Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

sync dev -> main #1869

Merged
merged 13 commits into from
Feb 24, 2024
Merged

sync dev -> main #1869

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
1dc2719
Remove _empty_series leftovers
mreiche Jan 23, 2024
75297c0
Merge pull request #1838 from mreiche/bugfix/remove-empty-series
ValueRaider Jan 23, 2024
58a0a57
adding upgrade for pandas deprecation warning, adding pyarrow>=0.17.0…
nikolauspschuetz Jan 27, 2024
212a798
do not disable app-wide logging in quote.py (fixes #1829)
Rogach Jan 26, 2024
6b8a4a5
Merge pull request #1841 from Rogach/pr/dont-disable-global-logging
ValueRaider Jan 28, 2024
5aef8ad
removing dev requirements (they are included by extras)
nikolauspschuetz Jan 29, 2024
97f93d3
Merge pull request #1844 from power-edge/dev
ValueRaider Jan 31, 2024
cdf897f
Move price history+repair logic into new file
ValueRaider Feb 4, 2024
683064f
Merge pull request #1849 from ranaroussi/refactor/price-history
ValueRaider Feb 7, 2024
afb4e0d
Fix some errors.
cottrell Feb 19, 2024
ac1d090
Merge pull request #1865 from cottrell/fix
ValueRaider Feb 19, 2024
d55c317
Fix bug: prices order flipping during repair, introducing potential d…
ValueRaider Feb 19, 2024
915bb1a
Merge pull request #1866 from ranaroussi/fix/price-repair-confusing-o…
ValueRaider Feb 24, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
51 changes: 37 additions & 14 deletions tests/prices.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -277,7 +277,7 @@ def test_dailyWithEvents_bugs(self):
# Reproduce issue #1634 - 1d dividend out-of-range, should be prepended to prices
div_dt = _pd.Timestamp(2022, 7, 21).tz_localize("America/New_York")
df_dividends = _pd.DataFrame(data={"Dividends":[1.0]}, index=[div_dt])
df_prices = _pd.DataFrame(data={c:[1.0] for c in yf.const.price_colnames}|{'Volume':0}, index=[div_dt+_dt.timedelta(days=1)])
df_prices = _pd.DataFrame(data={c:[1.0] for c in yf.const._PRICE_COLNAMES_}|{'Volume':0}, index=[div_dt+_dt.timedelta(days=1)])
df_merged = yf.utils.safe_merge_dfs(df_prices, df_dividends, '1d')
self.assertEqual(df_merged.shape[0], 2)
self.assertTrue(df_merged[df_prices.columns].iloc[1:].equals(df_prices))
Expand Down Expand Up @@ -470,6 +470,18 @@ def tearDownClass(cls):
if cls.session is not None:
cls.session.close()

def test_types(self):
tkr = 'INTC'
dat = yf.Ticker(tkr, session=self.session)

data = dat.history(period="3mo", interval="1d", prepost=True, repair=True)
self.assertIsInstance(data, _pd.DataFrame, "data has wrong type")
self.assertFalse(data.empty, "data is empty")

reconstructed = dat._lazy_load_price_history()._reconstruct_intervals_batch(data, "1wk", True)
self.assertIsInstance(reconstructed, _pd.DataFrame, "data has wrong type")
self.assertFalse(data.empty, "data is empty")

def test_reconstruct_2m(self):
# 2m repair requires 1m data.
# Yahoo restricts 1m fetches to 7 days max within last 30 days.
Expand All @@ -494,6 +506,7 @@ def test_repair_100x_random_weekly(self):
tkr = "PNL.L"
dat = yf.Ticker(tkr, session=self.session)
tz_exchange = dat.fast_info["timezone"]
hist = dat._lazy_load_price_history()

data_cols = ["Low", "High", "Open", "Close", "Adj Close"]
df = _pd.DataFrame(data={"Open": [470.5, 473.5, 474.5, 470],
Expand All @@ -517,7 +530,7 @@ def test_repair_100x_random_weekly(self):

