Atomizer/optimization_engine/reporting/html_report.py

"""
Interactive HTML Report Generator
=================================

Generates professional, interactive HTML reports for optimization studies using:
- Plotly for interactive charts (zoom, pan, hover)
- Tailwind CSS for styling
- Self-contained HTML (works offline)

Features:
- Executive summary with key metrics
- Interactive convergence plot
- Pareto front visualization (multi-objective)
- Parameter importance analysis
- Parallel coordinates plot
- Design comparison table
- Export to PDF option

Usage:
    from optimization_engine.reporting.html_report import HTMLReportGenerator

    generator = HTMLReportGenerator(study_dir)
    report_path = generator.generate()
"""

from __future__ import annotations

import json
import logging
from dataclasses import dataclass, field
from datetime import datetime
from pathlib import Path
from typing import Optional, List, Dict, Any, Tuple
import numpy as np

logger = logging.getLogger(__name__)

# Plotly CDN URL
PLOTLY_CDN = "https://cdn.plot.ly/plotly-2.27.0.min.js"

# Tailwind CDN URL
TAILWIND_CDN = "https://cdn.tailwindcss.com"


@dataclass
class StudyData:
    """Loaded study data for report generation."""

    study_name: str
    description: str = ""

    # Trials data
    trials: List[Dict[str, Any]] = field(default_factory=list)
    n_trials: int = 0
    n_successful: int = 0

    # Design variables
    design_variables: List[str] = field(default_factory=list)
    dv_bounds: Dict[str, Tuple[float, float]] = field(default_factory=dict)

    # Objectives
    objectives: List[str] = field(default_factory=list)
    is_multi_objective: bool = False

    # Constraints
    constraints: List[str] = field(default_factory=list)

    # Best results
    best_trial: Optional[Dict[str, Any]] = None
    best_values: Dict[str, float] = field(default_factory=dict)
    baseline_values: Dict[str, float] = field(default_factory=dict)

    # Pareto front (multi-objective)
    pareto_trials: List[Dict[str, Any]] = field(default_factory=list)

    # Timing
    total_runtime_seconds: float = 0.0
    avg_trial_time: float = 0.0

    # Metadata
    algorithm: str = ""
    created_at: Optional[datetime] = None
    completed_at: Optional[datetime] = None


class HTMLReportGenerator:
    """
    Generates interactive HTML reports for optimization studies.
    """

    def __init__(self, study_dir: Path):
        """
        Initialize the report generator.

        Args:
            study_dir: Path to the study directory
        """
        self.study_dir = Path(study_dir)
        self.study_name = self.study_dir.name
        self.data: Optional[StudyData] = None

    def generate(
        self,
        output_dir: Optional[Path] = None,
        include_pdf: bool = False,
    ) -> Path:
        """
        Generate the HTML report.

        Args:
            output_dir: Output directory (default: study_dir/4_report)
            include_pdf: Also generate PDF version

        Returns:
            Path to generated report
        """
        logger.info(f"Generating report for: {self.study_name}")

        # Load study data
        self.data = self._load_study_data()

        # Set output directory
        if output_dir is None:
            output_dir = self.study_dir / "4_report"
        output_dir.mkdir(parents=True, exist_ok=True)

        # Generate HTML
        html_content = self._generate_html()

        # Save HTML
        report_path = output_dir / "index.html"
        report_path.write_text(html_content, encoding="utf-8")
        logger.info(f"Report saved to: {report_path}")

        # Save figures as separate files
        self._save_figures(output_dir)

        # Save data exports
        self._save_data_exports(output_dir)

        # Generate PDF if requested
        if include_pdf:
            self._generate_pdf(output_dir)

        return report_path

    def _load_study_data(self) -> StudyData:
        """Load all study data from files."""
        data = StudyData(study_name=self.study_name)

        # Load spec/config
        spec = self._load_spec()
        if spec:
            data.description = spec.get("description", spec.get("meta", {}).get("description", ""))
            data.algorithm = spec.get("optimization_settings", {}).get(
                "sampler", spec.get("optimization", {}).get("algorithm", {}).get("type", "")
            )

            # Extract design variables
            for dv in spec.get("design_variables", []):
                name = dv.get("parameter", dv.get("expression_name", dv.get("name", "")))
                data.design_variables.append(name)

                bounds = dv.get("bounds", {})
                if isinstance(bounds, dict):
                    data.dv_bounds[name] = (bounds.get("min", 0), bounds.get("max", 1))
                elif isinstance(bounds, (list, tuple)):
                    data.dv_bounds[name] = tuple(bounds)

            # Extract objectives
            for obj in spec.get("objectives", []):
                data.objectives.append(obj.get("name", "objective"))

            data.is_multi_objective = len(data.objectives) > 1

            # Extract constraints
            for const in spec.get("constraints", []):
                data.constraints.append(const.get("name", "constraint"))

            # Baseline values
            baseline = spec.get("baseline", {})
            data.baseline_values = baseline

        # Load trials from database
        data.trials = self._load_trials_from_db()
        data.n_trials = len(data.trials)
        data.n_successful = len([t for t in data.trials if t.get("success", True)])

        # Find best trial
        if data.trials:
            if data.is_multi_objective:
                # For multi-objective, find Pareto front
                data.pareto_trials = self._find_pareto_front(data.trials, data.objectives)
                data.best_trial = data.pareto_trials[0] if data.pareto_trials else data.trials[0]
            else:
                # Single objective - find minimum
                valid_trials = [t for t in data.trials if t.get("objectives")]
                if valid_trials:
                    obj_name = data.objectives[0] if data.objectives else "objective"
                    data.best_trial = min(
                        valid_trials,
                        key=lambda t: t.get("objectives", {}).get(obj_name, float("inf")),
                    )

            if data.best_trial:
                data.best_values = data.best_trial.get("objectives", {})

        # Calculate timing
        if data.trials:
            times = [t.get("solve_time", 0) for t in data.trials if t.get("solve_time")]
            if times:
                data.total_runtime_seconds = sum(times)
                data.avg_trial_time = np.mean(times)

        return data

    def _load_spec(self) -> Optional[Dict[str, Any]]:
        """Load study specification."""
        spec_paths = [
            self.study_dir / "atomizer_spec.json",
            self.study_dir / "optimization_config.json",
            self.study_dir / "1_setup" / "optimization_config.json",
        ]

        for path in spec_paths:
            if path.exists():
                with open(path) as f:
                    return json.load(f)

        return None

    def _load_trials_from_db(self) -> List[Dict[str, Any]]:
        """Load trials from Optuna database."""
        db_paths = [
            self.study_dir / "3_results" / "study.db",
            self.study_dir / "2_results" / "study.db",
        ]

        for db_path in db_paths:
            if db_path.exists():
                return self._query_optuna_db(db_path)

        # Fall back to JSON history
        return self._load_trials_from_json()

    def _query_optuna_db(self, db_path: Path) -> List[Dict[str, Any]]:
        """Query trials from Optuna SQLite database."""
        import sqlite3

        trials = []

        try:
            conn = sqlite3.connect(str(db_path))
            conn.row_factory = sqlite3.Row
            cursor = conn.cursor()

            # Get study ID
            cursor.execute("SELECT study_id FROM studies LIMIT 1")
            row = cursor.fetchone()
            if not row:
                return trials
            study_id = row["study_id"]

            # Get trials
            cursor.execute(
                """
                SELECT trial_id, number, state, datetime_start, datetime_complete
                FROM trials
                WHERE study_id = ?
                ORDER BY number
            """,
                (study_id,),
            )

            for row in cursor.fetchall():
                trial = {
                    "trial_id": row["trial_id"],
                    "number": row["number"],
                    "state": row["state"],
                    "success": row["state"] == "COMPLETE",
                    "params": {},
                    "objectives": {},
                }

                # Get params
                cursor.execute(
                    """
                    SELECT param_name, param_value
                    FROM trial_params
                    WHERE trial_id = ?
                """,
                    (row["trial_id"],),
                )

                for param_row in cursor.fetchall():
                    try:
                        trial["params"][param_row["param_name"]] = float(param_row["param_value"])
                    except (ValueError, TypeError):
                        trial["params"][param_row["param_name"]] = param_row["param_value"]

                # Get values (objectives)
                cursor.execute(
                    """
                    SELECT objective, value
                    FROM trial_values
                    WHERE trial_id = ?
                """,
                    (row["trial_id"],),
                )

                for val_row in cursor.fetchall():
                    obj_idx = val_row["objective"]
                    obj_name = f"objective_{obj_idx}" if obj_idx > 0 else "objective"
                    trial["objectives"][obj_name] = val_row["value"]

                # Get user attributes
                cursor.execute(
                    """
                    SELECT key, value_json
                    FROM trial_user_attributes
                    WHERE trial_id = ?
                """,
                    (row["trial_id"],),
                )

                for attr_row in cursor.fetchall():
                    try:
                        trial[attr_row["key"]] = json.loads(attr_row["value_json"])
                    except (json.JSONDecodeError, TypeError):
                        trial[attr_row["key"]] = attr_row["value_json"]

                trials.append(trial)

            conn.close()

        except Exception as e:
            logger.warning(f"Failed to query Optuna DB: {e}")

        return trials

    def _load_trials_from_json(self) -> List[Dict[str, Any]]:
        """Load trials from JSON history file."""
        history_paths = [
            self.study_dir / "3_results" / "optimization_history.json",
            self.study_dir / "2_results" / "optimization_history_incremental.json",
        ]

        for path in history_paths:
            if path.exists():
                with open(path) as f:
                    return json.load(f)

        return []

    def _find_pareto_front(
        self, trials: List[Dict[str, Any]], objectives: List[str]
    ) -> List[Dict[str, Any]]:
        """Find Pareto-optimal trials."""
        if not trials or not objectives:
            return []

        pareto = []

        for trial in trials:
            objs = trial.get("objectives", {})
            if not all(obj in objs for obj in objectives):
                continue

            is_dominated = False
            for other in trials:
                other_objs = other.get("objectives", {})
                if not all(obj in other_objs for obj in objectives):
                    continue

                # Check if other dominates trial
                better_in_all = all(
                    other_objs.get(obj, float("inf")) <= objs.get(obj, float("inf"))
                    for obj in objectives
                )
                better_in_one = any(
                    other_objs.get(obj, float("inf")) < objs.get(obj, float("inf"))
                    for obj in objectives
                )

                if better_in_all and better_in_one:
                    is_dominated = True
                    break

            if not is_dominated:
                pareto.append(trial)

        return pareto

    def _generate_html(self) -> str:
        """Generate the complete HTML report."""
        return f"""<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>{self.data.study_name} - Optimization Report</title>
    <script src="{PLOTLY_CDN}"></script>
    <script src="{TAILWIND_CDN}"></script>
    <style>
        .plotly-graph-div {{ width: 100%; }}
        @media print {{
            .no-print {{ display: none; }}
            .page-break {{ page-break-before: always; }}
        }}
    </style>
</head>
<body class="bg-gray-100 min-h-screen">
    <div class="container mx-auto px-4 py-8 max-w-7xl">
        
        {self._generate_header()}
        
        {self._generate_executive_summary()}
        
        {self._generate_convergence_section()}
        
        {self._generate_pareto_section() if self.data.is_multi_objective else ""}
        
        {self._generate_parameters_section()}
        
        {self._generate_best_designs_section()}
        
        {self._generate_parallel_coords_section()}
        
        {self._generate_footer()}
        
    </div>
    
    <script>
        {self._generate_plotly_scripts()}
    </script>
</body>
</html>
"""

    def _generate_header(self) -> str:
        """Generate report header."""
        return f"""
        <!-- Header -->
        <header class="mb-8">
            <div class="flex justify-between items-start">
                <div>
                    <h1 class="text-3xl font-bold text-gray-800">{self.data.study_name}</h1>
                    <p class="text-gray-600 mt-1">{self.data.description or "Optimization Study Report"}</p>
                </div>
                <div class="text-right text-sm text-gray-500">
                    <p>Generated: {datetime.now().strftime("%Y-%m-%d %H:%M")}</p>
                    <p>Algorithm: {self.data.algorithm or "N/A"}</p>
                </div>
            </div>
            <div class="mt-4 flex gap-2 no-print">
                <button onclick="window.print()" class="px-4 py-2 bg-blue-600 text-white rounded hover:bg-blue-700">
                    Export PDF
                </button>
                <a href="data/all_trials.csv" download class="px-4 py-2 bg-green-600 text-white rounded hover:bg-green-700">
                    Download CSV
                </a>
            </div>
        </header>
        """

