Source code for mfml_qc.datasets

import os
import numpy as np
from typing import Dict, Any
from .representations import generate_coulomb_matrices, compute_flat_coulomb


[docs] def load_benzene_data(data_dir: str = None) -> Dict[str, Any]: """ Helper utility to load and parse the built-in Benzene trajectory dataset. This function reads the pre-computed energy and time cost CSV files, and either loads the cached Coulomb matrices or generates them dynamically from the provided XYZ trajectory file. Parameters ---------- data_dir : str, optional Path to the benzene data directory. If None, it dynamically resolves the path relative to the installed package's directory (assuming the standard 'data/benzene' repository layout). Default is None. Returns ------- dict A dictionary containing the parsed dataset components: * ``'X_CM'`` (np.ndarray): Flattened Coulomb matrices (shape: 15000, 36). * ``'energies'`` (np.ndarray): Raw energies extracted from the CSV data. * ``'timecosts'`` (np.ndarray): Time costs extracted from the CSV data. * ``'columns'`` (list of str): List of string names corresponding to each column. Raises ------ FileNotFoundError If the required 'energies.csv' file is not found at the resolved path, indicating the data has not been downloaded or placed correctly. """ if data_dir is None: # Resolve path relative to the installed package directory # package lives in src/mfml_qc/ so we go two levels up to find the root 'data/benzene' data_dir = os.path.abspath( os.path.join(os.path.dirname(__file__), "..", "..", "data", "benzene") ) xyz_path = os.path.join(data_dir, "traj.xyz") csv_path = os.path.join(data_dir, "energies.csv") time_path = os.path.join(data_dir, "timecosts.csv") cm_cache = os.path.join(data_dir, "X_CM.npy") if not os.path.exists(csv_path): raise FileNotFoundError( f"Benzene dataset not found at {data_dir}. " "Ensure you have placed the files in your project's 'data/benzene' directory.\nIf you have not installed the dataset in the pip installation, please do so." ) # Generate CM or load if already generated and saved if os.path.exists(cm_cache): X_CM = np.load(cm_cache) else: X_CM = generate_coulomb_matrices(xyz_path, save_path=cm_cache) # Energies and Time costs energies = np.genfromtxt(csv_path, delimiter=",", skip_header=1) timecosts = np.genfromtxt(time_path, delimiter=",", skip_header=1) # Define exact columns representing the CSV structure columns = [ "Time", "ZINDO", "LC-DFTB", "STO-3G", "3-21G", "6-31G", "def2-SVP", "def2-TZVP", "def2-QZVP", ] return { "X_CM": X_CM, "energies": energies, "timecosts": timecosts, "columns": columns, }
[docs] def load_nitrophenol_data(data_dir: str = None) -> Dict[str, Any]: """ Load and parse the built-in QeMFi nitrophenol dataset. The QeMFi dataset contains multifidelity electronic structure properties for 15,000 MD geometries of nitrophenol at 5 SCF fidelity levels (STO-3G, 3-21G, 6-31G, def2-SVP, def2-TZVP). Reference: Vinod et al., J. Chem. Phys. (2024). Parameters ---------- data_dir : str, optional Path to the nitrophenol data directory. If None, resolves the path relative to the installed package's directory (assuming the standard 'data/nitrophenol' repository layout). Default is None. Returns ------- dict A dictionary containing the parsed dataset components: * ``'R'`` (np.ndarray): Cartesian coordinates, shape (15000, 15, 3). * ``'Z'`` (np.ndarray): Atomic numbers, shape (15,). * ``'SCF'`` (np.ndarray): SCF energies at 5 fidelities, shape (15000, 5). * ``'DPe'`` (np.ndarray): Electronic dipole moments, shape (15000, 5, 3). * ``'X_CM'`` (np.ndarray): Flattened Coulomb matrices, shape (15000, 120). * ``'fidelities'`` (list of str): Fidelity level names. * ``'ID'`` (np.ndarray, optional): WS22 geometry indices, shape (15000,). Raises ------ FileNotFoundError If the required data file is not found at the resolved path. """ if data_dir is None: data_dir = os.path.abspath( os.path.join(os.path.dirname(__file__), "..", "..", "data", "nitrophenol") ) npz_path = os.path.join(data_dir, "QeMFi_nitrophenol.npz") cm_cache = os.path.join(data_dir, "X_CM.npy") if not os.path.exists(npz_path): raise FileNotFoundError( f"QeMFi nitrophenol dataset not found at {data_dir}. " "Ensure you have placed QeMFi_nitrophenol.npz in your project's " "'data/nitrophenol' directory." ) data = np.load(npz_path, allow_pickle=True) R = data["R"] Z = data["Z"] if os.path.exists(cm_cache): X_CM = np.load(cm_cache) else: n_geom = R.shape[0] n_feat = Z.shape[0] * (Z.shape[0] + 1) // 2 X_CM = np.zeros((n_geom, n_feat)) for i in range(n_geom): X_CM[i] = compute_flat_coulomb(Z=Z, R=R[i]) np.save(cm_cache, X_CM) fidelities = ["STO-3G", "3-21G", "6-31G", "def2-SVP", "def2-TZVP"] result = { "R": R, "Z": Z, "SCF": data["SCF"], "DPe": data["DPe"], "X_CM": X_CM, "fidelities": fidelities, } if "ID" in data.files: result["ID"] = data["ID"] return result