Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Remove ray lazy loader. #595

Merged
merged 4 commits into from
Feb 27, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 2 additions & 4 deletions data_juicer/core/ray_data.py
Original file line number Diff line number Diff line change
Expand Up @@ -5,19 +5,17 @@
from typing import Any, Dict, List, Literal, Optional, Union

import pyarrow
import ray.data as rd
import ray.data.read_api as ds
from loguru import logger

from data_juicer import cuda_device_count
from data_juicer.core.data import DJDataset
from data_juicer.ops import Deduplicator, Filter, Mapper
from data_juicer.ops.base_op import TAGGING_OPS
from data_juicer.utils.constant import Fields
from data_juicer.utils.lazy_loader import LazyLoader
from data_juicer.utils.process_utils import calculate_np

rd = LazyLoader('rd', 'ray.data')
ds = LazyLoader('ds', 'ray.data.read_api')


def get_abs_path(path, dataset_dir):
full_path = os.path.abspath(os.path.join(dataset_dir, path))
Expand Down
5 changes: 1 addition & 4 deletions data_juicer/core/ray_executor.py
Original file line number Diff line number Diff line change
Expand Up @@ -2,19 +2,16 @@
import shutil
import time

import ray
from loguru import logger

from data_juicer.config import init_configs
from data_juicer.core.ray_data import RayDataset
from data_juicer.ops import load_ops
from data_juicer.ops.op_fusion import fuse_operators
from data_juicer.utils.lazy_loader import LazyLoader

from .adapter import Adapter

ray = LazyLoader('ray', 'ray')
rd = LazyLoader('rd', 'ray.data')


class TempDirManager:

Expand Down
5 changes: 1 addition & 4 deletions data_juicer/format/empty_formatter.py
Original file line number Diff line number Diff line change
@@ -1,14 +1,11 @@
from typing import List

import pandas as pd
import ray
from datasets import Dataset, Features, Value

from data_juicer.utils.lazy_loader import LazyLoader

from .formatter import FORMATTERS, BaseFormatter

ray = LazyLoader('ray', 'ray')


@FORMATTERS.register_module()
class EmptyFormatter(BaseFormatter):
Expand Down
2 changes: 1 addition & 1 deletion data_juicer/utils/unittest_utils.py
Original file line number Diff line number Diff line change
Expand Up @@ -3,14 +3,14 @@
import unittest

import numpy
import ray.data as rd

from data_juicer import is_cuda_available
from data_juicer.core.data import DJDataset, NestedDataset
from data_juicer.core.ray_data import RayDataset
from data_juicer.utils.lazy_loader import LazyLoader
from data_juicer.utils.model_utils import free_models

rd = LazyLoader('rd', 'ray.data')
transformers = LazyLoader('transformers', 'transformers')

CLEAR_MODEL = False
Expand Down
Loading