Update to 0.1.78

Add 'ignore_tz' arg to download()

CHANGELOG.rst

@@ -1,6 +1,21 @@
 Change Log
 ===========
 
+0.1.78
+------
+- Fix download() when different timezones #1085
+
+0.1.77
+------
+- Fix user experience bug #1078
+
+0.1.75
+------
+- Fixed datetime-related issues: #1048
+- Add 'keepna' argument #1032
+- Speedup Ticker() creation #1042
+- Improve a bugfix #1033
+
 0.1.74
 ------
 - Fixed bug introduced in 0.1.73 (sorry :/)

README.md

@@ -187,6 +187,11 @@ data = yf.download(  # or pdr.get_data_yahoo(...
         # (optional, default is '1d')
         interval = "1m",
 
+        # Whether to ignore timezone when aligning ticker data from 
+        # different timezones. Default is True. False may be useful for 
+        # minute/hourly data.
+        ignore_tz = False,
+
         # group by ticker (to access via data['SPY'])
         # (optional, default is 'column')
         group_by = 'ticker',
@@ -264,6 +269,7 @@ To install `yfinance` using `conda`, see
 -   [Numpy](http://www.numpy.org) \>= 1.11.1
 -   [requests](http://docs.python-requests.org/en/master/) \>= 2.14.2
 -   [lxml](https://pypi.org/project/lxml/) \>= 4.5.1
+-   [appdirs](https://pypi.org/project/appdirs) \>=1.4.4
 
 ### Optional (if you want to use `pandas_datareader`)
 

meta.yaml

@@ -21,6 +21,7 @@ requirements:
     - requests >=2.21
     - multitasking >=0.0.7
     - lxml >=4.5.1
+    - appdirs >= 1.4.4
     - pip
     - python
 
@@ -30,6 +31,7 @@ requirements:
     - requests >=2.21
     - multitasking >=0.0.7
     - lxml >=4.5.1
+    - appdirs >= 1.4.4
     - python
 
 test:

requirements.txt

@@ -3,3 +3,4 @@ numpy>=1.16.5
 requests>=2.26
 multitasking>=0.0.7
 lxml>=4.5.1
+appdirs>=1.4.4

setup.py

@@ -63,7 +63,7 @@ setup(
     packages=find_packages(exclude=['contrib', 'docs', 'tests', 'examples']),
     install_requires=['pandas>=0.24.0', 'numpy>=1.15',
                       'requests>=2.26', 'multitasking>=0.0.7',
-                      'lxml>=4.5.1'],
+                      'lxml>=4.5.1', 'appdirs>=1.4.4'],
     entry_points={
         'console_scripts': [
             'sample=sample:main',

yfinance/base.py

@@ -23,6 +23,7 @@ from __future__ import print_function
 
 import time as _time
 import datetime as _datetime
+import pytz as _tz
 import requests as _requests
 import pandas as _pd
 import numpy as _np
@@ -53,6 +54,7 @@ class TickerBase():
         self._history = None
         self._base_url = _BASE_URL_
         self._scrape_url = _SCRAPE_URL_
+        self._tz = None
 
         self._fundamentals = False
         self._info = None
@@ -71,18 +73,10 @@ class TickerBase():
         self._earnings_dates = None
         self._earnings_history = None
 
-        self._earnings = {
-            "yearly": utils.empty_df(),
-            "quarterly": utils.empty_df()}
-        self._financials = {
-            "yearly": utils.empty_df(),
-            "quarterly": utils.empty_df()}
-        self._balancesheet = {
-            "yearly": utils.empty_df(),
-            "quarterly": utils.empty_df()}
-        self._cashflow = {
-            "yearly": utils.empty_df(),
-            "quarterly": utils.empty_df()}
+        self._earnings = None
+        self._financials = None
+        self._balancesheet = None
+        self._cashflow = None
 
