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

Added support for UD_NAIJA #1952

Merged
merged 2 commits into from
Nov 9, 2020
Merged

Added support for UD_NAIJA #1952

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b72d573
Added support for UD_NAIJA
teddim420 Nov 7, 2020
d5798c0
Merge branch 'master' into teddimnaija
alanakbik Nov 9, 2020
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
30 changes: 28 additions & 2 deletions flair/datasets/treebanks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1124,6 +1124,33 @@ def __init__(self, base_path: Union[str, Path] = None, in_memory: bool = True):
)

super(UD_GREEK, self).__init__(data_folder, in_memory=in_memory)


class UD_NAIJA(UniversalDependenciesCorpus):
def __init__(self, base_path: Union[str, Path] = None, in_memory: bool = True):

if type(base_path) == str:
base_path: Path = Path(base_path)

# this dataset name
dataset_name = self.__class__.__name__.lower()

# default dataset folder is the cache root
if not base_path:
base_path = Path(flair.cache_root) / "datasets"
data_folder = base_path / dataset_name

# download data if necessary
web_path = "https://raw.githubusercontent.com/UniversalDependencies/UD_Naija-NSC/master"
cached_path(f"{web_path}//pcm_nsc-ud-dev.conllu", Path("datasets") / dataset_name)
cached_path(
f"{web_path}//pcm_nsc-ud-test.conllu", Path("datasets") / dataset_name
)
cached_path(
f"{web_path}//pcm_nsc-ud-train.conllu", Path("datasets") / dataset_name
)

super(UD_NAIJA, self).__init__(data_folder, in_memory=in_memory)


class UD_LIVVI(UniversalDependenciesCorpus):
Expand All @@ -1145,5 +1172,4 @@ def __init__(self, base_path: Union[str, Path] = None, in_memory: bool = True):
cached_path(f"{web_path}/olo_kkpp-ud-test.conllu", Path("datasets") / dataset_name)
cached_path(f"{web_path}/olo_kkpp-ud-train.conllu", Path("datasets") / dataset_name)

super(UD_LIVVI, self).__init__(data_folder, in_memory=in_memory)

super(UD_LIVVI, self).__init__(data_folder, in_memory=in_memory)