Merge pull request #74 from stephenhky/aws_s3

Using AWS S3 buckets instead of GCP buckets for datasets
stephenhky · Sep 24, 2019 · 14bde0c · 14bde0c
2 parents 030f154 + 2b57eaf
commit 14bde0c
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 3 deletions.
diff --git a/shorttext/data/data_retrieval.py b/shorttext/data/data_retrieval.py
@@ -103,7 +103,7 @@ def inaugural():
     :rtype: dict
     """
     zfile = zipfile.ZipFile(get_or_download_data("USInaugural.zip",
-                                                 "http://storage.googleapis.com/pyshorttext/USPresidentInaugural/USInaugural.zip",
+                                                 "https://shorttext-data-northernvirginia.s3.amazonaws.com/trainingdata/USInaugural.zip",
                                                  asbytes=True),
                             )
     address_jsonstr = zfile.open("addresses.json").read()
@@ -144,7 +144,7 @@ def nihreports(txt_col='PROJECT_TITLE', label_col='FUNDING_ICs', sample_size=512
         raise KeyError('Undefined label column: '+label_col+'. Must be FUNDING_ICs or IC_NAME.')
 
     zfile = zipfile.ZipFile(get_or_download_data('nih_full.csv.zip',
-                                                 'http://storage.googleapis.com/pyshorttext/nih_grant_public/nih_full.csv.zip',
+                                                 'https://shorttext-data-northernvirginia.s3.amazonaws.com/trainingdata/nih_full.csv.zip',
                                                  asbytes=True),
                             'r',
                             zipfile.ZIP_DEFLATED)

diff --git a/test/test_var_nn_embedded_vec_classifier.py b/test/test_var_nn_embedded_vec_classifier.py
@@ -11,7 +11,7 @@
 class TestVarNNEmbeddedVecClassifier(unittest.TestCase):
     def setUp(self):
         print("Downloading word-embedding model....")
-        link = "http://storage.googleapis.com/pyshorttext/test_w2vmodel/test_w2v_model.bin"
+        link = "https://shorttext-data-northernvirginia.s3.amazonaws.com/trainingdata/test_w2v_model.bin"
         filename = "test_w2v_model.bin"
         if not os.path.isfile("test_w2v_model.bin"):
             if sys.version_info[0]==2: