sigma-terminal 2.0.1__py3-none-any.whl → 3.2.0__py3-none-any.whl

sigma/reporting.py

@@ -0,0 +1,658 @@
+"""Reporting system - Research memos, exports, reproducibility."""
+
+import json
+import os
+from datetime import datetime, date
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Union
+
+import pandas as pd
+from pydantic import BaseModel, Field
+
+
+# ============================================================================
+# DATA MODELS
+# ============================================================================
+
+class ResearchMemo(BaseModel):
+    """Structured research memo."""
+    
+    id: str = Field(default_factory=lambda: datetime.now().strftime("%Y%m%d_%H%M%S"))
+    title: str
+    thesis: str
+    key_findings: List[str]
+    data_sources: List[str]
+    methodology: str
+    results: Dict[str, Any]
+    conclusions: List[str]
+    risks_and_limitations: List[str]
+    recommendations: List[str]
+    appendix: Optional[Dict[str, Any]] = None
+    created_at: datetime = Field(default_factory=datetime.now)
+    author: str = "Sigma"
+    tags: List[str] = Field(default_factory=list)
+
+
+class ExportConfig(BaseModel):
+    """Configuration for exports."""
+    
+    format: str = "markdown"  # markdown, html, pdf, json
+    include_charts: bool = True
+    include_data: bool = True
+    include_code: bool = False
+    chart_format: str = "png"  # png, svg, html
+    data_format: str = "csv"  # csv, excel, parquet
+
+
+class ReproducibilityConfig(BaseModel):
+    """Configuration for reproducibility."""
+    
+    query: str
+    timestamp: datetime = Field(default_factory=datetime.now)
+    data_hash: Optional[str] = None
+    parameters: Dict[str, Any] = Field(default_factory=dict)
+    data_sources: List[str] = Field(default_factory=list)
+    random_seed: Optional[int] = None
+    versions: Dict[str, str] = Field(default_factory=dict)
+
+
+# ============================================================================
+# MEMO GENERATOR
+# ============================================================================
+
+class MemoGenerator:
+    """Generate research memos from analysis results."""
+    
+    MEMO_TEMPLATES = {
+        "stock_analysis": """
+# {title}
+
+**Date:** {date}
+**Author:** {author}
+
+## Executive Summary
+
+{thesis}
+
+## Key Findings
+
+{key_findings}
+
+## Methodology
+
+{methodology}
+
+## Results
+
+{results}
+
+## Conclusions
+
+{conclusions}
+
+## Risks and Limitations
+
+{risks}
+
+## Recommendations
+
+{recommendations}
+
+---
+*Generated by Sigma Financial Intelligence*
+""",
+        "comparison": """
+# {title}
+
+**Date:** {date}
+**Author:** {author}
+
+## Overview
+
+{thesis}
+
+## Comparison Summary
+
+{key_findings}
+
+## Detailed Analysis
+
+{results}
+
+## Winner Analysis
+
+{conclusions}
+
+## Considerations
+
+{risks}
+
+## Final Recommendation
+
+{recommendations}
+
+---
+*Generated by Sigma Financial Intelligence*
+""",
+        "backtest": """
+# {title}
+
+**Date:** {date}
+**Author:** {author}
+
+## Strategy Overview
+
+{thesis}
+
+## Performance Summary
+
+{key_findings}
+
+## Methodology
+
+{methodology}
+
+## Detailed Results
+
+{results}
+
+## Risk Analysis
+
+{risks}
+
+## Conclusions and Next Steps
+
+{conclusions}
+
+{recommendations}
+
+---
+*Generated by Sigma Financial Intelligence*
+""",
+    }
+    
+    def generate_memo(
+        self,
+        analysis_type: str,
+        title: str,
+        thesis: str,
+        key_findings: List[str],
+        methodology: str,
+        results: Dict[str, Any],
+        conclusions: List[str],
+        risks: List[str],
+        recommendations: List[str],
+        author: str = "Sigma",
+    ) -> ResearchMemo:
+        """Generate a structured research memo."""
+        
+        return ResearchMemo(
+            title=title,
+            thesis=thesis,
+            key_findings=key_findings,
+            data_sources=[],  # To be filled
+            methodology=methodology,
+            results=results,
+            conclusions=conclusions,
+            risks_and_limitations=risks,
+            recommendations=recommendations,
+            author=author,
+            tags=[analysis_type],
+        )
+    
+    def memo_to_markdown(self, memo: ResearchMemo, template: str = "stock_analysis") -> str:
+        """Convert memo to markdown format."""
