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

Import Documents: Read metas as the right type #677

Merged
merged 3 commits into from
Jul 21, 2021
Merged

Import Documents: Read metas as the right type #677

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
6024a65
Import Documents: Read metas as the right type
ajdapretnar Jul 6, 2021
c1d7c8a
Fix tests
ajdapretnar Jul 21, 2021
42405e2
Sanitize Yaml
ajdapretnar Jul 21, 2021
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
23 changes: 17 additions & 6 deletions orangecontrib/text/import_documents.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
import contextlib
import datetime
import fnmatch
import logging
import os
Expand Down Expand Up @@ -29,8 +30,10 @@

import serverfiles

from Orange.data import DiscreteVariable, Domain, StringVariable
from Orange.data.io import detect_encoding, UrlReader as CoreUrlReader
from Orange.data import DiscreteVariable, Domain, StringVariable, \
guess_data_type
from Orange.data.io import detect_encoding, sanitize_variable,\
UrlReader as CoreUrlReader
from Orange.data.util import get_unique_names
from Orange.util import Registry

Expand Down Expand Up @@ -178,6 +181,9 @@ class YamlMetaReader(Reader):
def read_file(self):
with open(self.path, "r") as f:
self.content = yaml.safe_load(f)
for k in self.content:
if self.content[k] is None:
self.content[k] = ""


class UrlReader(Reader, CoreUrlReader):
Expand Down Expand Up @@ -345,13 +351,18 @@ def _add_metadata(self, corpus: Corpus) -> Corpus:
if len(df.index.drop_duplicates()) != len(df.index):
df = df[~df.index.duplicated(keep='first')]
filtered = df.reindex(path_column)
for column in filtered.columns:
for name, column in filtered.iteritems():
data = column.astype(str).values
val_map, vals, var_type = guess_data_type(data)
values, variable = sanitize_variable(val_map, vals, data,
var_type, {},
name=get_unique_names(
corpus.domain, name))
corpus = corpus.add_column(
StringVariable(get_unique_names(corpus.domain, column)),
filtered[column].to_numpy(),
variable,
values,
to_metas=True
)

return corpus

@staticmethod
Expand Down
8 changes: 4 additions & 4 deletions orangecontrib/text/tests/test_import_documents.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -130,16 +130,16 @@ def test_run_url(self):
importer = ImportDocuments(path, True)
corpus2, _ = importer.run()
self.assertGreater(len(corpus1), 0)
self.assertEqual(corpus1.metas[mask].tolist(),
corpus2.metas[mask].tolist())
np.testing.assert_array_equal(corpus1.metas[mask].tolist(),
corpus2.metas[mask].tolist())

path = "http://file.biolab.si/text-semantics/data" \
"/predlogi-vladi-sample"
importer = ImportDocuments(path, True)
corpus3, _ = importer.run()
self.assertGreater(len(corpus2), 0)
self.assertEqual(corpus1.metas[mask].tolist(),
corpus3.metas[mask].tolist())
np.testing.assert_array_equal(corpus1.metas[mask].tolist(),
corpus3.metas[mask].tolist())

def test_run_url_special_characters(self):
path = "http://file.biolab.si/text-semantics/data/" \
Expand Down