#!/usr/bin/env python3
"""Load one released endpoint and average its five seed models.

The checkpoint directory is self-contained. Fingerprints are computed here.
PaDEL 3D columns, the GIN embedding, and the MiniMol embedding are inputs:
their encoder weights are not part of this release.

  from predict import EndpointModel
  model = EndpointModel.from_pretrained(".", "pgp_broccatelli")
  model.predict(["CCO", "c1ccccc1"])
"""
from __future__ import annotations

import json
from pathlib import Path

import numpy as np


def _read_json(path: Path) -> dict:
    return json.loads(path.read_text())


def invert_y(raw: np.ndarray, state: dict) -> np.ndarray:
    y = np.asarray(raw, dtype=float).reshape(-1) * float(state["scale"]) + float(state["mean"])
    if state["log"]:
        y = np.power(10.0, y) - 1.0
    return y + float(state["offset"])


def _mlp(x: np.ndarray, head: dict) -> np.ndarray:
    """One hidden ReLU layer, matching the exported scikit-learn head."""
    hidden = np.maximum(0.0, x @ head["coef_0"] + head["intercept_0"])
    out = hidden @ head["coef_1"] + head["intercept_1"]
    out = np.asarray(out, dtype=float)
    if out.ndim == 1 or out.shape[-1] == 1:
        return out.reshape(-1)
    if head["kind"] != "classifier":
        raise RuntimeError("regressor head has more than one output")
    shifted = out - out.max(axis=1, keepdims=True)
    exp = np.exp(shifted)
    return (exp / exp.sum(axis=1, keepdims=True))[:, 1]


def head_predict(minimol: np.ndarray, head: dict) -> np.ndarray:
    pred = np.full(len(minimol), np.nan, dtype=float)
    ok = np.isfinite(minimol).all(axis=1)
    if not ok.any():
        return pred
    scaled = (minimol[ok] - head["x_mean"]) / head["x_scale"]
    raw = _mlp(scaled, head)
    if head["kind"] == "classifier":
        if str(head["activation"]) == "logistic" and head["coef_1"].shape[-1] == 1:
            raw = 1.0 / (1.0 + np.exp(-raw))
        pred[ok] = raw
        return pred
    pred[ok] = invert_y(raw, head)
    return pred


def mix(catboost: np.ndarray, head: np.ndarray, weight: float) -> np.ndarray:
    blended = (1.0 - weight) * catboost + weight * head
    missing = ~np.isfinite(head)
    blended[missing] = catboost[missing]
    return blended


def fingerprints(smiles: list[str], descriptor_names: list[str]) -> np.ndarray:
    """Morgan count r=2 1024, Avalon count 1024, ErG 315, then the named RDKit descriptors."""
    from rdkit import Chem, RDLogger
    from rdkit.Avalon.pyAvalonTools import GetAvalonCountFP
    from rdkit.Chem import DataStructs, rdReducedGraphs
    from rdkit.Chem.rdMolDescriptors import GetHashedMorganFingerprint
    from rdkit.ML.Descriptors.MoleculeDescriptors import MolecularDescriptorCalculator

    RDLogger.DisableLog("rdApp.*")
    calculator = MolecularDescriptorCalculator(descriptor_names)
    rows = []
    for one in smiles:
        mol = Chem.MolFromSmiles(one) if isinstance(one, str) else None
        if mol is None:
            rows.append(None)
            continue
        morgan = np.zeros((0,), dtype=np.int32)
        DataStructs.ConvertToNumpyArray(
            GetHashedMorganFingerprint(mol, nBits=1024, radius=2), morgan
        )
        avalon = np.zeros((0,), dtype=np.int32)
        DataStructs.ConvertToNumpyArray(GetAvalonCountFP(mol, nBits=1024), avalon)
        erg = np.asarray(rdReducedGraphs.GetErGFingerprint(mol), dtype=float)
        desc = np.asarray(calculator.CalcDescriptors(mol), dtype=float)
        rows.append(np.concatenate([morgan, avalon, erg, desc]).astype(float))
    width = next(len(row) for row in rows if row is not None)
    out = np.full((len(smiles), width), np.nan, dtype=float)
    for i, row in enumerate(rows):
        if row is not None:
            out[i] = row
    return out


def _as_2d(block, width: int, name: str, n_rows: int) -> np.ndarray:
    array = np.asarray(block, dtype=float)
    if array.ndim != 2 or array.shape != (n_rows, width):
        raise ValueError(f"{name} must have shape ({n_rows}, {width}), got {array.shape}")
    return array


class EndpointModel:
    def __init__(self, root: Path, endpoint: str):
        self.root = Path(root)
        self.endpoint = endpoint
        self.config = _read_json(self.root / endpoint / "config.json")
        self.spec = _read_json(self.root / "feature_spec.json")
        self.endpoint_spec = self.spec["endpoints"][endpoint]
        if self.config["endpoint"] != endpoint:
            raise RuntimeError(f"{endpoint} config says {self.config['endpoint']}")