    def _generate_executive_summary(self) -> str:
        """Generate executive summary section."""
        # Calculate improvement
        improvement = 0.0
        if self.data.baseline_values and self.data.best_values and self.data.objectives:
            obj = self.data.objectives[0]
            baseline = self.data.baseline_values.get(obj, 0)
            best = self.data.best_values.get(obj, 0)
            if baseline > 0:
                improvement = ((baseline - best) / baseline) * 100

        # Format runtime
        runtime_str = self._format_duration(self.data.total_runtime_seconds)

        # Best value display
        best_display = ""
        if self.data.best_values and self.data.objectives:
            obj = self.data.objectives[0]
            val = self.data.best_values.get(obj, 0)
            best_display = f"{val:.4g}"

        return f"""
        <!-- Executive Summary -->
        <section class="bg-white rounded-lg shadow-lg p-6 mb-6">
            <h2 class="text-xl font-semibold text-gray-800 mb-4">Executive Summary</h2>
            
            <div class="grid grid-cols-2 md:grid-cols-4 gap-6">
                <div class="text-center p-4 bg-blue-50 rounded-lg">
                    <div class="text-3xl font-bold text-blue-600">{self.data.n_trials}</div>
                    <div class="text-sm text-gray-600">Total Trials</div>
                </div>
                <div class="text-center p-4 bg-green-50 rounded-lg">
                    <div class="text-3xl font-bold text-green-600">{improvement:.1f}%</div>
                    <div class="text-sm text-gray-600">Improvement</div>
                </div>
                <div class="text-center p-4 bg-purple-50 rounded-lg">
                    <div class="text-3xl font-bold text-purple-600">{best_display}</div>
                    <div class="text-sm text-gray-600">Best {self.data.objectives[0] if self.data.objectives else "Objective"}</div>
                </div>
                <div class="text-center p-4 bg-orange-50 rounded-lg">
                    <div class="text-3xl font-bold text-orange-600">{runtime_str}</div>
                    <div class="text-sm text-gray-600">Total Runtime</div>
                </div>
            </div>
            
            {self._generate_summary_details()}
        </section>
        """

    def _generate_summary_details(self) -> str:
        """Generate detailed summary info."""
        dv_list = ", ".join(self.data.design_variables[:5])
        if len(self.data.design_variables) > 5:
            dv_list += f" (+{len(self.data.design_variables) - 5} more)"

        return f"""
            <div class="mt-6 grid grid-cols-1 md:grid-cols-2 gap-4 text-sm">
                <div>
                    <h3 class="font-semibold text-gray-700">Study Configuration</h3>
                    <ul class="mt-2 space-y-1 text-gray-600">
                        <li><span class="font-medium">Design Variables:</span> {len(self.data.design_variables)}</li>
                        <li><span class="font-medium">Parameters:</span> {dv_list}</li>
                        <li><span class="font-medium">Objectives:</span> {", ".join(self.data.objectives) or "N/A"}</li>
                        <li><span class="font-medium">Constraints:</span> {len(self.data.constraints)}</li>
                    </ul>
                </div>
                <div>
                    <h3 class="font-semibold text-gray-700">Performance</h3>
                    <ul class="mt-2 space-y-1 text-gray-600">
                        <li><span class="font-medium">Success Rate:</span> {self.data.n_successful}/{self.data.n_trials} ({100 * self.data.n_successful / max(1, self.data.n_trials):.0f}%)</li>
                        <li><span class="font-medium">Avg Trial Time:</span> {self.data.avg_trial_time:.1f}s</li>
                        <li><span class="font-medium">Pareto Points:</span> {len(self.data.pareto_trials) if self.data.is_multi_objective else "N/A"}</li>
                    </ul>
                </div>
            </div>
        """

