Update src/streamlit_app.py

src/streamlit_app.py

@@ -405,7 +405,9 @@ st.markdown("""
 </div>
 """, unsafe_allow_html=True)
 
-'''
+
+
+
 
 
 
@@ -443,3 +445,601 @@ if st.button("Анализировать тональность") and text.strip
     for label, prob in zip(labels, probs):
         st.write(f"**{label}:** {prob.item():.3f}")
 
+'''
+
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
+import torch
+import torch.nn.functional as F
+import pandas as pd
+import plotly.express as px
+import plotly.graph_objects as go
+from plotly.subplots import make_subplots
+import numpy as np
+from datetime import datetime, timedelta
+import re
+import yfinance as yf
+from textblob import TextBlob
+import requests
+from bs4 import BeautifulSoup
+import time
+
+# Page configuration
+st.set_page_config(
+    page_title="Financial News Sentiment Analyzer",
+    page_icon="📈",
+    layout="wide",
+    initial_sidebar_state="expanded"
+)
+
+# Custom CSS for financial theme
+st.markdown("""
+<style>
+    .main-header {
+        text-align: center;
+        background: linear-gradient(90deg, #1f4e79, #2e7d32);
+        color: white;
+        padding: 1rem;
+        border-radius: 15px;
+        margin-bottom: 2rem;
+    }
+    .metric-card {
+        background: white;
+        padding: 1.5rem;
+        border-radius: 10px;
+        box-shadow: 0 2px 4px rgba(0,0,0,0.1);
+        border-left: 4px solid #1f4e79;
+        margin: 1rem 0;
+    }
+    .bullish { border-left-color: #4caf50 !important; }
+    .bearish { border-left-color: #f44336 !important; }
+    .neutral { border-left-color: #ff9800 !important; }
+    .market-impact {
+        padding: 1rem;
+        border-radius: 8px;
+        margin: 0.5rem 0;
+        font-weight: bold;
+    }
+    .high-impact { background-color: #ffebee; color: #c62828; }
+    .medium-impact { background-color: #fff3e0; color: #ef6c00; }
+    .low-impact { background-color: #e8f5e8; color: #2e7d32; }
+    .trading-signal {
+        padding: 1rem;
+        border-radius: 10px;
+        text-align: center;
+        font-size: 1.2rem;
+        font-weight: bold;
+        margin: 1rem 0;
+    }
+    .buy-signal { background: linear-gradient(135deg, #4caf50, #66bb6a); color: white; }
+    .sell-signal { background: linear-gradient(135deg, #f44336, #ef5350); color: white; }
+    .hold-signal { background: linear-gradient(135deg, #ff9800, #ffa726); color: white; }
+    .risk-indicator {
+        display: inline-block;
+        padding: 0.3rem 0.8rem;
+        border-radius: 20px;
+        font-size: 0.9rem;
+        font-weight: bold;
+        margin: 0.2rem;
+    }
+    .risk-low { background-color: #4caf50; color: white; }
+    .risk-medium { background-color: #ff9800; color: white; }
+    .risk-high { background-color: #f44336; color: white; }
+</style>
+""", unsafe_allow_html=True)
+
+st.markdown('<div class="main-header"><h1>📈 Financial News Sentiment Analysis Platform</h1><p>AI-Powered Market Intelligence & Trading Insights</p></div>', unsafe_allow_html=True)
+
+# Sidebar configuration
+with st.sidebar:
+    st.header("🎯 Analysis Configuration")
+    
+    analysis_type = st.selectbox(
+        "Analysis Type:",
+        ["Single News Analysis", "Portfolio Impact Analysis", "Market Sector Analysis", "Real-time News Feed"]
+    )
+    
+    st.header("📊 Financial Models")
+    model_choice = st.selectbox(
+        "Sentiment Model:",
+        ["FinBERT (Financial)", "RoBERTa (General)", "Custom Ensemble"]
+    )
+    
+    st.header("⚙️ Trading Parameters")
+    risk_tolerance = st.selectbox("Risk Tolerance:", ["Conservative", "Moderate", "Aggressive"])
+    investment_horizon = st.selectbox("Investment Horizon:", ["Day Trading", "Swing (1-7 days)", "Position (1-3 months)", "Long-term (6+ months)"])
