File tree 2 files changed +12
-7
lines changed
2 files changed +12
-7
lines changed Original file line number Diff line number Diff line change @@ -525,7 +525,6 @@ RUN pip install flashtext \
525
525
pyemd \
526
526
pyupset \
527
527
pympler \
528
- s3fs \
529
528
featuretools \
530
529
#-e git+https://github.com/SohierDane/BigQuery_Helper#egg=bq_helper \
531
530
git+https://github.com/Kaggle/learntools \
@@ -561,8 +560,9 @@ RUN pip install pytorch-ignite \
561
560
bqplot \
562
561
earthengine-api \
563
562
transformers \
564
- # b/232247930 >= 2.2.0 requires pyarrow >= 6.0.0 which conflicts with dependencies for rapidsai 0.21.*
565
- datasets==2.1.0 \
563
+ datasets \
564
+ s3fs \
565
+ gcsfs \
566
566
kaggle-environments \
567
567
geopandas \
568
568
"shapely<2" \
Original file line number Diff line number Diff line change 1
1
import unittest
2
2
3
- from datasets import Dataset
4
-
3
+ import datasets
4
+ import pandas as pd
5
5
6
6
class TestHuggingFaceDatasets (unittest .TestCase ):
7
7
@@ -10,7 +10,12 @@ def some_func(batch):
10
10
batch ['label' ] = 'foo'
11
11
return batch
12
12
13
- df = Dataset .from_dict ({'text' : ['Kaggle rocks!' ]})
13
+ df = datasets . Dataset .from_dict ({'text' : ['Kaggle rocks!' ]})
14
14
mapped_df = df .map (some_func )
15
15
16
- self .assertEqual ('foo' , mapped_df [0 ]['label' ])
16
+ self .assertEqual ('foo' , mapped_df [0 ]['label' ])
17
+
18
+ def test_load_dataset (self ):
19
+ dataset = datasets .load_dataset ("csv" , data_files = "/input/tests/data/train.csv" )
20
+ full_data = pd .DataFrame (dataset ['train' ])
21
+ self .assertFalse (full_data .empty )
You can’t perform that action at this time.
0 commit comments