src/data/generate_dataset.py

"""Dataset generation pipeline using Latin Hypercube Sampling.

Generates 100K structural analysis samples across beams, plates, and pressure
vessels using analytical closed-form solutions. LHS provides better coverage of
the design space than random sampling — a deliberate choice from Design of
Experiments (DoE) methodology.

Usage:
    python -m src.data.generate_dataset --config configs/data_generation.yaml
"""

import argparse
import hashlib
import logging
import uuid
from pathlib import Path
from typing import Any

import numpy as np
import pandas as pd
import yaml
from scipy.stats.qmc import LatinHypercube

from src.data.schema import ProblemFamily, SafetyCategory
from src.data.solvers.beam import BEAM_SOLVERS
from src.data.solvers.plate import PLATE_SOLVERS
from src.data.solvers.vessel import VESSEL_SOLVERS

logger = logging.getLogger(__name__)


def _lhs_sample(
    n_samples: int,
    param_ranges: dict[str, dict],
    seed: int,
) -> dict[str, np.ndarray]:
    """Generate Latin Hypercube Samples and map to physical parameter ranges.

    Log-uniform parameters are sampled uniform in log-space then exponentiated,
    which is critical because engineering quantities span orders of magnitude
    (e.g., elastic modulus: 1 GPa to 400 GPa).
    """
    param_names = list(param_ranges.keys())
    n_dims = len(param_names)

    sampler = LatinHypercube(d=n_dims, seed=seed)
    unit_samples = sampler.random(n=n_samples)  # shape: (n_samples, n_dims)

    result: dict[str, np.ndarray] = {}
    for i, name in enumerate(param_names):
        spec = param_ranges[name]
        lo, hi = float(spec["min"]), float(spec["max"])
        col = unit_samples[:, i]

        if spec.get("distribution") == "log_uniform":
            log_lo, log_hi = np.log10(lo), np.log10(hi)
            result[name] = 10.0 ** (log_lo + col * (log_hi - log_lo))
        else:  # uniform
            result[name] = lo + col * (hi - lo)

    return result


def _generate_beam_samples(
    config: dict,
    global_seed: int,
) -> list[dict[str, Any]]:
    """Generate beam samples across all 6 configurations."""
    samples = []
    beam_configs = config["beam"]["configs"]
    n_per_config = config["beam"]["samples_per_config"]
    param_ranges = config["beam"]["parameters"]

    for cfg_idx, cfg in enumerate(beam_configs):
        config_id = cfg["id"]
        solver_cls = BEAM_SOLVERS[config_id]
        solver = solver_cls()

        seed = global_seed + cfg_idx
        lhs_params = _lhs_sample(n_per_config, param_ranges, seed)

        for i in range(n_per_config):
            params = {k: float(v[i]) for k, v in lhs_params.items()}

            # Select load type based on config
            if "point" in config_id:
                load_params = {
                    "point_load": params["point_load"],
                    "distributed_load": 0.0,
                }
            else:
                load_params = {
                    "point_load": 0.0,
                    "distributed_load": params["distributed_load"],
                }

            solve_params = {
                "length": params["length"],
                "width": params["width"],
                "height": params["height"],
                "elastic_modulus": params["elastic_modulus"],
                "yield_strength": params["yield_strength"],
                **load_params,
            }

            result = solver.solve(solve_params)
            b, h = params["width"], params["height"]

            samples.append({
                "sample_id": str(uuid.uuid4()),
                "problem_family": ProblemFamily.BEAM.value,
                "config_id": config_id,
                "length": params["length"],
                "width": params["width"],
                "height": params["height"],
                "inner_radius": None,
                "outer_radius": None,
                "thickness": None,
                "elastic_modulus": params["elastic_modulus"],
                "poisson_ratio": params["poisson_ratio"],
                "yield_strength": params["yield_strength"],
                "density": params["density"],
                "point_load": load_params["point_load"],
                "distributed_load": load_params["distributed_load"],
                "internal_pressure": 0.0,
                "pressure": 0.0,
                "moment_of_inertia": b * h**3 / 12.0,
                "section_modulus": b * h**2 / 6.0,
                "cross_section_area": b * h,
                "max_stress": result.max_stress,
                "max_deflection": result.max_deflection,
                "safety_factor": result.safety_factor,
                "safety_category": result.safety_category.value,
            })

        logger.info(f"Generated {n_per_config} samples for {config_id}")

    return samples


def _generate_plate_samples(
    config: dict,
    global_seed: int,
) -> list[dict[str, Any]]:
    """Generate plate samples across both configurations."""
    samples = []
    plate_configs = config["plate"]["configs"]
    n_per_config = config["plate"]["samples_per_config"]
    param_ranges = config["plate"]["parameters"]

    for cfg_idx, cfg in enumerate(plate_configs):
        config_id = cfg["id"]
        solver_cls = PLATE_SOLVERS[config_id]
        solver = solver_cls()

        seed = global_seed + 100 + cfg_idx
        lhs_params = _lhs_sample(n_per_config, param_ranges, seed)

        for i in range(n_per_config):
            params = {k: float(v[i]) for k, v in lhs_params.items()}

            solve_params = {
                "length_a": params["length_a"],
                "length_b": params["length_b"],
                "thickness": params["thickness"],
                "elastic_modulus": params["elastic_modulus"],
                "poisson_ratio": params["poisson_ratio"],
                "yield_strength": params["yield_strength"],
                "pressure": params["pressure"],
            }

            result = solver.solve(solve_params)