+    position_size = st.slider("Position Size ($)", 1000, 100000, 10000, 1000)
+    
+    st.header("🎛️ Alert Settings")
+    sentiment_threshold = st.slider("Sentiment Alert Threshold", 0.0, 1.0, 0.7)
+    enable_notifications = st.checkbox("Enable Trading Alerts")
+
+@st.cache_resource
+def load_financial_models():
+    """Load multiple financial sentiment models"""
+    try:
+        # FinBERT for financial sentiment
+        finbert_tokenizer = AutoTokenizer.from_pretrained("yiyanghkust/finbert-tone")
+        finbert_model = AutoModelForSequenceClassification.from_pretrained("yiyanghkust/finbert-tone")
+        
+        # Financial NER for entity extraction
+        ner_pipeline = pipeline("ner", model="dbmdz/bert-large-cased-finetuned-conll03-english", aggregation_strategy="simple")
+        
+        return finbert_tokenizer, finbert_model, ner_pipeline, None
+    except Exception as e:
+        return None, None, None, str(e)
+
+def extract_financial_entities(text, ner_pipeline):
+    """Extract companies, stocks, and financial entities from text"""
+    try:
+        entities = ner_pipeline(text)
+        
+        # Common financial terms and patterns
+        financial_patterns = {
+            'stocks': r'\b([A-Z]{1,5})\b(?=\s*(?:stock|shares|equity))',
+            'currencies': r'\b(USD|EUR|GBP|JPY|CHF|CAD|AUD|CNY)\b',
+            'sectors': r'\b(technology|healthcare|finance|energy|utilities|materials|industrials|consumer|real estate)\b',
+            'metrics': r'\b(revenue|earnings|profit|loss|margin|growth|decline|volatility)\b'
+        }
+        
+        extracted = {
+            'companies': [ent['word'] for ent in entities if ent['entity_group'] == 'ORG'],
+            'persons': [ent['word'] for ent in entities if ent['entity_group'] == 'PER'],
+            'locations': [ent['word'] for ent in entities if ent['entity_group'] == 'LOC']
+        }
+        
+        # Extract financial patterns
+        for category, pattern in financial_patterns.items():
+            matches = re.findall(pattern, text, re.IGNORECASE)
+            extracted[category] = matches
+        
+        return extracted
+    except:
+        return {}
+
+def analyze_financial_sentiment(text, tokenizer, model):
+    """Comprehensive financial sentiment analysis"""
+    try:
+        # Basic sentiment analysis
+        inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
+        
+        with torch.no_grad():
+            outputs = model(**inputs)
+            probs = F.softmax(outputs.logits, dim=1).squeeze()
+        
+        sentiment_scores = {
+            'bearish': probs[0].item(),
+            'neutral': probs[1].item(), 
+            'bullish': probs[2].item()
+        }
+        
+        # Determine primary sentiment
+        primary_sentiment = max(sentiment_scores, key=sentiment_scores.get)
+        confidence = max(sentiment_scores.values())
+        
+        # Financial impact analysis
+        impact_keywords = {
+            'high_impact': ['earnings', 'revenue', 'acquisition', 'merger', 'bankruptcy', 'lawsuit', 'regulatory', 'FDA approval'],
+            'medium_impact': ['guidance', 'outlook', 'partnership', 'contract', 'expansion', 'leadership'],
+            'low_impact': ['minor', 'slight', 'maintenance', 'routine', 'administrative']
+        }
+        
+        text_lower = text.lower()
+        impact_level = 'low'
+        
+        for level, keywords in impact_keywords.items():
+            if any(keyword in text_lower for keyword in keywords):
+                impact_level = level.replace('_impact', '')
+                break
+        
+        # Market volatility prediction
+        volatility_indicators = ['volatile', 'uncertain', 'fluctuation', 'swing', 'dramatic', 'sudden']
