Skip to content

Commit

Permalink
bring back master for tests
Browse files Browse the repository at this point in the history
  • Loading branch information
magdyksaleh committed Jul 26, 2022
1 parent 5eabb0f commit c06b7be
Showing 1 changed file with 6 additions and 4 deletions.
10 changes: 6 additions & 4 deletions tests/integration_tests/test_preprocessing.py
Original file line number Diff line number Diff line change
Expand Up @@ -121,12 +121,14 @@ def test_with_split(backend, csv_filename, tmpdir):
def test_dask_known_divisions(feature_fn, csv_filename, tmpdir):
import dask.dataframe as dd

num_examples = NUM_EXAMPLES

input_features = [feature_fn(os.path.join(tmpdir, "generated_output"))]
output_features = [category_feature(vocab_size=5, reduce_input="sum")]

# num_examples=100 and npartitions=2 to ensure the test is not flaky, by having non-empty post-split datasets.
data_csv = generate_data(input_features, output_features, os.path.join(tmpdir, csv_filename), num_examples=100)
data_df = dd.from_pandas(pd.read_csv(data_csv), npartitions=2)
data_csv = generate_data(
input_features, output_features, os.path.join(tmpdir, csv_filename), num_examples=num_examples
)
data_df = dd.from_pandas(pd.read_csv(data_csv), npartitions=10)
assert data_df.known_divisions

config = {
Expand Down

0 comments on commit c06b7be

Please sign in to comment.