggingface.co/spaces/pradeepodela/Stock-Analyser/blob/main/app.py
+        interval = Interval.INTERVAL_1_DAY
+        analysis_summary = get_tradingview_analysis(
+                symbol=ticker_user,
+                exchange="NSE",
+                screener="india",
+                interval=interval,
+            )
+        # st.title("Analysis Summary")
+        # st.dataframe(analysis_summary.summary)
+        # query = f"{ticker_user} stock"
+        details = {
+            "symbol": ticker_user,
+            "exchange": "NSE",
+            "screener": "india",
+            "interval": interval,
+        }
+        # st.title("Details")
+        # st.dataframe(details)
+        # st.title("Oscillator Analysis")
+        # st.dataframe(analysis_summary.oscillators)
+        # st.title("Moving Averages")
+        # st.dataframe(analysis_summary.moving_averages)
+        # st.title("Summary")
+        # st.dataframe(analysis_summary.summary)
+        # st.title("Indicators")
+        # st.dataframe(analysis_summary.indicators)
+        # Page Title
+        st.header(f"📊 TradingView Analysis: {ticker_user}:{interval} ({details['exchange']})")
+        # --- Row 1: Details + Summary ---
+        col1, col2 = st.columns([1, 3])
+        with col1:
+            st.subheader("📝 Summary")
+            # st.write(analysis_summary.summary)
+            summary= analysis_summary.summary
+            counts = {
+                "BUY": summary["BUY"],
+                "SELL": summary["SELL"],
+                "NEUTRAL": summary["NEUTRAL"]
+            }
+            total = sum(counts.values())
+            # Calculate percentage widths
+            percentages = {k: (v / total) * 100 for k, v in counts.items()}
+            # Color map
+            color_map = {
+                "BUY": "#4CAF50",     # Green
+                "SELL": "#F44336",    # Red
+                "NEUTRAL": "#FFC107"  # Amber
+            }
+            # Create the stacked bar using HTML
+            bar_html = '<div style="display: flex; height: 30px; width: 100%; border: 1px solid #ccc; border-radius: 5px; overflow: hidden;">'
+            for key in ['BUY', 'SELL', 'NEUTRAL']:
+                bar_html += f'''
+                    <div style="
+                        width: {percentages[key]}%;
+                        background-color: {color_map[key]};
+                        display: flex;
+                        justify-content: center;
+                        align-items: center;
+                        color: white;
+                        font-size: 12px;
+                        font-weight: bold;">
+                        {key} {counts[key]}
+                    </div>
+                '''
+            bar_html += '</div>'
+            st.markdown("### Recommendation Summary")
+            st.markdown(f"**Final Recommendation**: `{summary['RECOMMENDATION']}`")
+            st.markdown(bar_html, unsafe_allow_html=True)
+        # --- Row 2: Oscillators + Moving Averages ---
+        # col3, col4 = st.columns(2)
+        # with col3:
+        #     st.subheader("⚙️ Oscillator Analysis")
+        #     st.dataframe(analysis_summary.oscillators, use_container_width=True)
+        # with col4:
+        #     st.subheader("📈 Moving Averages")
+        #     st.dataframe(analysis_summary.moving_averages, use_container_width=True)
+        # # --- Row 3: Indicators ---
+        # st.subheader("🔍 Indicators")
+        # st.dataframe(analysis_summary.indicators, use_container_width=True)
+        # url = "https://api.chart-img.com/v2/tradingview/advanced-chart"
+        # api_key = "l0iUFRSeqC9z7nDPTd1hnafPh2RrdcEy6rl6tNqV"
+        # headers = {
+        #     "x-api-key": api_key,
+        #     "content-type": "application/json"
+        # }
+        # data = {
+        #     "height": 400,
+        #     "theme": "light",
+        #     "interval": "1D",
+        #     "session": "extended",
+        #     "symbol": f"NSE:{ticker_user}"
+        # }
+        # response = requests.post(url, headers=headers, json=data)
+        # if response.status_code == 200:
+        #     with open("chart_t1.jpg", "wb") as f:
+        #         f.write(response.content)
+        #     with col2:
+        #         st.image("chart_t1.jpg", caption='')
+        # else:
+        #     st.warning(f"Failed to retrieve image. Status code: {response.status_code}")
+        #     st.warning("Response:", response.text)
+        llm_prompt = PromptTemplate.from_template(llm_prompt_template)
+        llm_chain = LLMChain(llm=llm,prompt=llm_prompt)
+        stuff_chain = StuffDocumentsChain(llm_chain=llm_chain,document_variable_name="input_documents")
+        # res = stuff_chain.invoke(docs)
+        res = stuff_chain.invoke({"input_documents": docs})
+        try:
+            raw_text = res["output_text"]
+            # Remove markdown code block delimiters if present
+            if raw_text.startswith("```json"):
+                raw_text = raw_text[len("```json"):]
+            if raw_text.endswith("```"):