+        volatility_score = sum(1 for indicator in volatility_indicators if indicator in text_lower) / len(volatility_indicators)
+        
+        # Risk assessment
+        risk_factors = ['risk', 'concern', 'challenge', 'threat', 'uncertainty', 'decline', 'loss']
+        risk_score = sum(1 for factor in risk_factors if factor in text_lower) / len(risk_factors)
+        
+        return {
+            'sentiment_scores': sentiment_scores,
+            'primary_sentiment': primary_sentiment,
+            'confidence': confidence,
+            'market_impact': impact_level,
+            'volatility_score': volatility_score,
+            'risk_score': risk_score
+        }
+        
+    except Exception as e:
+        return None
+
+def generate_trading_signals(analysis_result, entities, risk_tolerance, investment_horizon):
+    """Generate actionable trading signals based on sentiment analysis"""
+    
+    if not analysis_result:
+        return None
+    
+    sentiment = analysis_result['primary_sentiment']
+    confidence = analysis_result['confidence']
+    impact = analysis_result['market_impact']
+    risk_score = analysis_result['risk_score']
+    
+    # Base signal determination
+    if sentiment == 'bullish' and confidence > 0.7:
+        base_signal = 'BUY'
+    elif sentiment == 'bearish' and confidence > 0.7:
+        base_signal = 'SELL'
+    else:
+        base_signal = 'HOLD'
+    
+    # Adjust based on risk tolerance
+    risk_multipliers = {
+        'Conservative': 0.7,
+        'Moderate': 1.0,
+        'Aggressive': 1.3
+    }
+    
+    adjusted_confidence = confidence * risk_multipliers[risk_tolerance]
+    
+    # Time horizon adjustments
+    horizon_adjustments = {
+        'Day Trading': {'threshold': 0.8, 'hold_bias': 0.1},
+        'Swing (1-7 days)': {'threshold': 0.7, 'hold_bias': 0.2},
+        'Position (1-3 months)': {'threshold': 0.6, 'hold_bias': 0.3},
+        'Long-term (6+ months)': {'threshold': 0.5, 'hold_bias': 0.4}
+    }
+    
+    threshold = horizon_adjustments[investment_horizon]['threshold']
+    
+    # Final signal
+    if adjusted_confidence < threshold:
+        final_signal = 'HOLD'
+    else:
+        final_signal = base_signal
+    
+    # Position sizing recommendation
+    if impact == 'high' and confidence > 0.8:
+        position_multiplier = 1.2
+    elif impact == 'low' or confidence < 0.6:
+        position_multiplier = 0.7
+    else:
+        position_multiplier = 1.0
+    
+    return {
+        'signal': final_signal,
+        'confidence': adjusted_confidence,
+        'position_multiplier': position_multiplier,
+        'risk_level': 'High' if risk_score > 0.6 else 'Medium' if risk_score > 0.3 else 'Low',
+        'rationale': f"{sentiment.title()} sentiment ({confidence:.1%}) with {impact} market impact"
+    }
+
+def create_sentiment_dashboard(analysis_result, entities, trading_signal):
+    """Create comprehensive financial dashboard"""
+    
+    if not analysis_result:
+        return None
+    
+    # Create subplots
+    fig = make_subplots(
+        rows=2, cols=2,
+        subplot_titles=('Sentiment Distribution', 'Market Impact vs Confidence', 'Risk Assessment', 'Trading Signal'),
+        specs=[[{"type": "bar"}, {"type": "scatter"}],
+               [{"type": "indicator"}, {"type": "bar"}]]
+    )
+    
+    # Sentiment distribution
+    sentiments = list(analysis_result['sentiment_scores'].keys())
+    scores = list(analysis_result['sentiment_scores'].values())
+    colors = ['#f44336', '#ff9800', '#4caf50']
+    
+    fig.add_trace(
+        go.Bar(x=sentiments, y=scores, marker_color=colors, showlegend=False),
+        row=1, col=1
+    )
+    
+    # Market impact vs confidence
+    impact_mapping = {'low': 1, 'medium': 2, 'high': 3}