    def _generate_convergence_section(self) -> str:
        """Generate convergence plot section."""
        return """
        <!-- Convergence -->
        <section class="bg-white rounded-lg shadow-lg p-6 mb-6">
            <h2 class="text-xl font-semibold text-gray-800 mb-4">Convergence History</h2>
            <div id="convergence-plot" class="h-96"></div>
            <p class="text-sm text-gray-500 mt-2">
                Hover over points to see trial details. Use mouse to zoom and pan.
            </p>
        </section>
        """

    def _generate_pareto_section(self) -> str:
        """Generate Pareto front section (multi-objective only)."""
        if not self.data.is_multi_objective:
            return ""

        return f"""
        <!-- Pareto Front -->
        <section class="bg-white rounded-lg shadow-lg p-6 mb-6 page-break">
            <h2 class="text-xl font-semibold text-gray-800 mb-4">Pareto Front</h2>
            <div id="pareto-plot" class="h-96"></div>
            <p class="text-sm text-gray-500 mt-2">
                {len(self.data.pareto_trials)} Pareto-optimal solutions found.
                These represent the best trade-offs between objectives.
            </p>
        </section>
        """

    def _generate_parameters_section(self) -> str:
        """Generate parameter importance section."""
        return """
        <!-- Parameter Analysis -->
        <section class="bg-white rounded-lg shadow-lg p-6 mb-6">
            <h2 class="text-xl font-semibold text-gray-800 mb-4">Parameter Analysis</h2>
            <div class="grid grid-cols-1 md:grid-cols-2 gap-6">
                <div id="importance-plot" class="h-80"></div>
                <div id="distribution-plot" class="h-80"></div>
            </div>
        </section>
        """

    def _generate_best_designs_section(self) -> str:
        """Generate best designs table."""
        if not self.data.trials:
            return ""

        # Get top 10 trials
        valid_trials = [t for t in self.data.trials if t.get("objectives")]
        if self.data.is_multi_objective:
            top_trials = self.data.pareto_trials[:10]
        else:
            obj = self.data.objectives[0] if self.data.objectives else "objective"
            top_trials = sorted(
                valid_trials, key=lambda t: t.get("objectives", {}).get(obj, float("inf"))
            )[:10]

        # Build table rows
        rows = []
        for i, trial in enumerate(top_trials, 1):
            params_cells = []
            for dv in self.data.design_variables[:4]:
                val = trial.get("params", {}).get(dv, "N/A")
                if isinstance(val, (int, float)):
                    cell_content = f"{val:.3f}"
                else:
                    cell_content = "N/A"
                params_cells.append(f'<td class="px-4 py-2 text-center">{cell_content}</td>')

            obj_cells = []
            for obj_name in self.data.objectives[:2]:
                val = trial.get("objectives", {}).get(obj_name, "N/A")
                if isinstance(val, (int, float)):
                    cell_content = f"{val:.4f}"
                else:
                    cell_content = "N/A"
                obj_cells.append(
                    f'<td class="px-4 py-2 text-center font-medium">{cell_content}</td>'
                )

            row_class = "bg-green-50" if i == 1 else "hover:bg-gray-50"
            trial_num = trial.get("number", i)
            rows.append(f"""
                <tr class="{row_class}">
                    <td class="px-4 py-2 text-center">{i}</td>
                    <td class="px-4 py-2 text-center">#{trial_num}</td>
                    {"".join(params_cells)}
                    {"".join(obj_cells)}
                </tr>
            """)