    @classmethod
    def from_pretrained(cls, root: str | Path, endpoint: str) -> "EndpointModel":
        return cls(Path(root), endpoint)

    def _padel_block(self, padel, n_rows: int) -> np.ndarray:
        n_keep = int(self.config["n_3d"])
        if n_keep == 0:
            if padel is not None:
                raise ValueError(f"{self.endpoint} does not use PaDEL columns")
            return np.zeros((n_rows, 0), dtype=float)
        if padel is None:
            raise ValueError(
                f"{self.endpoint} expects PaDEL 3D columns. "
                "Pass an array of shape (n, 431) in feature_spec padel_3d column order, "
                "or an array already reduced to this endpoint's columns."
            )
        if hasattr(padel, "columns"):
            names = list(self.endpoint_spec["padel_columns"])
            missing = [name for name in names if name not in padel.columns]
            if missing:
                raise ValueError(f"PaDEL frame is missing {missing[:5]}")
            return np.asarray(padel[names], dtype=float)
        array = np.asarray(padel, dtype=float)
        if array.ndim != 2 or array.shape[0] != n_rows:
            raise ValueError(f"padel must have {n_rows} rows, got {getattr(array, 'shape', None)}")
        canonical = len(self.spec["padel_3d"]["columns"])
        if array.shape[1] == canonical:
            index = self.endpoint_spec["padel_index"]
            return np.ascontiguousarray(array[:, index])
        if array.shape[1] == n_keep:
            return array
        raise ValueError(
            f"padel second dimension must be {canonical} or {n_keep}, got {array.shape[1]}"
        )

    def features(self, smiles: list[str], padel=None, gin=None, minimol=None) -> np.ndarray:
        fp = fingerprints(smiles, self.spec["rdkit_descriptors"])
        if fp.shape[1] != int(self.config["n_fingerprint"]):
            raise RuntimeError(f"fingerprint width {fp.shape[1]} != {self.config['n_fingerprint']}")
        blocks = [fp, self._padel_block(padel, len(smiles))]
        if self.config["gin"]:
            if gin is None:
                raise ValueError(f"{self.endpoint} expects a GIN embedding of shape (n, 300)")
            blocks.append(_as_2d(gin, 300, "gin", len(smiles)))
        if self.config["minimol_concat"]:
            if minimol is None:
                raise ValueError(f"{self.endpoint} expects a MiniMol embedding of shape (n, 512)")
            blocks.append(_as_2d(minimol, 512, "minimol", len(smiles)))
        x = np.ascontiguousarray(np.hstack(blocks))
        if x.shape[1] != int(self.config["n_features"]):
            raise RuntimeError(f"feature width {x.shape[1]} != {self.config['n_features']}")
        return x

    def predict_features(self, x: np.ndarray, minimol=None) -> np.ndarray:
        from catboost import CatBoostClassifier, CatBoostRegressor

        x = np.asarray(x, dtype=float)
        if x.ndim != 2 or x.shape[1] != int(self.config["n_features"]):
            raise ValueError(f"x must have shape (n, {self.config['n_features']})")
        weight = float(self.config["blend_weight"])
        if weight > 0.0:
            minimol = _as_2d(minimol, 512, "minimol", len(x))
        task = self.config["task"]
        klass = CatBoostRegressor if task == "regression" else CatBoostClassifier
        seeds = []
        for seed in self.config["seeds"]:
            folder = self.root / self.endpoint / f"seed{seed}"
            model = klass()
            model.load_model(str(folder / "catboost.cbm"))
            if task == "regression":
                pred = invert_y(model.predict(x), _read_json(folder / "y_scaler.json"))
            else:
                pred = np.asarray(model.predict_proba(x)[:, 1], dtype=float)
            if weight > 0.0:
                head = dict(np.load(folder / "minimol_head.npz"))
                pred = mix(pred, head_predict(minimol, head), weight)
            seeds.append(pred)
        return np.mean(seeds, axis=0)

    def predict(self, smiles, padel=None, gin=None, minimol=None) -> np.ndarray:
        if isinstance(smiles, str):
            smiles = [smiles]
        smiles = list(smiles)
        x = self.features(smiles, padel=padel, gin=gin, minimol=minimol)
        return self.predict_features(x, minimol=minimol)