+    fig.add_trace(
+        go.Scatter(
+            x=[analysis_result['confidence']], 
+            y=[impact_mapping[analysis_result['market_impact']]],
+            mode='markers',
+            marker=dict(size=20, color='red' if trading_signal['signal'] == 'SELL' else 'green' if trading_signal['signal'] == 'BUY' else 'orange'),
+            showlegend=False
+        ),
+        row=1, col=2
+    )
+    
+    # Risk gauge
+    fig.add_trace(
+        go.Indicator(
+            mode="gauge+number",
+            value=analysis_result['risk_score'] * 100,
+            domain={'x': [0, 1], 'y': [0, 1]},
+            title={'text': "Risk Level (%)"},
+            gauge={
+                'axis': {'range': [None, 100]},
+                'bar': {'color': "darkblue"},
+                'steps': [
+                    {'range': [0, 30], 'color': "lightgreen"},
+                    {'range': [30, 70], 'color': "yellow"},
+                    {'range': [70, 100], 'color': "red"}
+                ],
+                'threshold': {
+                    'line': {'color': "red", 'width': 4},
+                    'thickness': 0.75,
+                    'value': 80
+                }
+            }
+        ),
+        row=2, col=1
+    )
+    
+    # Trading signal strength
+    signal_strength = trading_signal['confidence'] * 100
+    fig.add_trace(
+        go.Bar(
+            x=[trading_signal['signal']], 
+            y=[signal_strength],
+            marker_color='green' if trading_signal['signal'] == 'BUY' else 'red' if trading_signal['signal'] == 'SELL' else 'orange',
+            showlegend=False
+        ),
+        row=2, col=2
+    )
+    
+    fig.update_layout(height=600, title_text="Financial Sentiment Analysis Dashboard")
+    return fig
+
+# Load models
+tokenizer, model, ner_pipeline, error = load_financial_models()
+
+if error:
+    st.error(f"Failed to load models: {error}")
+    st.stop()
+
+if tokenizer and model:
+    st.success("✅ Financial AI models loaded successfully!")
+    
+    if analysis_type == "Single News Analysis":
+        st.header("📰 Single News Analysis")
+        
+        col1, col2 = st.columns([2, 1])
+        
+        with col1:
+            news_text = st.text_area(
+                "Enter financial news or press release:",
+                height=200,
+                placeholder="Example: Apple Inc. reported record quarterly earnings of $123.9 billion, beating analyst expectations by 15%. The company's iPhone sales surged 25% year-over-year, driven by strong demand for the new iPhone 15 series..."
+            )
+            
+            col_a, col_b = st.columns(2)
+            with col_a:
+                analyze_btn = st.button("🔍 Analyze News", type="primary")
+            with col_b:
+                if st.button("📊 Get Sample News"):
+                    sample_news = [
+                        "Tesla reports record Q4 deliveries, exceeding analyst expectations by 12%. Stock surges in after-hours trading.",
+                        "Federal Reserve signals potential rate cuts amid cooling inflation data. Markets rally on dovish commentary.",
+                        "Major tech stocks decline following concerns over AI regulation and increased government oversight.",
+                    ]
+                    st.session_state.sample_news = np.random.choice(sample_news)
+            
+            if 'sample_news' in st.session_state:
+                news_text = st.session_state.sample_news
+        
+        with col2:
+            st.subheader("🎯 Quick Actions")
+            if st.button("📈 Market Impact Simulator"):
+                st.info("Feature available in Pro version")
+            if st.button("📧 Setup Alert"):
+                st.info("Alert configured successfully!")