         # accept isin as ticker
         if utils.is_isin(self.ticker):
@@ -106,8 +100,8 @@ class TickerBase():
 
     def history(self, period="1mo", interval="1d",
                 start=None, end=None, prepost=False, actions=True,
-                auto_adjust=True, back_adjust=False,
-                proxy=None, rounding=False, tz=None, timeout=None, **kwargs):
+                auto_adjust=True, back_adjust=False, keepna=False,
+                proxy=None, rounding=False, timeout=None, **kwargs):
         """
         :Parameters:
             period : str
@@ -129,14 +123,14 @@ class TickerBase():
                 Adjust all OHLC automatically? Default is True
             back_adjust: bool
                 Back-adjusted data to mimic true historical prices
+            keepna: bool
+                Keep NaN rows returned by Yahoo?
+                Default is False
             proxy: str
                 Optional. Proxy server URL scheme. Default is None
             rounding: bool
                 Round values to 2 decimal places?
                 Optional. Default is False = precision suggested by Yahoo!
-            tz: str
-                Optional timezone locale for dates.
-                (default data is returned as non-localized dates)
             timeout: None or float
                 If not None stops waiting for a response after given number of
                 seconds. (Can also be a fraction of a second e.g. 0.01)
@@ -147,23 +141,38 @@ class TickerBase():
                     error message printing to console.
         """
 
+        # Work with errors
+        debug_mode = True
+        if "debug" in kwargs and isinstance(kwargs["debug"], bool):
+            debug_mode = kwargs["debug"]
+
+        err_msg = "No data found for this date range, symbol may be delisted"
+
         if start or period is None or period.lower() == "max":
+            # Check can get TZ. Fail => probably delisted
+            try:
+                tz = self._get_ticker_tz()
+            except KeyError as e:
+                if "exchangeTimezoneName" in str(e):
+                    shared._DFS[self.ticker] = utils.empty_df()
+                    shared._ERRORS[self.ticker] = err_msg
+                    if "many" not in kwargs and debug_mode:
+                        print('- %s: %s' % (self.ticker, err_msg))
+                    return utils.empty_df()
+                else:
+                    raise
+
             if end is None:
                 end = int(_time.time())
-            elif isinstance(end, _datetime.datetime):
-                end = int(_time.mktime(end.timetuple()))
             else:
-                end = int(_time.mktime(_time.strptime(str(end), '%Y-%m-%d')))
+                end = utils._parse_user_dt(end, tz)
             if start is None:
                 if interval == "1m":
                     start = end - 604800  # Subtract 7 days
                 else:
                     start = -631159200
-            elif isinstance(start, _datetime.datetime):
-                start = int(_time.mktime(start.timetuple()))
             else:
-                start = int(_time.mktime(
-                    _time.strptime(str(start), '%Y-%m-%d')))
+                start = utils._parse_user_dt(start, tz)
             params = {"period1": start, "period2": end}
         else:
             period = period.lower()
@@ -206,13 +215,6 @@ class TickerBase():
         except Exception:
             pass
 
-        # Work with errors
-        debug_mode = True
-        if "debug" in kwargs and isinstance(kwargs["debug"], bool):
-            debug_mode = kwargs["debug"]
-
-        err_msg = "No data found for this date range, symbol may be delisted"
-
         if data is None or not type(data) is dict or 'status_code' in data.keys():
             shared._DFS[self.ticker] = utils.empty_df()
             shared._ERRORS[self.ticker] = err_msg
@@ -238,7 +240,12 @@ class TickerBase():
 
         # parse quotes
         try:
-            quotes = utils.parse_quotes(data["chart"]["result"][0], tz)
+            quotes = utils.parse_quotes(data["chart"]["result"][0])
+            # Yahoo bug fix - it often appends latest price even if after end date
+            if end and not quotes.empty:
+                endDt = _pd.to_datetime(_datetime.datetime.utcfromtimestamp(end))
+                if quotes.index[quotes.shape[0]-1] >= endDt:
+                    quotes = quotes.iloc[0:quotes.shape[0]-1]
         except Exception:
             shared._DFS[self.ticker] = utils.empty_df()
             shared._ERRORS[self.ticker] = err_msg
@@ -286,16 +293,13 @@ class TickerBase():
                 "chart"]["result"][0]["meta"]["priceHint"])
         quotes['Volume'] = quotes['Volume'].fillna(0).astype(_np.int64)
 
-        quotes.dropna(inplace=True)
+        if not keepna:
+            quotes.dropna(inplace=True)
 
         # actions
-        dividends, splits = utils.parse_actions(data["chart"]["result"][0], tz)
+        dividends, splits = utils.parse_actions(data["chart"]["result"][0])
 
-        # Yahoo bug fix - it often appends latest price even if after end date
-        if end and not quotes.empty:
-            endDt = _pd.to_datetime(_datetime.datetime.fromtimestamp(end))
-            if quotes.index[quotes.shape[0]-1] > endDt:
-                quotes = quotes.iloc[0:quotes.shape[0]-1]
+        tz_exchange = data["chart"]["result"][0]["meta"]["exchangeTimezoneName"]
 
         # combine
         df = _pd.concat([quotes, dividends, splits], axis=1, sort=True)
@@ -303,17 +307,16 @@ class TickerBase():
         df["Stock Splits"].fillna(0, inplace=True)
 
         # index eod/intraday
-        df.index = df.index.tz_localize("UTC").tz_convert(
-            data["chart"]["result"][0]["meta"]["exchangeTimezoneName"])
+        df.index = df.index.tz_localize("UTC").tz_convert(tz_exchange)
 
+        df = utils.fix_Yahoo_dst_issue(df, params["interval"])
+            
         if params["interval"][-1] == "m":
             df.index.name = "Datetime"
         elif params["interval"] == "1h":
             pass
         else:
-            df.index = _pd.to_datetime(df.index.date)
-            if tz is not None:
-                df.index = df.index.tz_localize(tz)
+            df.index = _pd.to_datetime(df.index.date).tz_localize(tz_exchange)
             df.index.name = "Date"
 
         # duplicates and missing rows cleanup
@@ -329,35 +332,30 @@ class TickerBase():
 
     # ------------------------
 
-    def _get_fundamentals(self, proxy=None):
-        def cleanup(data):
-            df = _pd.DataFrame(data).drop(columns=['maxAge'])
-            for col in df.columns:
-                df[col] = _np.where(
-                    df[col].astype(str) == '-', _np.nan, df[col])
+    def _get_ticker_tz(self):
+        if not self._tz is None:
+            return self._tz
 
-            df.set_index('endDate', inplace=True)
-            try:
-                df.index = _pd.to_datetime(df.index, unit='s')
-            except ValueError:
-                df.index = _pd.to_datetime(df.index)
-            df = df.T
-            df.columns.name = ''
-            df.index.name = 'Breakdown'
+        tkr_tz = utils.cache_lookup_tkr_tz(self.ticker)
+        if tkr_tz is None:
+            tkr_tz = self.info["exchangeTimezoneName"]
+            # info fetch is relatively slow so cache timezone
+            utils.cache_store_tkr_tz(self.ticker, tkr_tz)
 
-            # rename incorrect yahoo key
-            df.rename(index={'treasuryStock': 'Gains Losses Not Affecting Retained Earnings'}, inplace=True)
-
-            df.index = utils.camel2title(df.index)
-            return df
+        self._tz = tkr_tz
+        return tkr_tz
 
+    def _get_info(self, proxy=None):
         # setup proxy in requests format
         if proxy is not None:
             if isinstance(proxy, dict) and "https" in proxy:
                 proxy = proxy["https"]
             proxy = {"https": proxy}
 
-        if self._fundamentals:
+        if (self._info is None) or (self._sustainability is None) or (self._recommendations is None):
+            ## Need to fetch
+            pass
+        else:
             return
 
         ticker_url = "{}/{}".format(self._scrape_url, self.ticker)
@@ -365,42 +363,6 @@ class TickerBase():
         # get info and sustainability
         data = utils.get_json(ticker_url, proxy, self.session)
 
-        # holders
-        try:
-            resp = utils.get_html(ticker_url + '/holders', proxy, self.session)
-            holders = _pd.read_html(resp)
-        except Exception:
-            holders = []
-
-        if len(holders) >= 3:
-            self._major_holders = holders[0]
-            self._institutional_holders = holders[1]
-            self._mutualfund_holders = holders[2]
-        elif len(holders) >= 2:
-            self._major_holders = holders[0]
-            self._institutional_holders = holders[1]
-        elif len(holders) >= 1:
-            self._major_holders = holders[0]
-
-        # self._major_holders = holders[0]
-        # self._institutional_holders = holders[1]
-
-        if self._institutional_holders is not None:
-            if 'Date Reported' in self._institutional_holders:
-                self._institutional_holders['Date Reported'] = _pd.to_datetime(
-                    self._institutional_holders['Date Reported'])
-            if '% Out' in self._institutional_holders:
-                self._institutional_holders['% Out'] = self._institutional_holders[
-                    '% Out'].str.replace('%', '').astype(float) / 100
-
-        if self._mutualfund_holders is not None:
-            if 'Date Reported' in self._mutualfund_holders:
-                self._mutualfund_holders['Date Reported'] = _pd.to_datetime(
-                    self._mutualfund_holders['Date Reported'])
-            if '% Out' in self._mutualfund_holders:
-                self._mutualfund_holders['% Out'] = self._mutualfund_holders[
-                    '% Out'].str.replace('%', '').astype(float) / 100
-
         # sustainability
         d = {}
         try:
@@ -431,7 +393,7 @@ class TickerBase():
         except Exception:
             pass
 
-       # For ETFs, provide this valuable data: the top holdings of the ETF
+        # For ETFs, provide this valuable data: the top holdings of the ETF
         try:
             if 'topHoldings' in data:
                 self._info.update(data['topHoldings'])
@@ -492,10 +454,85 @@ class TickerBase():
         except Exception:
             pass
 
+    def _get_fundamentals(self, proxy=None):
+        def cleanup(data):
+            df = _pd.DataFrame(data).drop(columns=['maxAge'])
+            for col in df.columns:
+                df[col] = _np.where(
+                    df[col].astype(str) == '-', _np.nan, df[col])
+
+            df.set_index('endDate', inplace=True)
+            try:
+                df.index = _pd.to_datetime(df.index, unit='s')
+            except ValueError:
+                df.index = _pd.to_datetime(df.index)
+            df = df.T
+            df.columns.name = ''
+            df.index.name = 'Breakdown'
+
+            # rename incorrect yahoo key
+            df.rename(index={'treasuryStock': 'Gains Losses Not Affecting Retained Earnings'}, inplace=True)
+
+            df.index = utils.camel2title(df.index)
+            return df
+
+        # setup proxy in requests format
+        if proxy is not None:
+            if isinstance(proxy, dict) and "https" in proxy:
+                proxy = proxy["https"]
+            proxy = {"https": proxy}
+
+        if self._fundamentals:
+            return
+
+        ticker_url = "{}/{}".format(self._scrape_url, self.ticker)
+
+        # holders
+        try:
+            resp = utils.get_html(ticker_url + '/holders', proxy, self.session)
+            holders = _pd.read_html(resp)
+        except Exception:
+            holders = []
+
+        if len(holders) >= 3:
+            self._major_holders = holders[0]
+            self._institutional_holders = holders[1]
+            self._mutualfund_holders = holders[2]
+        elif len(holders) >= 2:
+            self._major_holders = holders[0]
+            self._institutional_holders = holders[1]
+        elif len(holders) >= 1:
+            self._major_holders = holders[0]
+
+        # self._major_holders = holders[0]
+        # self._institutional_holders = holders[1]
+
+        if self._institutional_holders is not None:
+            if 'Date Reported' in self._institutional_holders:
+                self._institutional_holders['Date Reported'] = _pd.to_datetime(
+                    self._institutional_holders['Date Reported'])
+            if '% Out' in self._institutional_holders:
+                self._institutional_holders['% Out'] = self._institutional_holders[
+                    '% Out'].str.replace('%', '').astype(float) / 100
+
+        if self._mutualfund_holders is not None:
+            if 'Date Reported' in self._mutualfund_holders:
+                self._mutualfund_holders['Date Reported'] = _pd.to_datetime(
+                    self._mutualfund_holders['Date Reported'])
+            if '% Out' in self._mutualfund_holders:
+                self._mutualfund_holders['% Out'] = self._mutualfund_holders[
+                    '% Out'].str.replace('%', '').astype(float) / 100
+
+        self._get_info(proxy)
+
         # get fundamentals
         data = utils.get_json(ticker_url + '/financials', proxy, self.session)
 
         # generic patterns
+        self._earnings = {"yearly": utils.empty_df(), "quarterly": utils.empty_df()}
+        self._cashflow = {"yearly": utils.empty_df(), "quarterly": utils.empty_df()}
+        self._balancesheet = {"yearly": utils.empty_df(), "quarterly": utils.empty_df()}
+        self._financials = {"yearly": utils.empty_df(), "quarterly": utils.empty_df()}
         for key in (
             (self._cashflow, 'cashflowStatement', 'cashflowStatements'),
             (self._balancesheet, 'balanceSheet', 'balanceSheetStatements'),
@@ -621,14 +658,14 @@ class TickerBase():
         self._fundamentals = True
 
     def get_recommendations(self, proxy=None, as_dict=False, *args, **kwargs):
-        self._get_fundamentals(proxy=proxy)
+        self._get_info(proxy)
         data = self._recommendations
         if as_dict:
             return data.to_dict()
         return data
 
     def get_calendar(self, proxy=None, as_dict=False, *args, **kwargs):
-        self._get_fundamentals(proxy=proxy)
+        self._get_info(proxy)
         data = self._calendar
         if as_dict:
             return data.to_dict()
@@ -658,14 +695,14 @@ class TickerBase():
             return data
 
     def get_info(self, proxy=None, as_dict=False, *args, **kwargs):
-        self._get_fundamentals(proxy=proxy)
+        self._get_info(proxy)
         data = self._info
         if as_dict:
             return data.to_dict()
         return data
 
     def get_sustainability(self, proxy=None, as_dict=False, *args, **kwargs):
-        self._get_fundamentals(proxy=proxy)
+        self._get_info(proxy)
         data = self._sustainability
         if as_dict:
             return data.to_dict()

yfinance/multi.py

@@ -29,8 +29,8 @@ from . import Ticker, utils
 from . import shared
 
 
-def download(tickers, start=None, end=None, actions=False, threads=True,
-             group_by='column', auto_adjust=False, back_adjust=False,
+def download(tickers, start=None, end=None, actions=False, threads=True, ignore_tz=True, 
+             group_by='column', auto_adjust=False, back_adjust=False, keepna=False,
              progress=True, period="max", show_errors=True, interval="1d", prepost=False,
              proxy=None, rounding=False, timeout=None, **kwargs):
     """Download yahoo tickers
@@ -56,10 +56,16 @@ def download(tickers, start=None, end=None, actions=False, threads=True,
             Default is False
         auto_adjust: bool
             Adjust all OHLC automatically? Default is False
+        keepna: bool
+            Keep NaN rows returned by Yahoo?
+            Default is False
         actions: bool
             Download dividend + stock splits data. Default is False
         threads: bool / int
             How many threads to use for mass downloading. Default is True
+        ignore_tz: bool
+            When combining from different timezones, ignore that part of datetime.
+            Default is True
         proxy: str
             Optional. Proxy server URL scheme. Default is None
         rounding: bool
@@ -105,7 +111,7 @@ def download(tickers, start=None, end=None, actions=False, threads=True,
             _download_one_threaded(ticker, period=period, interval=interval,
                                    start=start, end=end, prepost=prepost,
                                    actions=actions, auto_adjust=auto_adjust,
-                                   back_adjust=back_adjust,
+                                   back_adjust=back_adjust, keepna=keepna,
                                    progress=(progress and i > 0), proxy=proxy,
                                    rounding=rounding, timeout=timeout)
         while len(shared._DFS) < len(tickers):
@@ -117,7 +123,7 @@ def download(tickers, start=None, end=None, actions=False, threads=True,
             data = _download_one(ticker, period=period, interval=interval,
                                  start=start, end=end, prepost=prepost,
                                  actions=actions, auto_adjust=auto_adjust,
-                                 back_adjust=back_adjust, proxy=proxy,
+                                 back_adjust=back_adjust, keepna=keepna, proxy=proxy,
                                  rounding=rounding, timeout=timeout)
             shared._DFS[ticker.upper()] = data
             if progress:
@@ -137,12 +143,17 @@ def download(tickers, start=None, end=None, actions=False, threads=True,
         ticker = tickers[0]
         return shared._DFS[shared._ISINS.get(ticker, ticker)]
 
+    if ignore_tz:
+        for tkr in shared._DFS.keys():
+            if (shared._DFS[tkr] is not None) and (shared._DFS[tkr].shape[0]>0):
+                shared._DFS[tkr].index = shared._DFS[tkr].index.tz_localize(None)
+
     try:
-        data = _pd.concat(shared._DFS.values(), axis=1,
+        data = _pd.concat(shared._DFS.values(), axis=1, sort=True,
                           keys=shared._DFS.keys())
     except Exception:
         _realign_dfs()
-        data = _pd.concat(shared._DFS.values(), axis=1,
+        data = _pd.concat(shared._DFS.values(), axis=1, sort=True,
                           keys=shared._DFS.keys())
 
     # switch names back to isins if applicable
@@ -183,11 +194,11 @@ def _download_one_threaded(ticker, start=None, end=None,
                            auto_adjust=False, back_adjust=False,
                            actions=False, progress=True, period="max",
                            interval="1d", prepost=False, proxy=None,
-                           rounding=False, timeout=None):
+                           keepna=False, rounding=False, timeout=None):
 
     data = _download_one(ticker, start, end, auto_adjust, back_adjust,
                          actions, period, interval, prepost, proxy, rounding,
-                         timeout)
+                         keepna, timeout)
     shared._DFS[ticker.upper()] = data
     if progress:
         shared._PROGRESS_BAR.animate()
@@ -197,11 +208,11 @@ def _download_one(ticker, start=None, end=None,
                   auto_adjust=False, back_adjust=False,
                   actions=False, period="max", interval="1d",
                   prepost=False, proxy=None, rounding=False,
-                  timeout=None):
+                  keepna=False, timeout=None):
 
     return Ticker(ticker).history(period=period, interval=interval,
                                   start=start, end=end, prepost=prepost,
                                   actions=actions, auto_adjust=auto_adjust,
                                   back_adjust=back_adjust, proxy=proxy,
-                                  rounding=rounding, many=True,
+                                  rounding=rounding, keepna=keepna, many=True,
                                   timeout=timeout)

yfinance/utils.py

@@ -21,11 +21,15 @@
 
 from __future__ import print_function
 
+import datetime as _datetime
+import pytz as _tz
 import requests as _requests
 import re as _re
 import pandas as _pd
 import numpy as _np
 import sys as _sys
+import os as _os
+import appdirs as _ad
 
 try:
     import ujson as _json
@@ -135,6 +139,23 @@ def camel2title(o):
     return [_re.sub("([a-z])([A-Z])", r"\g<1> \g<2>", i).title() for i in o]
 
 
+def _parse_user_dt(dt, exchange_tz):
+    if isinstance(dt, int):
+        ## Should already be epoch, test with conversion:
+        _datetime.datetime.fromtimestamp(dt)
+    else:
+        # Convert str/date -> datetime, set tzinfo=exchange, get timestamp:
+        if isinstance(dt, str):
+            dt = _datetime.datetime.strptime(str(dt), '%Y-%m-%d')
+        if isinstance(dt, _datetime.date) and not isinstance(dt, _datetime.datetime):
+            dt = _datetime.datetime.combine(dt, _datetime.time(0))
+        if isinstance(dt, _datetime.datetime) and dt.tzinfo is None:
+            # Assume user is referring to exchange's timezone
+            dt = _tz.timezone(exchange_tz).localize(dt)
+        dt = int(dt.timestamp())
+    return dt
+
+
 def auto_adjust(data):
     df = data.copy()
     ratio = df["Close"] / df["Adj Close"]
@@ -176,7 +197,7 @@ def back_adjust(data):
     return df[["Open", "High", "Low", "Close", "Volume"]]
 
 
-def parse_quotes(data, tz=None):
+def parse_quotes(data):
     timestamps = data["timestamp"]
     ohlc = data["indicators"]["quote"][0]
     volumes = ohlc["volume"]
@@ -199,13 +220,10 @@ def parse_quotes(data, tz=None):
     quotes.index = _pd.to_datetime(timestamps, unit="s")
     quotes.sort_index(inplace=True)
 
-    if tz is not None:
-        quotes.index = quotes.index.tz_localize(tz)
-
     return quotes
 
 
-def parse_actions(data, tz=None):
+def parse_actions(data):
     dividends = _pd.DataFrame(
         columns=["Dividends"], index=_pd.DatetimeIndex([]))
     splits = _pd.DataFrame(
@@ -218,8 +236,6 @@ def parse_actions(data, tz=None):
             dividends.set_index("date", inplace=True)
             dividends.index = _pd.to_datetime(dividends.index, unit="s")
             dividends.sort_index(inplace=True)
-            if tz is not None:
-                dividends.index = dividends.index.tz_localize(tz)
 
             dividends.columns = ["Dividends"]
 
@@ -229,8 +245,6 @@ def parse_actions(data, tz=None):
             splits.set_index("date", inplace=True)
             splits.index = _pd.to_datetime(splits.index, unit="s")
             splits.sort_index(inplace=True)
-            if tz is not None:
-                splits.index = splits.index.tz_localize(tz)
             splits["Stock Splits"] = splits["numerator"] / \
                 splits["denominator"]
             splits = splits["Stock Splits"]
@@ -238,6 +252,19 @@ def parse_actions(data, tz=None):
     return dividends, splits
 
 
+def fix_Yahoo_dst_issue(df, interval):
+    if interval in ["1d","1w","1wk"]:
+        # These intervals should start at time 00:00. But for some combinations of date and timezone, 
+        # Yahoo has time off by few hours (e.g. Brazil 23:00 around Jan-2022). Suspect DST problem.
+        # The clue is (a) minutes=0 and (b) hour near 0. 
+        # Obviously Yahoo meant 00:00, so ensure this doesn't affect date conversion:
+        f_pre_midnight = (df.index.minute == 0) & (df.index.hour.isin([22,23]))
+        dst_error_hours = _np.array([0]*df.shape[0])
+        dst_error_hours[f_pre_midnight] = 24-df.index[f_pre_midnight].hour
+        df.index += _pd.TimedeltaIndex(dst_error_hours, 'h')
+    return df
+
+
 class ProgressBar:
     def __init__(self, iterations, text='completed'):
         self.text = text
@@ -286,3 +313,37 @@ class ProgressBar:
 
     def __str__(self):
         return str(self.prog_bar)
+
+
+# Simple file cache of ticker->timezone:
+def get_cache_dirpath():
+    return _os.path.join(_ad.user_cache_dir(), "py-yfinance")
+def cache_lookup_tkr_tz(tkr):
+    fp = _os.path.join(get_cache_dirpath(), "tkr-tz.csv")
+    if not _os.path.isfile(fp):
+        return None
+
+    df = _pd.read_csv(fp)
+    f = df["Ticker"] == tkr
+    if sum(f) == 0:
+        return None
+
+    return df["Tz"][f].iloc[0]
+def cache_store_tkr_tz(tkr,tz):
+    df = _pd.DataFrame({"Ticker":[tkr], "Tz":[tz]})
+
+    dp = get_cache_dirpath()
+    if not _os.path.isdir(dp):
+        _os.makedirs(dp)
+    fp = _os.path.join(dp, "tkr-tz.csv")
+    if not _os.path.isfile(fp):
+        df.to_csv(fp, index=False)
+        return
+
+    df_all = _pd.read_csv(fp)
+    f = df_all["Ticker"]==tkr
+    if sum(f) > 0:
+        raise Exception("Tkr {} tz already in cache".format(tkr))
+
+    _pd.concat([df_all,df]).to_csv(fp, index=False)
+

yfinance/version.py

@@ -1 +1 @@
-version = "0.1.74"
+version = "0.1.78"