utils.py

import torch
import joblib
import numpy as np
from io import BytesIO
from pathlib import Path
from typing import Tuple, Optional
from huggingface_hub import HfFileSystem


def load_kmeans_model(km_path: str) -> Tuple[torch.Tensor, torch.Tensor]:
    """Load the k-means model."""
    fs = HfFileSystem()

    if Path(km_path).exists():
        km_file = Path(km_path)
    elif fs.exists(km_path):
        km_file = BytesIO(fs.read_bytes(km_path))
    else:
        raise FileNotFoundError(f"K-means model not found at {km_path}")

    kmeans_model = joblib.load(km_file)
    C = torch.from_numpy(kmeans_model.cluster_centers_.transpose())
    Cnorm = C.pow(2).sum(0, keepdim=True)
    return C, Cnorm


def find_runs(x: np.ndarray) -> Tuple[np.ndarray, np.ndarray, np.ndarray]:
    """Find runs of consecutive items in an array."""

    # ensure array
    x = np.asanyarray(x)
    if x.ndim != 1:
        raise ValueError("only 1D array supported")
    n = x.shape[0]

    # handle empty array
    if n == 0:
        return np.array([]), np.array([]), np.array([])
    else:
        # find run starts
        loc_run_start = np.empty(n, dtype=bool)
        loc_run_start[0] = True
        np.not_equal(x[:-1], x[1:], out=loc_run_start[1:])
        run_starts = np.nonzero(loc_run_start)[0]

        # find run values
        run_values = x[loc_run_start]

        # find run lengths
        run_lengths = np.diff(np.append(run_starts, n))

        return run_values, run_starts, run_lengths


def compute_mask_indices(
    shape: Tuple[int, int],
    padding_mask: Optional[torch.Tensor],
    mask_prob: float,
    mask_length: int,
    mask_type: str = "static",
    mask_other: float = 0.0,
    min_masks: int = 0,
    no_overlap: bool = False,
    min_space: int = 0,
) -> np.ndarray:
    """
    Computes random mask spans for a given shape
    Args:
        shape: the the shape for which to compute masks.
            should be of size 2 where first element is batch size and 2nd is timesteps
        padding_mask: optional padding mask of the same size as shape, which will prevent masking padded elements
        mask_prob: probability for each token to be chosen as start of the span to be masked. this will be multiplied by
            number of timesteps divided by length of mask span to mask approximately this percentage of all elements.
            however due to overlaps, the actual number will be smaller (unless no_overlap is True)
        mask_type: how to compute mask lengths
            static = fixed size
            uniform = sample from uniform distribution [mask_other, mask_length*2]
            normal = sample from normal distribution with mean mask_length and stdev mask_other. mask is min 1 element
            poisson = sample from possion distribution with lambda = mask length
        min_masks: minimum number of masked spans
        no_overlap: if false, will switch to an alternative recursive algorithm that prevents spans from overlapping
        min_space: only used if no_overlap is True, this is how many elements to keep unmasked between spans
    """
    bsz, all_sz = shape
    mask = np.full((bsz, all_sz), False)

    all_num_mask = int(
        # add a random number for probabilistic rounding
        mask_prob * all_sz / float(mask_length)
        + np.random.rand()
    )

    all_num_mask = max(min_masks, all_num_mask)

    mask_idcs = []
    for i in range(bsz):
        if padding_mask is not None:
            sz = all_sz - padding_mask[i].long().sum().item()
            num_mask = int(
                # add a random number for probabilistic rounding
                mask_prob * sz / float(mask_length)
                + np.random.rand()
            )
            num_mask = max(min_masks, num_mask)
        else:
            sz = all_sz
            num_mask = all_num_mask

        if mask_type == "static":
            lengths = np.full(num_mask, mask_length)
        elif mask_type == "uniform":
            lengths = np.random.randint(mask_other, mask_length * 2 + 1, size=num_mask)
        elif mask_type == "normal":
            lengths = np.random.normal(mask_length, mask_other, size=num_mask)
            lengths = [max(1, int(round(x))) for x in lengths]
        elif mask_type == "poisson":
            lengths = np.random.poisson(mask_length, size=num_mask)
            lengths = [int(round(x)) for x in lengths]
        else:
            raise Exception("unknown mask selection " + mask_type)

        if sum(lengths) == 0:
            lengths[0] = min(mask_length, sz - 1)

        if no_overlap:
            mask_idc = []

            def arrange(s, e, length, keep_length):
                span_start = np.random.randint(s, e - length)
                mask_idc.extend(span_start + i for i in range(length))

                new_parts = []
                if span_start - s - min_space >= keep_length:
                    new_parts.append((s, span_start - min_space + 1))
                if e - span_start - keep_length - min_space > keep_length:
                    new_parts.append((span_start + length + min_space, e))
                return new_parts

            parts = [(0, sz)]
            min_length = min(lengths)
            for length in sorted(lengths, reverse=True):
                lens = np.fromiter(
                    (e - s if e - s >= length + min_space else 0 for s, e in parts),
                    np.int,
                )
                l_sum = np.sum(lens)
                if l_sum == 0:
                    break
                probs = lens / np.sum(lens)
                c = np.random.choice(len(parts), p=probs)
                s, e = parts.pop(c)
                parts.extend(arrange(s, e, length, min_length))
            mask_idc = np.asarray(mask_idc)
        else:
            min_len = min(lengths)
            if sz - min_len <= num_mask:
                min_len = sz - num_mask - 1

            mask_idc = np.random.choice(sz - min_len, num_mask, replace=False)

            mask_idc = np.asarray(
                [
                    mask_idc[j] + offset
                    for j in range(len(mask_idc))
                    for offset in range(lengths[j])
                ]
            )

        mask_idcs.append(np.unique(mask_idc[mask_idc < sz]))

    min_len = min([len(m) for m in mask_idcs])
    batch_indexes, starts, ends = [], [], []
    for i, mask_idc in enumerate(mask_idcs):
        if len(mask_idc) > min_len:
            mask_idc = np.random.choice(mask_idc, min_len, replace=False)
        mask[i, mask_idc] = True
        vals, run_starts, run_lengths = find_runs(mask[i])
        start_indices, lengths = run_starts[vals == True], run_lengths[vals == True]
        starts.append(start_indices)
        ends.append(start_indices + lengths)
        batch_indexes.append(np.zeros([len(start_indices)]) + i)
    return (
        mask,
        np.concatenate(starts).astype(np.int64),
        np.concatenate(ends).astype(np.int64),
        np.concatenate(batch_indexes).astype(np.int64),
    )