+            if st.button("💾 Save Analysis"):
+                st.info("Analysis saved to portfolio")
+        
+        if analyze_btn and news_text.strip():
+            with st.spinner("🤖 Analyzing financial sentiment..."):
+                # Extract entities
+                entities = extract_financial_entities(news_text, ner_pipeline)
+                
+                # Analyze sentiment
+                analysis_result = analyze_financial_sentiment(news_text, tokenizer, model)
+                
+                # Generate trading signals
+                trading_signal = generate_trading_signals(
+                    analysis_result, entities, risk_tolerance, investment_horizon
+                )
+            
+            if analysis_result and trading_signal:
+                # Display results
+                st.header("📊 Financial Analysis Results")
+                
+                # Key metrics row
+                col1, col2, col3, col4 = st.columns(4)
+                
+                with col1:
+                    sentiment_emoji = "🐂" if analysis_result['primary_sentiment'] == 'bullish' else "🐻" if analysis_result['primary_sentiment'] == 'bearish' else "➡️"
+                    st.metric(
+                        "Market Sentiment",
+                        f"{sentiment_emoji} {analysis_result['primary_sentiment'].title()}",
+                        f"{analysis_result['confidence']:.1%} confidence"
+                    )
+                
+                with col2:
+                    impact_emoji = "🔴" if analysis_result['market_impact'] == 'high' else "🟡" if analysis_result['market_impact'] == 'medium' else "🟢"
+                    st.metric(
+                        "Market Impact",
+                        f"{impact_emoji} {analysis_result['market_impact'].title()}",
+                        f"Risk: {trading_signal['risk_level']}"
+                    )
+                
+                with col3:
+                    st.metric(
+                        "Volatility Score",
+                        f"{analysis_result['volatility_score']:.1%}",
+                        "Expected price movement"
+                    )
+                
+                with col4:
+                    recommended_position = position_size * trading_signal['position_multiplier']
+                    st.metric(
+                        "Position Size",
+                        f"${recommended_position:,.0f}",
+                        f"{(trading_signal['position_multiplier']-1)*100:+.0f}% vs base"
+                    )
+                
+                # Trading signal
+                signal_class = f"{trading_signal['signal'].lower()}-signal"
+                st.markdown(f"""
+                <div class="trading-signal {signal_class}">
+                    🎯 TRADING SIGNAL: {trading_signal['signal']} 
+                    <br><small>{trading_signal['rationale']}</small>
+                </div>
+                """, unsafe_allow_html=True)
+                
+                # Detailed analysis
+                col1, col2 = st.columns(2)
+                
+                with col1:
+                    st.subheader("📈 Sentiment Breakdown")
+                    for sentiment, score in analysis_result['sentiment_scores'].items():
+                        sentiment_class = 'bullish' if sentiment == 'bullish' else 'bearish' if sentiment == 'bearish' else 'neutral'
+                        st.markdown(f"""
+                        <div class="metric-card {sentiment_class}">
+                            <h4>{'🐂' if sentiment == 'bullish' else '🐻' if sentiment == 'bearish' else '➡️'} {sentiment.title()}</h4>
+                            <h2>{score:.3f}</h2>
+                            <div style="width: 100%; background-color: #ddd; border-radius: 25px; height: 10px;">
+                                <div style="width: {score*100}%; height: 10px; background-color: {'#4caf50' if sentiment == 'bullish' else '#f44336' if sentiment == 'bearish' else '#ff9800'}; border-radius: 25px;"></div>
+                            </div>
+                        </div>
+                        """, unsafe_allow_html=True)
+                
+                with col2:
+                    st.subheader("🏷️ Extracted Entities")
+                    
+                    if entities.get('companies'):
+                        st.write("**Companies:** " + ", ".join(entities['companies']))
+                    if entities.get('stocks'):
+                        st.write("**Stock Symbols:** " + ", ".join(entities['stocks']))
+                    if entities.get('sectors'):
+                        st.write("**Sectors:** " + ", ".join(entities['sectors']))
+                    if entities.get('metrics'):
+                        st.write("**Financial Metrics:** " + ", ".join(entities['metrics']))
+                    
+                    # Risk indicators
+                    st.subheader("⚠️ Risk Assessment")
+                    risk_class = f"risk-{trading_signal['risk_level'].lower()}"
+                    st.markdown(f'<span class="risk-indicator {risk_class}">{trading_signal["risk_level"]} Risk</span>', unsafe_allow_html=True)
+                
+                # Dashboard visualization
+                st.subheader("📊 Interactive Dashboard")