        # Build header
        dv_headers = "".join(
            [f'<th class="px-4 py-2">{dv[:12]}</th>' for dv in self.data.design_variables[:4]]
        )
        obj_headers = "".join(
            [f'<th class="px-4 py-2">{obj[:12]}</th>' for obj in self.data.objectives[:2]]
        )

        return f"""
        <!-- Best Designs Table -->
        <section class="bg-white rounded-lg shadow-lg p-6 mb-6 page-break">
            <h2 class="text-xl font-semibold text-gray-800 mb-4">Top Designs</h2>
            <div class="overflow-x-auto">
                <table class="min-w-full text-sm">
                    <thead class="bg-gray-100">
                        <tr>
                            <th class="px-4 py-2">Rank</th>
                            <th class="px-4 py-2">Trial</th>
                            {dv_headers}
                            {obj_headers}
                        </tr>
                    </thead>
                    <tbody class="divide-y">
                        {"".join(rows)}
                    </tbody>
                </table>
            </div>
            <p class="text-sm text-gray-500 mt-4">
                Best design highlighted in green. Full data available in CSV export.
            </p>
        </section>
        """

    def _generate_parallel_coords_section(self) -> str:
        """Generate parallel coordinates plot section."""
        return """
        <!-- Parallel Coordinates -->
        <section class="bg-white rounded-lg shadow-lg p-6 mb-6">
            <h2 class="text-xl font-semibold text-gray-800 mb-4">Design Space Exploration</h2>
            <div id="parallel-plot" class="h-96"></div>
            <p class="text-sm text-gray-500 mt-2">
                Each line represents a trial. Color indicates objective value.
                Drag on axes to filter.
            </p>
        </section>
        """

    def _generate_footer(self) -> str:
        """Generate report footer."""
        return f"""
        <!-- Footer -->
        <footer class="text-center text-sm text-gray-500 mt-8 pb-8">
            <p>Generated by Atomizer Optimization Framework</p>
            <p class="mt-1">Report created: {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}</p>
        </footer>
        """

    def _generate_plotly_scripts(self) -> str:
        """Generate Plotly JavaScript for all charts."""
        return f"""
        // Convergence Plot
        {self._generate_convergence_plot_js()}
        
        // Pareto Plot (if multi-objective)
        {self._generate_pareto_plot_js() if self.data.is_multi_objective else ""}
        
        // Importance Plot
        {self._generate_importance_plot_js()}
        
        // Distribution Plot
        {self._generate_distribution_plot_js()}
        
        // Parallel Coordinates
        {self._generate_parallel_plot_js()}
        """

    def _generate_convergence_plot_js(self) -> str:
        """Generate JavaScript for convergence plot."""
        if not self.data.trials or not self.data.objectives:
            return "// No data for convergence plot"

        obj = self.data.objectives[0]

        # Extract data
        trial_numbers = []
        values = []
        best_so_far = []
        current_best = float("inf")

        for trial in self.data.trials:
            num = trial.get("number", len(trial_numbers))
            val = trial.get("objectives", {}).get(obj)

            if val is not None and not np.isinf(val):
                trial_numbers.append(num)
                values.append(val)
                current_best = min(current_best, val)
                best_so_far.append(current_best)

        return f"""
        var convergenceData = [
            {{
                x: {json.dumps(trial_numbers)},
                y: {json.dumps(values)},
                mode: 'markers',
                type: 'scatter',
                name: 'All Trials',
                marker: {{ color: 'rgba(99, 102, 241, 0.5)', size: 8 }}
            }},
            {{
                x: {json.dumps(trial_numbers)},
                y: {json.dumps(best_so_far)},
                mode: 'lines',
                type: 'scatter',
                name: 'Best So Far',
                line: {{ color: 'rgb(34, 197, 94)', width: 2 }}
            }}
        ];
        
        var convergenceLayout = {{
            title: '',
            xaxis: {{ title: 'Trial Number' }},
            yaxis: {{ title: '{obj}' }},
            hovermode: 'closest',
            showlegend: true,
            legend: {{ x: 1, y: 1, xanchor: 'right' }}
        }};
        
        Plotly.newPlot('convergence-plot', convergenceData, convergenceLayout, {{responsive: true}});
        """

    def _generate_pareto_plot_js(self) -> str:
        """Generate JavaScript for Pareto front plot."""
        if not self.data.is_multi_objective or len(self.data.objectives) < 2:
            return ""

        obj1, obj2 = self.data.objectives[0], self.data.objectives[1]

        # All trials
        all_x = []
        all_y = []
        for trial in self.data.trials:
            x = trial.get("objectives", {}).get(obj1)
            y = trial.get("objectives", {}).get(obj2)
            if x is not None and y is not None:
                all_x.append(x)
                all_y.append(y)

