ff-performance-tests/py/gen_data.py

import sys
from argparse import ArgumentParser
from pathlib import Path
from typing import Sequence

import numpy as np


THIS_DIR = Path(__file__).parent
DEFAULT_DATA_DIR = Path(THIS_DIR, '..', 'data')

INPUTS_FILE_NAME = 'inputs'
WEIGHTS_FILE_NAME = 'weights'
BIASES_FILE_NAME = 'biases'

RNG = np.random.default_rng()


def extension_with_dot(string: str) -> str:
    string = string.strip()
    if not string:
        return string
    return string if string.startswith('.') else '.' + string


def parse_cli(args: list[str] = None) -> dict:
    parser = ArgumentParser(description="Create test data files (input vector, weight matrices, and bias vectors).")
    parser.add_argument(
        'num_inputs',
        type=int,
        metavar='inputs',
        help="Number of input dimensions. Random values are generated from a uniform distribution between 0.0 and 1.0."
    )
    parser.add_argument(
        'num_neurons',
        nargs='+',
        type=int,
        metavar='neurons',
        help="Number of neurons in a layer. A weights file and a biases file will be created for each value passed. "
             "Random values are generated from a uniform distribution between -1.0 and 1.0."
    )
    parser.add_argument(
        '-d', '--directory',
        type=Path,
        default=DEFAULT_DATA_DIR,
        help=f"Target directory to create the generated files in. Defaults to '{DEFAULT_DATA_DIR}'."
    )
    parser.add_argument(
        '-e', '--file-extension',
        type=extension_with_dot,
        default='.csv',
        help="File extension to use for the generated file names. Defaults to '.csv'."
    )
    parser.add_argument(
        '--fmt',
        default='%f',
        help="Passed as the `fmt` parameter to numpy's `savetxt` function. Defaults to '%%f'. "
             "(https://numpy.org/doc/stable/reference/generated/numpy.savetxt.html)"
    )
    parser.add_argument(
        '--delimiter',
        default=',',
        help="Passed as the `delimiter` parameter to numpy's `savetxt` function. Defaults to ','. "
             "(https://numpy.org/doc/stable/reference/generated/numpy.savetxt.html)"
    )
    parser.add_argument(
        '-q', '--quiet',
        action='store_true',
        help="If this flag is set, no additional info is printed throughout the script."
    )
    parser.add_argument(
        '-Y', '--yes',
        action='store_true',
        help="If this flag is set, confirmation is assumed throughout the script."
    )
    return vars(parser.parse_args(args))


def prepare_directory(directory: Path, file_extension: str, yes: bool = False, quiet: bool = False) -> None:
    directory.mkdir(exist_ok=True)
    existing_files = list(directory.glob(f'*{file_extension}'))
    if existing_files:
        if yes:
            delete = 'y'
        else:
            delete = input(f"{len(existing_files)} existing files with '{file_extension}' extension "
                           f"found in {directory}. Delete these first? [Y/n] ").strip().lower() or 'y'
        if delete == 'y':
            for file_path in existing_files:
                file_path.unlink()
            if not quiet:
                print("Deleted existing files.")
        elif delete != 'n':
            raise ValueError


def generate_inputs(num_inputs: int, directory: Path, file_extension: str, quiet: bool = False, **kwargs) -> None:
    inputs_file = Path(directory, INPUTS_FILE_NAME).with_suffix(file_extension)
    input_vector = RNG.uniform(0.0, 1.0, size=num_inputs)
    np.savetxt(inputs_file, input_vector, **kwargs)
    if not quiet:
        print(inputs_file, 'x'.join(str(n) for n in input_vector.shape))


def generate_layers(num_inputs: int, num_neurons: Sequence[int], directory: Path, file_extension: str, 
                    quiet: bool = False, **kwargs) -> None:
    weights_file = Path(directory, WEIGHTS_FILE_NAME).with_suffix(file_extension)
    biases_file = Path(directory, BIASES_FILE_NAME).with_suffix(file_extension)
    dim_before = num_inputs
    for i, dim in enumerate(num_neurons, start=1):
        weight_matrix = RNG.uniform(-1.0, 1.0, size=(dim, dim_before))
        bias_vector = RNG.uniform(-1.0, 1.0, size=dim)
        weights_file = weights_file.with_stem(f'{WEIGHTS_FILE_NAME}{i:02}')
        biases_file = biases_file.with_stem(f'{BIASES_FILE_NAME}{i:02}')
        np.savetxt(weights_file, weight_matrix, **kwargs)
        np.savetxt(biases_file, bias_vector, **kwargs)
        if not quiet:
            print(weights_file, 'x'.join(str(n) for n in weight_matrix.shape))
            print(biases_file, 'x'.join(str(n) for n in bias_vector.shape))
        dim_before = dim


def generate_data(num_inputs: int, num_neurons: Sequence[int], directory: Path, file_extension: str, 
                  quiet: bool = False, yes: bool = False, **kwargs) -> None:
    prepare_directory(directory, file_extension, quiet, yes)
    if not quiet:
        print("Creating new test data...")
    generate_inputs(num_inputs, directory, file_extension, quiet, **kwargs)
    generate_layers(num_inputs, num_neurons, directory, file_extension, quiet, **kwargs)


def main() -> None:
    generate_data(**parse_cli())


if __name__ == '__main__':
    main()