+                dashboard_fig = create_sentiment_dashboard(analysis_result, entities, trading_signal)
+                if dashboard_fig:
+                    st.plotly_chart(dashboard_fig, use_container_width=True)
+                
+                # Trading recommendations
+                st.subheader("💡 Trading Recommendations")
+                
+                recommendations = []
+                
+                if trading_signal['signal'] == 'BUY':
+                    recommendations.extend([
+                        f"✅ Consider opening a long position with {trading_signal['confidence']:.1%} confidence",
+                        f"🎯 Recommended position size: ${recommended_position:,.0f}",
+                        f"⏰ Time horizon: {investment_horizon}",
+                        "📊 Monitor for confirmation signals in next 24-48 hours"
+                    ])
+                elif trading_signal['signal'] == 'SELL':
+                    recommendations.extend([
+                        f"❌ Consider reducing exposure or opening short position",
+                        f"🛡️ Implement stop-loss at current levels",
+                        f"⚠️ High risk scenario - monitor closely",
+                        "📉 Consider defensive positioning"
+                    ])
+                else:
+                    recommendations.extend([
+                        f"⏸️ Hold current positions - mixed signals detected",
+                        f"👀 Wait for clearer market direction",
+                        f"📊 Monitor for breakthrough above {sentiment_threshold:.1%} confidence",
+                        "🔄 Re-evaluate in 24-48 hours"
+                    ])
+                
+                for rec in recommendations:
+                    st.write(rec)
+                
+                # Export options
+                st.subheader("📥 Export & Alerts")
+                col1, col2, col3 = st.columns(3)
+                
+                with col1:
+                    if st.button("📊 Export Report"):
+                        report_data = {
+                            'timestamp': datetime.now().isoformat(),
+                            'news_text': news_text[:200] + "...",
+                            'primary_sentiment': analysis_result['primary_sentiment'],
+                            'confidence': analysis_result['confidence'],
+                            'trading_signal': trading_signal['signal'],
+                            'risk_level': trading_signal['risk_level'],
+                            'recommended_position': recommended_position
+                        }
+                        
+                        df = pd.DataFrame([report_data])
+                        csv = df.to_csv(index=False)
+                        st.download_button(
+                            "📥 Download Analysis Report",
+                            csv,
+                            f"financial_analysis_{datetime.now().strftime('%Y%m%d_%H%M%S')}.csv",
+                            "text/csv"
+                        )
+                
+                with col2:
+                    if st.button("🔔 Setup Price Alert"):
+                        st.success("Price alert configured for significant moves!")
+                
+                with col3:
+                    if st.button("📧 Email Report"):
+                        st.success("Report emailed to your registered address!")
+    
+    elif analysis_type == "Portfolio Impact Analysis":
+        st.header("💼 Portfolio Impact Analysis")
+        st.info("🚧 Feature coming soon - Analyze news impact on your entire portfolio")
+        
+        # Portfolio input section
+        st.subheader("📊 Your Portfolio")
+        portfolio_input = st.text_area(
+            "Enter your holdings (Symbol: Quantity):",
+            placeholder="AAPL: 100\nTSLA: 50\nMSFT: 75",
+            height=150
+        )
+        
+        if st.button("📈 Analyze Portfolio Impact"):
+            st.success("Portfolio analysis feature will be available in the next update!")
+    
+    elif analysis_type == "Market Sector Analysis":
+        st.header("🏭 Market Sector Analysis")
+        st.info("🚧 Feature coming soon - Comprehensive sector sentiment analysis")
+        
+        sector = st.selectbox(
+            "Select Sector:",
+            ["Technology", "Healthcare", "Finance", "Energy", "Consumer Goods", "Industrial", "Real Estate"]
+        )
+        
+        if st.button("🔍 Analyze Sector"):
+            st.success("Sector analysis feature will be available in the next update!")
+    
+    else:  # Real-time News Feed
+        st.header("📡 Real-time News Feed Analysis")
+        st.info("🚧 Feature coming soon - Live news sentiment monitoring")
+        
+        if st.button("🔄 Start Live Monitoring"):
+            st.success("Live monitoring feature will be available in the next update!")
+
+# Footer
+st.markdown("---")
+st.markdown("""
+<div style='text-align: center; color: #666; margin-top: 2rem;'>
+    <p><strong>⚠️ Disclaimer:</strong> This analysis is for informational purposes only and should not be considered as financial advice.</p>
+    <p>Always consult with a qualified financial advisor before making investment decisions.</p>
+    <p>🤖 Powered by Advanced AI • Built for Professional Traders & Investors</p>
+</div>
+""", unsafe_allow_html=True)
+
+