+        
+        template_str = self.MEMO_TEMPLATES.get(template, self.MEMO_TEMPLATES["stock_analysis"])
+        
+        # Format lists
+        key_findings_str = "\n".join([f"- {f}" for f in memo.key_findings])
+        conclusions_str = "\n".join([f"- {c}" for c in memo.conclusions])
+        risks_str = "\n".join([f"- {r}" for r in memo.risks_and_limitations])
+        recommendations_str = "\n".join([f"- {r}" for r in memo.recommendations])
+        
+        # Format results
+        results_str = self._format_results(memo.results)
+        
+        return template_str.format(
+            title=memo.title,
+            date=memo.created_at.strftime("%Y-%m-%d"),
+            author=memo.author,
+            thesis=memo.thesis,
+            key_findings=key_findings_str,
+            methodology=memo.methodology,
+            results=results_str,
+            conclusions=conclusions_str,
+            risks=risks_str,
+            recommendations=recommendations_str,
+        )
+    
+    def _format_results(self, results: Dict[str, Any], indent: int = 0) -> str:
+        """Format results dictionary as markdown."""
+        
+        lines = []
+        prefix = "  " * indent
+        
+        for key, value in results.items():
+            if isinstance(value, dict):
+                lines.append(f"{prefix}### {key.replace('_', ' ').title()}")
+                lines.append(self._format_results(value, indent + 1))
+            elif isinstance(value, list):
+                lines.append(f"{prefix}**{key.replace('_', ' ').title()}:**")
+                for item in value:
+                    lines.append(f"{prefix}- {item}")
+            elif isinstance(value, (int, float)):
+                if isinstance(value, float):
+                    if abs(value) < 1:
+                        formatted = f"{value:.2%}"
+                    else:
+                        formatted = f"{value:,.2f}"
+                else:
+                    formatted = f"{value:,}"
+                lines.append(f"{prefix}**{key.replace('_', ' ').title()}:** {formatted}")
+            else:
+                lines.append(f"{prefix}**{key.replace('_', ' ').title()}:** {value}")
+        
+        return "\n".join(lines)
+    
+    def quick_summary(
+        self,
+        ticker: str,
+        analysis_results: Dict[str, Any],
+    ) -> str:
+        """Generate a quick 1-paragraph summary."""
+        
+        # Extract key metrics
+        metrics = analysis_results.get("metrics", {})
+        
+        total_return = metrics.get("total_return", 0)
+        sharpe = metrics.get("sharpe_ratio", 0)
+        max_dd = metrics.get("max_drawdown", 0)
+        
+        # Generate summary
+        performance = "strong" if total_return > 0.15 else "moderate" if total_return > 0 else "weak"
+        risk_adj = "excellent" if sharpe > 1.5 else "good" if sharpe > 1 else "acceptable" if sharpe > 0.5 else "poor"
+        
+        summary = (
+            f"{ticker} has shown {performance} performance with a total return of {total_return:.1%}. "
+            f"Risk-adjusted returns are {risk_adj} (Sharpe: {sharpe:.2f}). "
+            f"Maximum drawdown was {abs(max_dd):.1%}."
+        )
+        
+        return summary
+
+
+# ============================================================================
+# EXPORT ENGINE
+# ============================================================================
+
+class ExportEngine:
+    """Export analysis results in various formats."""
+    
+    def __init__(self, output_dir: str = None):
+        self.output_dir = Path(output_dir or os.path.expanduser("~/Documents/Sigma"))
+        self.output_dir.mkdir(parents=True, exist_ok=True)
+    
+    def export_memo(
+        self,
+        memo: ResearchMemo,
+        config: ExportConfig = None,
+    ) -> str:
+        """Export a research memo."""
+        
+        config = config or ExportConfig()
+        
+        # Generate filename
+        filename = f"{memo.id}_{memo.title.replace(' ', '_')[:30]}"
+        
+        if config.format == "markdown":
+            return self._export_markdown(memo, filename)
+        elif config.format == "html":
+            return self._export_html(memo, filename)
+        elif config.format == "json":
+            return self._export_json(memo, filename)
+        else:
+            return self._export_markdown(memo, filename)
+    
+    def _export_markdown(self, memo: ResearchMemo, filename: str) -> str:
+        """Export as markdown."""
+        
+        generator = MemoGenerator()
+        content = generator.memo_to_markdown(memo)
+        
+        filepath = self.output_dir / f"{filename}.md"
+        filepath.write_text(content)
+        
+        return str(filepath)
+    
+    def _export_html(self, memo: ResearchMemo, filename: str) -> str:
+        """Export as HTML."""
