Merge pull request #32 from ComplexData-MILA/dtdg

update the download logic

py_tgx.egg-info/PKG-INFO

@@ -13,6 +13,17 @@ Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
 
+# Temporal Graph Analysis with TGX (to appear in WSDM 2024)
+
+
+### Example Usage ###
+TGX provides many built in datasets as well as supporting TGB datasets. In addition, TGX provides dataset discretization and visualization.
+To get started, see our [starting example](https://github.com/ComplexData-MILA/TGX/blob/master/starting_example.py)
+```
+python starting_example.py -d tgbl-wiki -t daily
+```
+
+
 ### Install dependency
 Our implementation works with python >= 3.9 and can be installed as follows
 
@@ -27,10 +38,27 @@ source ~/tgx_env/bin/activate
 pip install -r requirements.txt
 ```
 
-
 3. install local dependencies under root directory `/TGX`
-```
+<!-- ```
 pip install -e py-tgx
+``` -->
+```
+pip install -e .
+```
+
+
+
+3. [alternatively] install from test-pypi
+
+```
+pip install -i https://test.pypi.org/simple/ py-tgx
+```
+You can specify the version with `==`, note that the pypi version might not always be the most updated version
+
+
+4. [optional] install mkdocs dependencies to serve the documentation locally
+```
+pip install mkdocs-glightbox
 ```
 
 ### Creating new branch ###

requirements.txt

@@ -1,3 +1,4 @@
+requests>=2.28.2
 appdirs==1.4.4
 args==0.1.0
 certifi==2022.12.7
@@ -60,4 +61,4 @@ tzdata==2023.3
 urllib3==1.26.15
 virtualenv==20.0.18
 wandb==0.16.3
-zipp==3.15.0
+zipp==3.15.0

tgx/data/builtin.py

@@ -1,11 +1,14 @@
 import pandas as pd
 import zipfile
 import urllib
+import requests
+
 
 __all__ = ["data"]
 
 root_path = "."
 
+
 DataPath={
     'USLegis'   : "/data/USLegis/ml_USLegis.csv",
     'CanParl'   : "/data/CanParl/ml_CanParl.csv",
@@ -36,6 +39,18 @@
         'lastfm'        : {'discretize' : True,     'time_scale': 'monthly'}
         }
 
+def download(url: str, output_path: str):
+    get_response = requests.get(url,stream=True)
+    file_name  = url.split("/")[-1]
+    fpath = output_path + file_name
+    with open(output_path + file_name, 'wb') as f:
+        for chunk in get_response.iter_content(chunk_size=1024):
+            if chunk: # filter out keep-alive new chunks
+                f.write(chunk)
+    return fpath
+
+
+
 class builtin(object):
     def __init__(self):
         """
@@ -85,8 +100,8 @@ def download_file(self):
         print(path_download)
         print(url)
         if inp == 'y':
-            print(f"Download started, this might take a while . . .")
-            zip_path, _ = urllib.request.urlretrieve(url)
+            print(f"Downloading {self.name} dataset . . .")
+            zip_path = download(url, path_download)
             with zipfile.ZipFile(zip_path, "r") as f:
                 f.extractall(path_download)
             print("Download completed")