        # Pareto trials
        pareto_x = []
        pareto_y = []
        for trial in self.data.pareto_trials:
            x = trial.get("objectives", {}).get(obj1)
            y = trial.get("objectives", {}).get(obj2)
            if x is not None and y is not None:
                pareto_x.append(x)
                pareto_y.append(y)

        return f"""
        var paretoData = [
            {{
                x: {json.dumps(all_x)},
                y: {json.dumps(all_y)},
                mode: 'markers',
                type: 'scatter',
                name: 'All Trials',
                marker: {{ color: 'rgba(156, 163, 175, 0.5)', size: 6 }}
            }},
            {{
                x: {json.dumps(pareto_x)},
                y: {json.dumps(pareto_y)},
                mode: 'markers',
                type: 'scatter',
                name: 'Pareto Front',
                marker: {{ color: 'rgb(239, 68, 68)', size: 10, symbol: 'diamond' }}
            }}
        ];
        
        var paretoLayout = {{
            title: '',
            xaxis: {{ title: '{obj1}' }},
            yaxis: {{ title: '{obj2}' }},
            hovermode: 'closest',
            showlegend: true
        }};
        
        Plotly.newPlot('pareto-plot', paretoData, paretoLayout, {{responsive: true}});
        """

    def _generate_importance_plot_js(self) -> str:
        """Generate JavaScript for parameter importance plot."""
        if not self.data.trials or not self.data.design_variables:
            return "// No data for importance plot"

        # Calculate simple correlation-based importance
        obj = self.data.objectives[0] if self.data.objectives else "objective"

        importances = []
        for dv in self.data.design_variables:
            param_values = []
            obj_values = []

            for trial in self.data.trials:
                p = trial.get("params", {}).get(dv)
                o = trial.get("objectives", {}).get(obj)

                if p is not None and o is not None and not np.isinf(o):
                    param_values.append(p)
                    obj_values.append(o)

            if len(param_values) > 2:
                corr = abs(np.corrcoef(param_values, obj_values)[0, 1])
                importances.append(corr if not np.isnan(corr) else 0)
            else:
                importances.append(0)

        # Sort by importance
        sorted_indices = np.argsort(importances)[::-1]
        sorted_dvs = [self.data.design_variables[i] for i in sorted_indices]
        sorted_imp = [importances[i] for i in sorted_indices]

        return f"""
        var importanceData = [{{
            x: {json.dumps(sorted_imp)},
            y: {json.dumps(sorted_dvs)},
            type: 'bar',
            orientation: 'h',
            marker: {{ color: 'rgb(99, 102, 241)' }}
        }}];
        
        var importanceLayout = {{
            title: 'Parameter Importance',
            xaxis: {{ title: 'Correlation with Objective' }},
            yaxis: {{ automargin: true }},
            margin: {{ l: 120 }}
        }};
        
        Plotly.newPlot('importance-plot', importanceData, importanceLayout, {{responsive: true}});
        """

    def _generate_distribution_plot_js(self) -> str:
        """Generate JavaScript for parameter distribution plot."""
        if not self.data.trials or not self.data.design_variables:
            return "// No data for distribution plot"

        # Use first design variable
        dv = self.data.design_variables[0]
        values = [
            t.get("params", {}).get(dv)
            for t in self.data.trials
            if t.get("params", {}).get(dv) is not None
        ]

        return f"""
        var distData = [{{
            x: {json.dumps(values)},
            type: 'histogram',
            marker: {{ color: 'rgb(34, 197, 94)' }},
            nbinsx: 20
        }}];
        
        var distLayout = {{
            title: 'Distribution: {dv}',
            xaxis: {{ title: '{dv}' }},
            yaxis: {{ title: 'Count' }}
        }};
        
        Plotly.newPlot('distribution-plot', distData, distLayout, {{responsive: true}});
        """

    def _generate_parallel_plot_js(self) -> str:
        """Generate JavaScript for parallel coordinates plot."""
        if not self.data.trials or not self.data.design_variables:
            return "// No data for parallel plot"

        obj = self.data.objectives[0] if self.data.objectives else "objective"

