Skip to content

Rename prepare_alliccp to prepare_aliccp #1145

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

Merged
edknv merged 3 commits into from
Jun 13, 2023
Merged

Rename prepare_alliccp to prepare_aliccp #1145

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d05bf57
Rename `prepare_alliccp` to `prepare_aliccp`
oliverholworthy Jun 12, 2023
803b05c
Merge branch 'main' into aliccp-rename-prepare-function
rnyak Jun 12, 2023
558ed71
Merge branch 'main' into aliccp-rename-prepare-function
edknv Jun 12, 2023
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
4 changes: 2 additions & 2 deletions merlin/datasets/ecommerce/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,14 +17,14 @@
from merlin.datasets.ecommerce.aliccp.dataset import (
default_aliccp_transformation,
get_aliccp,
prepare_alliccp,
prepare_aliccp,
transform_aliccp,
)
from merlin.datasets.ecommerce.booking.dataset import get_booking, transform_booking
from merlin.datasets.ecommerce.dressipi.dataset import get_dressipi2022

__all__ = [
"prepare_alliccp",
"prepare_aliccp",
"transform_aliccp",
"get_aliccp",
"default_aliccp_transformation",
Expand Down
6 changes: 3 additions & 3 deletions merlin/datasets/ecommerce/aliccp/dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ def get_aliccp(
1. Download the raw data from
[tianchi.aliyun.com](https://tianchi.aliyun.com/dataset/dataDetail?dataId=408#1).
2. Unzip the raw data to a directory.
3. Run `prepare_alliccp(data_dir)` to convert the raw data to parquet files.
3. Run `prepare_aliccp(data_dir)` to convert the raw data to parquet files.

Downloading & preparing the data can take quite a while.
In case you want to use this dataset to run our tutorials, you can also opt for synthetic data.
Expand Down Expand Up @@ -98,7 +98,7 @@ def get_aliccp(
raw_path = p / "raw"
if not raw_path.exists():
raw_path.mkdir(parents=True)
prepare_alliccp(path, output_dir=raw_path, file_size=file_size, **kwargs)
prepare_aliccp(path, output_dir=raw_path, file_size=file_size, **kwargs)

nvt_path = p / transformed_name
train_path, valid_path = nvt_path / "train", nvt_path / "valid"
Expand All @@ -112,7 +112,7 @@ def get_aliccp(
return train, valid


def prepare_alliccp(
def prepare_aliccp(
data_dir: Union[str, Path],
convert_train: bool = True,
convert_test: bool = True,
Expand Down
8 changes: 4 additions & 4 deletions tests/unit/datasets/test_ecommerce.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,7 @@ def test_synthetic_aliccp_raw_data(tmp_path):
MAYBE_ALICCP_DATA is None,
reason="ALI-CCP data is not available, pass it through env variable $DATA_PATH_ALICCP",
)
def test_get_alliccp():
def test_get_aliccp():
data_path = MAYBE_ALICCP_DATA

nvt_workflow = ecommerce.default_aliccp_transformation(add_target_encoding=False)
Expand All @@ -104,10 +104,10 @@ def test_get_alliccp():
MAYBE_ALICCP_DATA is None,
reason="ALI-CCP data is not available, pass it through env variable $DATA_PATH_ALICCP",
)
def test_prepare_alliccp(tmp_path):
def test_prepare_aliccp(tmp_path):
data_path = MAYBE_ALICCP_DATA

ecommerce.prepare_alliccp(data_path, file_size=50, max_num_rows=100, output_dir=tmp_path)
ecommerce.prepare_aliccp(data_path, file_size=50, max_num_rows=100, output_dir=tmp_path)
output_files = list(tmp_path.glob("*/*"))

assert len(output_files) == 2
Expand All @@ -118,7 +118,7 @@ def test_prepare_alliccp(tmp_path):
MAYBE_ALICCP_DATA is None,
reason="ALI-CCP data is not available, pass it through env variable $DATA_PATH_ALICCP",
)
def test_transform_alliccp(tmp_path):
def test_transform_aliccp(tmp_path):
data_path = MAYBE_ALICCP_DATA

ecommerce.transform_aliccp(data_path, tmp_path)
Expand Down