From 6f6b2f8afbc053e3bc0ce5f7bf51cb1d9d21c520 Mon Sep 17 00:00:00 2001
From: Olivier Grisel <olivier.grisel@ensta.org>
Date: Sun, 4 Jul 2010 19:48:35 +0200
Subject: [PATCH] make it easy to find the raw source document
---
scikits/learn/datasets/mlcomp.py | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/scikits/learn/datasets/mlcomp.py b/scikits/learn/datasets/mlcomp.py
index bde4a7f1ff..f6a79eb8f9 100644
--- a/scikits/learn/datasets/mlcomp.py
+++ b/scikits/learn/datasets/mlcomp.py
@@ -11,6 +11,7 @@ def load_document_classification(dataset_path, metadata, set_, **kw):
"""Loader implementation for the DocumentClassification format"""
target = []
target_names = {}
+ filenames = []
vectorizer = kw.get('vectorizer', HashingVectorizer())
dataset_path = os.path.join(dataset_path, set_)
@@ -23,9 +24,11 @@ def load_document_classification(dataset_path, metadata, set_, **kw):
for d in sorted(os.listdir(folder_path))]
vectorizer.vectorize(documents)
target.extend(len(documents) * [label])
+ filenames.extend(documents)
return Bunch(data=vectorizer.get_vectors(), target=target,
- target_names=target_names, DESCR=metadata.get('description'))
+ target_names=target_names, filenames=filenames,
+ DESCR=metadata.get('description'))
LOADERS = {
--
GitLab