Merge pull request #2016 from mreiche/bugfix/mixed-tz-conversion

Fix datetime conversion with mixed timezones when ignore_tz is False

tests/test_prices.py

@@ -1,13 +1,13 @@
-from .context import yfinance as yf
-from .context import session_gbl
-
+import datetime as _dt
+import os
 import unittest
 
-import os
-import datetime as _dt
-import pytz as _tz
 import numpy as _np
 import pandas as _pd
+import pytz as _tz
+
+from .context import session_gbl
+from .context import yfinance as yf
 
 
 class TestPriceHistory(unittest.TestCase):
@@ -32,17 +32,23 @@ def test_daily_index(self):
                 f = df.index.time == _dt.time(0)
                 self.assertTrue(f.all())
 
-    def test_download(self):
+    def test_download_multi_large_interval(self):
         tkrs = ["BHP.AX", "IMP.JO", "BP.L", "PNL.L", "INTC"]
         intervals = ["1d", "1wk", "1mo"]
         for interval in intervals:
-            df = yf.download(tkrs, period="5y", interval=interval)
+            with self.subTest(interval):
+                df = yf.download(tkrs, period="5y", interval=interval)
+
+                f = df.index.time == _dt.time(0)
+                self.assertTrue(f.all())
 
-            f = df.index.time == _dt.time(0)
-            self.assertTrue(f.all())
+                df_tkrs = df.columns.levels[1]
+                self.assertEqual(sorted(tkrs), sorted(df_tkrs))
 
-            df_tkrs = df.columns.levels[1]
-            self.assertEqual(sorted(tkrs), sorted(df_tkrs))
+    def test_download_multi_small_interval(self):
+        use_tkrs = ["AAPL", "0Q3.DE", "ATVI"]
+        df = yf.download(use_tkrs, period="1d", interval="5m")
+        self.assertEqual(df.index.tz, _dt.timezone.utc)
 
     def test_download_with_invalid_ticker(self):
         #Checks if using an invalid symbol gives the same output as not using an invalid symbol in combination with a valid symbol (AAPL)

tests/test_utils.py

@@ -8,9 +8,10 @@
    python -m unittest tests.utils.TestTicker
 
 """
+from datetime import datetime
 from unittest import TestSuite
 
-# import pandas as pd
+import pandas as pd
 # import numpy as np
 
 from .context import yfinance as yf
@@ -81,10 +82,34 @@ def test_tzCacheRootLookup(self):
         cache.lookup(tkr)
 
 
+class TestPandas(unittest.TestCase):
+    date_strings = ["2024-08-07 09:05:00+02:00", "2024-08-07 09:05:00-04:00"]
+
+    @unittest.expectedFailure
+    def test_mixed_timezones_to_datetime_fails(self):
+        series = pd.Series(self.date_strings)
+        series = series.map(pd.Timestamp)
+        converted = pd.to_datetime(series)
+        self.assertIsNotNone(converted[0].tz)
+
+    def test_mixed_timezones_to_datetime(self):
+        series = pd.Series(self.date_strings)
+        series = series.map(pd.Timestamp)
+        converted = pd.to_datetime(series, utc=True)
+        self.assertIsNotNone(converted[0].tz)
+        i = 0
+        for dt in converted:
+            dt: datetime
+            ts: pd.Timestamp = series[i]
+            self.assertEqual(dt.isoformat(), ts.tz_convert(tz="UTC").isoformat())
+            i += 1
+
+
 def suite():
     ts: TestSuite = unittest.TestSuite()
     ts.addTest(TestCache('Test cache'))
     ts.addTest(TestCacheNoPermission('Test cache no permission'))
+    ts.addTest(TestPandas("Test pandas"))
     return ts
 
 

yfinance/multi.py

@@ -211,7 +211,7 @@ def download(tickers, start=None, end=None, actions=False, threads=True, ignore_
         _realign_dfs()
         data = _pd.concat(shared._DFS.values(), axis=1, sort=True,
                           keys=shared._DFS.keys(), names=['Ticker', 'Price'])
-    data.index = _pd.to_datetime(data.index)
+    data.index = _pd.to_datetime(data.index, utc=True)
     # switch names back to isins if applicable
     data.rename(columns=shared._ISINS, inplace=True)