From e1e6bfcd7f675b73e7eab6284ed5390738368e48 Mon Sep 17 00:00:00 2001
From: Daniel <dcolinmorgan@gmail.com>
Date: Fri, 29 Mar 2024 15:20:40 +0700
Subject: [PATCH] dbscan clusters on story features

---
 .github/workflows/on_push.yml | 2 +-
 main.py                       | 6 +++---
 setup.py                      | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/.github/workflows/on_push.yml b/.github/workflows/on_push.yml
index fe56766..f8f5c86 100644
--- a/.github/workflows/on_push.yml
+++ b/.github/workflows/on_push.yml
@@ -34,7 +34,7 @@ jobs:
       run: |
           source dots/bin/activate
           python -m spacy download en_core_web_sm
-          python DOTS/test/test_dots_feat.py -n 5 -f 3 -s 1 -o dots_feats.csv
+          python DOTS/test/test_dots_feat.py -n 5 -f 3 -d 4 -o dots_feats.csv
       env:
           OS_TOKEN: ${{ secrets.OS_TOKEN }}
           LOBSTR_KEY: ${{ secrets.LOBSTR_KEY }}
diff --git a/main.py b/main.py
index 7a3d2be..e970e9a 100644
--- a/main.py
+++ b/main.py
@@ -80,13 +80,13 @@ def main(args):
         articles = get_google_news('disaster')
         dname = 'google2_'
     elif args.d == 3:
-        articles = pull_lobstr_gdoc()
+        articles = pull_lobstr_gdoc(args.n)
         dname = 'lobstr3_'
     elif args.d == 4:
-        response = get_test_gnews(100)
+        response = get_test_gnews(args.n)
         hits = response["hits"]["hits"]
         articles = pull_data(hits)
-        dname = 'test_gnews _'
+        dname = 'test_gnews_'
     rank_articles = []
     if device == 'cuda':
         dataloader = DataLoader(data['text'], batch_size=1, shuffle=True, num_workers=4)
diff --git a/setup.py b/setup.py
index d380659..e99b995 100755
--- a/setup.py
+++ b/setup.py
@@ -17,7 +17,7 @@
   'nltk',
   'numpy',
   'GNews',
-  'graphistry[umap-learn]'
+  'graphistry[umap-learn]',
   'umap-learn'
 ]