From e29a62da948446ec090e257daa4736544825fb20 Mon Sep 17 00:00:00 2001
From: ivanzvonkov <ivan.zvonkov@gmail.com>
Date: Tue, 17 Dec 2024 15:32:10 -0500
Subject: [PATCH] Fix start date

---
 data/datasets.dvc | 6 +++---
 datasets.py       | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/data/datasets.dvc b/data/datasets.dvc
index 40956867..0229b588 100644
--- a/data/datasets.dvc
+++ b/data/datasets.dvc
@@ -1,6 +1,6 @@
 outs:
-- md5: ebe078dafe84bf33fd0b6244a5d96976.dir
-  size: 750599973
-  nfiles: 63
+- md5: 255771180339afd476bb65d11d0406e5.dir
+  size: 745188620
+  nfiles: 62
   path: datasets
   hash: md5
diff --git a/datasets.py b/datasets.py
index 392c9384..888fff60 100644
--- a/datasets.py
+++ b/datasets.py
@@ -567,7 +567,7 @@ def load_labels(self) -> pd.DataFrame:
                 "email": join_unique,
             }
         )
-        df[START], df[END] = date(2019, 1, 1), date(2020, 12, 31)
+        df[START], df[END] = date(2020, 1, 1), date(2021, 12, 31)
         df[SUBSET] = train_val_test_split(df.index, 0.3, 0.3)
         return df