+        
+        generator = MemoGenerator()
+        markdown_content = generator.memo_to_markdown(memo)
+        
+        # Simple markdown to HTML conversion
+        html_content = self._markdown_to_html(markdown_content)
+        
+        # Wrap in HTML template
+        html = f"""
+<!DOCTYPE html>
+<html>
+<head>
+    <title>{memo.title}</title>
+    <style>
+        body {{
+            font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
+            max-width: 800px;
+            margin: 40px auto;
+            padding: 20px;
+            line-height: 1.6;
+            color: #333;
+        }}
+        h1 {{ color: #1a1a1a; border-bottom: 2px solid #0066cc; padding-bottom: 10px; }}
+        h2 {{ color: #333; margin-top: 30px; }}
+        h3 {{ color: #555; }}
+        ul {{ padding-left: 20px; }}
+        li {{ margin: 5px 0; }}
+        strong {{ color: #1a1a1a; }}
+        .meta {{ color: #666; font-size: 0.9em; margin-bottom: 20px; }}
+    </style>
+</head>
+<body>
+{html_content}
+</body>
+</html>
+"""
+        
+        filepath = self.output_dir / f"{filename}.html"
+        filepath.write_text(html)
+        
+        return str(filepath)
+    
+    def _export_json(self, memo: ResearchMemo, filename: str) -> str:
+        """Export as JSON."""
+        
+        filepath = self.output_dir / f"{filename}.json"
+        filepath.write_text(memo.model_dump_json(indent=2))
+        
+        return str(filepath)
+    
+    def _markdown_to_html(self, markdown: str) -> str:
+        """Simple markdown to HTML conversion."""
+        
+        lines = markdown.split("\n")
+        html_lines = []
+        in_list = False
+        
+        for line in lines:
+            # Headers
+            if line.startswith("# "):
+                html_lines.append(f"<h1>{line[2:]}</h1>")
+            elif line.startswith("## "):
+                html_lines.append(f"<h2>{line[3:]}</h2>")
+            elif line.startswith("### "):
+                html_lines.append(f"<h3>{line[4:]}</h3>")
+            # Lists
+            elif line.startswith("- "):
+                if not in_list:
+                    html_lines.append("<ul>")
+                    in_list = True
+                html_lines.append(f"<li>{line[2:]}</li>")
+            # Bold
+            elif line.startswith("**") and ":**" in line:
+                if in_list:
+                    html_lines.append("</ul>")
+                    in_list = False
+                parts = line.split(":**", 1)
+                key = parts[0].replace("**", "")
+                value = parts[1] if len(parts) > 1 else ""
+                html_lines.append(f"<p><strong>{key}:</strong>{value}</p>")
+            # Empty line
+            elif not line.strip():
+                if in_list:
+                    html_lines.append("</ul>")
+                    in_list = False
+                html_lines.append("<br>")
+            # Regular text
+            else:
+                if in_list:
+                    html_lines.append("</ul>")
+                    in_list = False
+                html_lines.append(f"<p>{line}</p>")
+        
+        if in_list:
+            html_lines.append("</ul>")
+        
+        return "\n".join(html_lines)
+    
+    def export_data(
+        self,
+        data: pd.DataFrame,
+        filename: str,
+        format: str = "csv",
+    ) -> str:
+        """Export DataFrame to file."""
+        
+        if format == "csv":
+            filepath = self.output_dir / f"{filename}.csv"
+            data.to_csv(filepath)
+        elif format == "excel":
+            filepath = self.output_dir / f"{filename}.xlsx"
+            data.to_excel(filepath)
+        elif format == "parquet":
+            filepath = self.output_dir / f"{filename}.parquet"
+            data.to_parquet(filepath)
+        else:
+            filepath = self.output_dir / f"{filename}.csv"
+            data.to_csv(filepath)
+        
+        return str(filepath)
+    
+    def export_chart(
+        self,
+        fig,  # plotly figure
+        filename: str,
+        format: str = "png",
+        scale: int = 2,
+    ) -> str:
+        """Export chart to file."""
+        
+        filepath = self.output_dir / f"{filename}.{format}"
+        
+        if format == "html":
+            fig.write_html(str(filepath))
+        else:
+            fig.write_image(str(filepath), format=format, scale=scale)
+        
+        return str(filepath)
+
+
+# ============================================================================
+# REPRODUCIBILITY ENGINE
+# ============================================================================
+
+class ReproducibilityEngine:
+    """Ensure reproducibility of analysis."""
+    
+    def __init__(self, config_dir: str = None):
+        self.config_dir = Path(config_dir or os.path.expanduser("~/.sigma/reproducibility"))
+        self.config_dir.mkdir(parents=True, exist_ok=True)
+    
+    def save_config(
+        self,
+        query: str,
+        parameters: Dict[str, Any],
+        data_sources: List[str],
+        random_seed: Optional[int] = None,
+    ) -> str:
+        """Save reproducibility configuration."""
