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.

Sign up for GitHub

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 DASK_DATAFRAME__QUERY_PLANNING environment variable #270

Merged
merged 2 commits into from
Oct 9, 2024
Merged

Remove DASK_DATAFRAME__QUERY_PLANNING environment variable #270

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7486eeb
remove DASK_DATAFRAME__QUERY_PLANNING False
sarahyurick Sep 30, 2024
7635e41
isort
sarahyurick Sep 30, 2024
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
3 changes: 0 additions & 3 deletions examples/translation_example.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,4 @@
import os

os.environ["DASK_DATAFRAME__QUERY_PLANNING"] = "False"
import argparse
import re
import time
from dataclasses import dataclass
Expand Down
1 change: 0 additions & 1 deletion nemo_curator/classifiers/aegis.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,6 @@
import os

os.environ["RAPIDS_NO_INITIALIZE"] = "1"
os.environ["DASK_DATAFRAME__QUERY_PLANNING"] = "False"
from dataclasses import dataclass
from functools import lru_cache
from typing import List, Optional, Union
Expand Down
2 changes: 0 additions & 2 deletions nemo_curator/classifiers/fineweb_edu.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,6 @@
import os

os.environ["RAPIDS_NO_INITIALIZE"] = "1"
os.environ["DASK_DATAFRAME__QUERY_PLANNING"] = "False"
import torch
from crossfit import op
from crossfit.backend.torch.hf.model import HFModel
Expand All @@ -23,7 +22,6 @@
from nemo_curator.classifiers.base import (
DistributedDataClassifier,
_get_suggest_memory_for_classifier,
_run_classifier_helper,
)
from nemo_curator.datasets import DocumentDataset

Expand Down
1 change: 0 additions & 1 deletion nemo_curator/scripts/semdedup/clustering.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,6 @@
import os
from datetime import datetime

os.environ["DASK_DATAFRAME__QUERY_PLANNING"] = "False"
import dask_cudf

from nemo_curator.datasets import DocumentDataset
Expand Down
2 changes: 0 additions & 2 deletions tests/test_semdedup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,8 +14,6 @@
import os

import pytest

os.environ["DASK_DATAFRAME__QUERY_PLANNING"] = "False"
from dask.dataframe.utils import assert_eq
from distributed import Client

Expand Down
4 changes: 1 addition & 3 deletions tutorials/distributed_data_classification/distributed_data_classification.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,16 +20,14 @@
"name": "stdout",
"output_type": "stream",
"text": [
"env: PYTHONWARNINGS=ignore\n",
"env: DASK_DATAFRAME__QUERY_PLANNING=False\n"
"env: PYTHONWARNINGS=ignore\n"
]
}
],
"source": [
"# Silence Warnings (HuggingFace internal warnings)\n",
"\n",
"%env PYTHONWARNINGS=ignore\n",
"%env DASK_DATAFRAME__QUERY_PLANNING=False\n",
"import warnings\n",
"warnings.filterwarnings(\"ignore\")"
]
Expand Down
1 change: 0 additions & 1 deletion tutorials/single_node_tutorial/single_gpu_tutorial.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,7 +110,6 @@
},
"outputs": [],
"source": [
"%env DASK_DATAFRAME__QUERY_PLANNING False\n",
"%env CUDA_VISIBLE_DEVICES 0"
]
},
Expand Down