+                raw_text = raw_text[:-3]
+            # Also strip leading/trailing whitespace/newlines
+            raw_text = raw_text.strip()
+            data = json.loads(raw_text)
+            # data = res["output_text"]
+            # Header Info
+            st.markdown(f"### {data['stock_summary']['company_name']} ({data['stock_summary']['ticker']}) | {data['stock_summary']['exchange']}")
+            st.markdown(f"**Description**: {data['stock_summary']['description']}")
+            # === Row 1: Price and Market Cap ===
+            row1 = st.columns(3)
+            row1[0].metric("💰 Current Price", data["stock_summary"]["current_price"])
+            row1[1].metric("🏢 Market Cap", data["stock_summary"]["market_cap"])
+            row1[2].metric("⭐ Rating", data["overall_rating"]["rating"])
+            # === Row 2: Historical Performance ===
+            st.subheader("📊 Historical Performance")
+            perf_cols = st.columns(len(data["stock_summary"]["historical_performance"]))
+            for i, (k, v) in enumerate(data["stock_summary"]["historical_performance"].items()):
+                perf_cols[i].metric(k.replace("_", " ").title(), v)
+            # === Row 3: Fundamentals ===
+            st.subheader("📘 Company Fundamentals")
+            row3 = st.columns(4)
+            metrics = data["evaluation_parameters"]["company_fundamentals"]["key_metrics"]
+            row3[0].metric("P/E Ratio", metrics["pe_ratio"])
+            row3[1].metric("EPS YoY", metrics["eps_growth_yoy"])
+            row3[2].metric("Revenue YoY", metrics["revenue_growth_yoy"])
+            row3[3].metric("Dividend Yield", metrics["dividend_yield"])
+            row3b = st.columns(4)
+            row3b[0].metric("Net Income YoY", metrics["net_income_growth_yoy"])
+            row3b[1].metric("Volume", metrics["volume"])
+            row3b[2].metric("Return on Capital", metrics["return_on_capital"])
+            row3b[3].metric("Balance Sheet", metrics["balance_sheet"])
+            st.info(data["evaluation_parameters"]["company_fundamentals"]["assessment"])
+            # === Row 4: Trends and Technicals ===
+            st.subheader("📈 Trends & Technical Analysis")
+            row4 = st.columns(3)
+            row4[0].markdown(f"**Historical Trends:** {data['evaluation_parameters']['current_and_future_price_trends']['historical_trends']}")
+            row4[1].markdown(f"**Current Trends:** {data['evaluation_parameters']['current_and_future_price_trends']['current_trends']}")
+            row4[2].markdown(f"**Technical Indicators:** {data['evaluation_parameters']['current_and_future_price_trends']['technical_indicators']}")
+            st.success(data["evaluation_parameters"]["current_and_future_price_trends"]["assessment"])
+            st.caption(f"📝 Notes: {data['evaluation_parameters']['current_and_future_price_trends']['technical_analysis_notes']}")
+            # === Row 5: Sentiment ===
+            st.subheader("📰 News & Sentiment")
+            sentiment_cols = st.columns(2)
+            with sentiment_cols[0]:
+                st.success("👍 Positive Sentiment")
+                for s in data["evaluation_parameters"]["news_and_sentiment"]["positive_sentiment"]:
+                    st.write(f"✅ {s}")
+            with sentiment_cols[1]:
+                st.error("👎 Negative Sentiment")
+                for s in data["evaluation_parameters"]["news_and_sentiment"]["negative_sentiment"]:
+                    st.write(f"❌ {s}")
+            st.info(data["evaluation_parameters"]["news_and_sentiment"]["assessment"])
+            # === Row 6: Red Flags ===
+            st.subheader("🚩 Red Flags")
+            red_flag_cols = st.columns(3)
+            for i, flag in enumerate(data["evaluation_parameters"]["red_flags"]):
+                red_flag_cols[i].warning(f"**{flag['flag']}**\n{flag['details']}")
+            # === Row 7: Investment Advice ===
+            st.subheader("💡 Investment Advice")
+            advice_cols = st.columns(3)
+            advice = data["investment_advice"]
+            advice_cols[0].markdown(f"**Next 1 Week**\n{advice['next_1_weeks_outlook']}")
+            advice_cols[1].markdown(f"**Next 5 Weeks**\n{advice['next_5_weeks_outlook']}")
+            advice_cols[2].markdown(f"**Next 10 Weeks**\n{advice['next_10_weeks_outlook']}")
+            action_cols = st.columns(3)
+            action_cols[0].success(f"**Buy:** {advice['price_action_suggestions']['buy']}")
+            action_cols[1].info(f"**Hold:** {advice['price_action_suggestions']['hold']}")
+            action_cols[2].error(f"**Sell:** {advice['price_action_suggestions']['sell']}")
+            # === Footer ===
+            st.markdown("---")
+            st.caption("Generated by AI-powered financial analysis dashboard.")
+        except json.JSONDecodeError as e:
+            st.error(f"JSON decode error: {e}")
+            st.write("Raw text was:")
+            st.text(res["output_text"])
+    elif activities=="News Sentiment":
+        st.header("News Action : ")