+        
+        import hashlib
+        
+        config = ReproducibilityConfig(
+            query=query,
+            parameters=parameters,
+            data_sources=data_sources,
+            random_seed=random_seed,
+            versions=self._get_versions(),
+        )
+        
+        # Generate config ID
+        config_hash = hashlib.sha256(
+            f"{query}{json.dumps(parameters, sort_keys=True)}".encode()
+        ).hexdigest()[:12]
+        
+        config_id = f"{datetime.now().strftime('%Y%m%d_%H%M%S')}_{config_hash}"
+        
+        # Save config
+        filepath = self.config_dir / f"{config_id}.json"
+        filepath.write_text(config.model_dump_json(indent=2))
+        
+        return config_id
+    
+    def load_config(self, config_id: str) -> Optional[ReproducibilityConfig]:
+        """Load reproducibility configuration."""
+        
+        filepath = self.config_dir / f"{config_id}.json"
+        
+        if not filepath.exists():
+            return None
+        
+        data = json.loads(filepath.read_text())
+        return ReproducibilityConfig(**data)
+    
+    def _get_versions(self) -> Dict[str, str]:
+        """Get versions of key packages."""
+        
+        versions = {}
+        
+        packages = ["pandas", "numpy", "scipy", "plotly", "yfinance"]
+        
+        for package in packages:
+            try:
+                import importlib
+                mod = importlib.import_module(package)
+                versions[package] = getattr(mod, "__version__", "unknown")
+            except ImportError:
+                versions[package] = "not installed"
+        
+        return versions
+    
+    def generate_reproduction_script(
+        self,
+        config: ReproducibilityConfig,
+    ) -> str:
+        """Generate a Python script to reproduce the analysis."""
+        
+        script = f'''#!/usr/bin/env python3
+"""
+Reproduction Script
+Generated: {datetime.now().isoformat()}
+Original Query: {config.query}
+"""
+
+import pandas as pd
+import numpy as np
+
+# Set random seed for reproducibility
+{f"np.random.seed({config.random_seed})" if config.random_seed else "# No random seed specified"}
+
+# Parameters
+PARAMETERS = {json.dumps(config.parameters, indent=4)}
+
+# Data sources
+DATA_SOURCES = {json.dumps(config.data_sources, indent=4)}
+
+# Expected versions (for verification)
+EXPECTED_VERSIONS = {json.dumps(config.versions, indent=4)}
+
+def verify_versions():
+    """Verify package versions match original analysis."""
+    import warnings
+    for package, expected in EXPECTED_VERSIONS.items():
+        try:
+            import importlib
+            mod = importlib.import_module(package)
+            actual = getattr(mod, "__version__", "unknown")
+            if actual != expected:
+                warnings.warn(f"{{package}} version mismatch: {{actual}} vs {{expected}}")
+        except ImportError:
+            warnings.warn(f"{{package}} not installed")
+
+def main():
+    """Reproduce the analysis."""
+    verify_versions()
+    
+    # TODO: Add reproduction code
+    print("Reproduction script generated. Add your analysis code here.")
+    print(f"Original query: {config.query}")
+
+if __name__ == "__main__":
+    main()
+'''
+        
+        return script
+
+
+# ============================================================================
+# SESSION LOGGER
+# ============================================================================
+
+class SessionLogger:
+    """Log analysis sessions for audit and reproducibility."""
+    
+    def __init__(self, log_dir: str = None):
+        self.log_dir = Path(log_dir or os.path.expanduser("~/.sigma/logs"))
+        self.log_dir.mkdir(parents=True, exist_ok=True)
+        self.session_id = datetime.now().strftime("%Y%m%d_%H%M%S")
+        self.entries = []
+    
+    def log_query(self, query: str, response: str = None):
+        """Log a query and response."""
+        
+        entry = {
+            "timestamp": datetime.now().isoformat(),
+            "type": "query",
+            "query": query,
+            "response": response,
+        }
+        self.entries.append(entry)
+    
+    def log_action(self, action: str, details: Dict[str, Any] = None):
+        """Log an action."""
+        
+        entry = {
+            "timestamp": datetime.now().isoformat(),
+            "type": "action",
+            "action": action,
+            "details": details or {},
+        }
+        self.entries.append(entry)
+    
+    def log_error(self, error: str, context: Dict[str, Any] = None):
+        """Log an error."""
+        
+        entry = {
+            "timestamp": datetime.now().isoformat(),
+            "type": "error",
+            "error": error,
+            "context": context or {},
+        }
+        self.entries.append(entry)
+    
+    def save_session(self) -> str:
+        """Save session log to file."""
+        
+        filepath = self.log_dir / f"session_{self.session_id}.json"
+        
+        session_data = {
+            "session_id": self.session_id,
+            "start_time": self.entries[0]["timestamp"] if self.entries else None,
+            "end_time": datetime.now().isoformat(),
+            "entry_count": len(self.entries),
+            "entries": self.entries,
+        }
+        
+        filepath.write_text(json.dumps(session_data, indent=2))
+        
+        return str(filepath)