        # Build dimensions
        dimensions = []

        for dv in self.data.design_variables[:6]:  # Limit to 6 DVs
            values = [t.get("params", {}).get(dv, 0) for t in self.data.trials]
            bounds = self.data.dv_bounds.get(dv, (min(values), max(values)))

            dimensions.append({"label": dv[:15], "values": values, "range": list(bounds)})

        # Add objective as color dimension
        obj_values = [t.get("objectives", {}).get(obj, 0) for t in self.data.trials]

        return f"""
        var parallelData = [{{
            type: 'parcoords',
            line: {{
                color: {json.dumps(obj_values)},
                colorscale: 'Viridis',
                showscale: true,
                colorbar: {{ title: '{obj}' }}
            }},
            dimensions: {json.dumps(dimensions)}
        }}];
        
        var parallelLayout = {{
            title: ''
        }};
        
        Plotly.newPlot('parallel-plot', parallelData, parallelLayout, {{responsive: true}});
        """

    def _save_figures(self, output_dir: Path) -> None:
        """Save static figures for PDF export."""
        figures_dir = output_dir / "figures"
        figures_dir.mkdir(exist_ok=True)

        # Note: Static image export requires kaleido
        # For now, we just create the directory structure
        logger.info(f"Figures directory: {figures_dir}")

    def _save_data_exports(self, output_dir: Path) -> None:
        """Save data exports (CSV, JSON)."""
        data_dir = output_dir / "data"
        data_dir.mkdir(exist_ok=True)

        # Save all trials as JSON
        with open(data_dir / "all_trials.json", "w") as f:
            json.dump(self.data.trials, f, indent=2, default=str)

        # Save as CSV
        self._save_trials_csv(data_dir / "all_trials.csv")

        # Save summary
        summary = {
            "study_name": self.data.study_name,
            "n_trials": self.data.n_trials,
            "n_successful": self.data.n_successful,
            "design_variables": self.data.design_variables,
            "objectives": self.data.objectives,
            "best_values": self.data.best_values,
            "total_runtime_seconds": self.data.total_runtime_seconds,
        }

        with open(data_dir / "summary.json", "w") as f:
            json.dump(summary, f, indent=2)

        logger.info(f"Data exports saved to: {data_dir}")

    def _save_trials_csv(self, csv_path: Path) -> None:
        """Save trials as CSV file."""
        if not self.data.trials:
            return

        # Build CSV content
        lines = []

        # Header
        headers = ["trial", "success"]
        headers.extend(self.data.design_variables)
        headers.extend(self.data.objectives)
        lines.append(",".join(headers))

        # Rows
        for trial in self.data.trials:
            row = [
                str(trial.get("number", "")),
                str(trial.get("success", True)),
            ]

            for dv in self.data.design_variables:
                val = trial.get("params", {}).get(dv, "")
                row.append(f"{val:.6f}" if isinstance(val, (int, float)) else str(val))

            for obj in self.data.objectives:
                val = trial.get("objectives", {}).get(obj, "")
                row.append(f"{val:.6f}" if isinstance(val, (int, float)) else str(val))

            lines.append(",".join(row))

        csv_path.write_text("\n".join(lines))

    def _generate_pdf(self, output_dir: Path) -> Optional[Path]:
        """Generate PDF version of the report."""
        # This would use playwright or weasyprint
        # For now, we rely on browser print functionality
        logger.info("PDF export available via browser print (Ctrl+P)")
        return None

    def _format_duration(self, seconds: float) -> str:
        """Format duration in human-readable form."""
        if seconds < 60:
            return f"{seconds:.0f}s"
        elif seconds < 3600:
            return f"{seconds / 60:.0f}m"
        else:
            return f"{seconds / 3600:.1f}h"


def generate_report(study_dir: Path, output_dir: Path = None) -> Path:
    """
    Convenience function to generate a report.

    Args:
        study_dir: Path to study directory
        output_dir: Output directory (optional)

    Returns:
        Path to generated report
    """
    generator = HTMLReportGenerator(study_dir)
    return generator.generate(output_dir)