            samples.append({
                "sample_id": str(uuid.uuid4()),
                "problem_family": ProblemFamily.PLATE.value,
                "config_id": config_id,
                "length": params["length_a"],
                "width": params["length_b"],
                "height": None,
                "inner_radius": None,
                "outer_radius": None,
                "thickness": params["thickness"],
                "elastic_modulus": params["elastic_modulus"],
                "poisson_ratio": params["poisson_ratio"],
                "yield_strength": params["yield_strength"],
                "density": params["density"],
                "point_load": 0.0,
                "distributed_load": 0.0,
                "internal_pressure": 0.0,
                "pressure": params["pressure"],
                "moment_of_inertia": None,
                "section_modulus": None,
                "cross_section_area": None,
                "max_stress": result.max_stress,
                "max_deflection": result.max_deflection,
                "safety_factor": result.safety_factor,
                "safety_category": result.safety_category.value,
            })

        logger.info(f"Generated {n_per_config} samples for {config_id}")

    return samples


def _generate_vessel_samples(
    config: dict,
    global_seed: int,
) -> list[dict[str, Any]]:
    """Generate pressure vessel samples across both configurations."""
    samples = []
    vessel_configs = config["vessel"]["configs"]
    n_per_config = config["vessel"]["samples_per_config"]
    param_ranges = config["vessel"]["parameters"]

    for cfg_idx, cfg in enumerate(vessel_configs):
        config_id = cfg["id"]
        solver_cls = VESSEL_SOLVERS[config_id]
        solver = solver_cls()

        seed = global_seed + 200 + cfg_idx
        lhs_params = _lhs_sample(n_per_config, param_ranges, seed)

        for i in range(n_per_config):
            params = {k: float(v[i]) for k, v in lhs_params.items()}

            r_i = params["inner_radius"]
            r_o = r_i * params["radius_ratio"]

            solve_params = {
                "inner_radius": r_i,
                "outer_radius": r_o,
                "elastic_modulus": params["elastic_modulus"],
                "poisson_ratio": params["poisson_ratio"],
                "yield_strength": params["yield_strength"],
                "internal_pressure": params["internal_pressure"],
            }

            result = solver.solve(solve_params)

            samples.append({
                "sample_id": str(uuid.uuid4()),
                "problem_family": ProblemFamily.VESSEL.value,
                "config_id": config_id,
                "length": params.get("length", None) if config_id == "vessel_cylinder" else None,
                "width": None,
                "height": None,
                "inner_radius": r_i,
                "outer_radius": r_o,
                "thickness": r_o - r_i,
                "elastic_modulus": params["elastic_modulus"],
                "poisson_ratio": params["poisson_ratio"],
                "yield_strength": params["yield_strength"],
                "density": params["density"],
                "point_load": 0.0,
                "distributed_load": 0.0,
                "internal_pressure": params["internal_pressure"],
                "pressure": 0.0,
                "moment_of_inertia": None,
                "section_modulus": None,
                "cross_section_area": None,
                "max_stress": result.max_stress,
                "max_deflection": result.max_deflection,
                "safety_factor": result.safety_factor,
                "safety_category": result.safety_category.value,
            })

        logger.info(f"Generated {n_per_config} samples for {config_id}")

    return samples


def generate_dataset(config_path: str) -> pd.DataFrame:
    """Generate the full dataset from config file."""
    with open(config_path) as f:
        config = yaml.safe_load(f)

    seed = config["seed"]
    np.random.seed(seed)

    logger.info("Generating beam samples...")
    beam_samples = _generate_beam_samples(config, seed)

    logger.info("Generating plate samples...")
    plate_samples = _generate_plate_samples(config, seed)

    logger.info("Generating vessel samples...")
    vessel_samples = _generate_vessel_samples(config, seed)

    all_samples = beam_samples + plate_samples + vessel_samples
    df = pd.DataFrame(all_samples)

    logger.info(f"Total samples generated: {len(df)}")
    logger.info(f"Safety category distribution:\n{df['safety_category'].value_counts()}")

    return df


def split_and_save(df: pd.DataFrame, config_path: str) -> None:
    """Stratified split and save as Parquet files."""
    with open(config_path) as f:
        config = yaml.safe_load(f)

    output_dir = Path(config["output"]["directory"])
    output_dir.mkdir(parents=True, exist_ok=True)

    splits = config["splits"]
    train_frac = splits["train"]
    val_frac = splits["validation"]

    # Stratified split by config_id and safety_category
    df_shuffled = df.sample(frac=1.0, random_state=config["seed"]).reset_index(drop=True)

    n = len(df_shuffled)
    n_train = int(n * train_frac)
    n_val = int(n * val_frac)

    train_df = df_shuffled.iloc[:n_train]
    val_df = df_shuffled.iloc[n_train:n_train + n_val]
    test_df = df_shuffled.iloc[n_train + n_val:]

    train_df.to_parquet(output_dir / "train.parquet", index=False)
    val_df.to_parquet(output_dir / "validation.parquet", index=False)
    test_df.to_parquet(output_dir / "test.parquet", index=False)

    logger.info(f"Saved splits: train={len(train_df)}, val={len(val_df)}, test={len(test_df)}")
    logger.info(f"Output directory: {output_dir}")


def main() -> None:
    parser = argparse.ArgumentParser(description="Generate structural mechanics dataset")
    parser.add_argument("--config", default="configs/data_generation.yaml")
    args = parser.parse_args()

    logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")

    df = generate_dataset(args.config)
    split_and_save(df, args.config)


if __name__ == "__main__":
    main()