# Run test

df_repaired = dat._fix_unit_random_mixups(df_bad, "1wk", tz_exchange, prepost=False)
df_repaired = hist._fix_unit_random_mixups(df_bad, "1wk", tz_exchange, prepost=False)

# First test - no errors left
for c in data_cols:
Expand Down Expand Up @@ -548,6 +561,7 @@ def test_repair_100x_random_weekly_preSplit(self):
tkr = "PNL.L"
dat = yf.Ticker(tkr, session=self.session)
tz_exchange = dat.fast_info["timezone"]
hist = dat._lazy_load_price_history()

data_cols = ["Low", "High", "Open", "Close", "Adj Close"]
df = _pd.DataFrame(data={"Open": [400, 398, 392.5, 417],
Expand All @@ -574,7 +588,7 @@ def test_repair_100x_random_weekly_preSplit(self):
df.index = df.index.tz_localize(tz_exchange)
df_bad.index = df_bad.index.tz_localize(tz_exchange)

df_repaired = dat._fix_unit_random_mixups(df_bad, "1wk", tz_exchange, prepost=False)
df_repaired = hist._fix_unit_random_mixups(df_bad, "1wk", tz_exchange, prepost=False)

# First test - no errors left
for c in data_cols:
Expand Down Expand Up @@ -606,6 +620,7 @@ def test_repair_100x_random_daily(self):
tkr = "PNL.L"
dat = yf.Ticker(tkr, session=self.session)
tz_exchange = dat.fast_info["timezone"]
hist = dat._lazy_load_price_history()

data_cols = ["Low", "High", "Open", "Close", "Adj Close"]
df = _pd.DataFrame(data={"Open": [478, 476, 476, 472],
Expand All @@ -627,7 +642,7 @@ def test_repair_100x_random_daily(self):
df.index = df.index.tz_localize(tz_exchange)
df_bad.index = df_bad.index.tz_localize(tz_exchange)

df_repaired = dat._fix_unit_random_mixups(df_bad, "1d", tz_exchange, prepost=False)
df_repaired = hist._fix_unit_random_mixups(df_bad, "1d", tz_exchange, prepost=False)

# First test - no errors left
for c in data_cols:
Expand Down Expand Up @@ -656,6 +671,7 @@ def test_repair_100x_block_daily(self):
for interval in ['1d', '1wk']:
dat = yf.Ticker(tkr, session=self.session)
tz_exchange = dat.fast_info["timezone"]
hist = dat._lazy_load_price_history()

data_cols = ["Low", "High", "Open", "Close", "Adj Close"]
_dp = os.path.dirname(__file__)
Expand All @@ -672,7 +688,7 @@ def test_repair_100x_block_daily(self):
df.index = _pd.to_datetime(df.index, utc=True).tz_convert(tz_exchange)
df = df.sort_index()

df_repaired = dat._fix_unit_switch(df_bad, interval, tz_exchange)
df_repaired = hist._fix_unit_switch(df_bad, interval, tz_exchange)
df_repaired = df_repaired.sort_index()

# First test - no errors left
Expand Down Expand Up @@ -704,6 +720,7 @@ def test_repair_100x_block_daily(self):
def test_repair_zeroes_daily(self):
tkr = "BBIL.L"
dat = yf.Ticker(tkr, session=self.session)
hist = dat._lazy_load_price_history()
tz_exchange = dat.fast_info["timezone"]

df_bad = _pd.DataFrame(data={"Open": [0, 102.04, 102.04],
Expand All @@ -719,7 +736,7 @@ def test_repair_zeroes_daily(self):
df_bad.index.name = "Date"
df_bad.index = df_bad.index.tz_localize(tz_exchange)

repaired_df = dat._fix_zeroes(df_bad, "1d", tz_exchange, prepost=False)
repaired_df = hist._fix_zeroes(df_bad, "1d", tz_exchange, prepost=False)

correct_df = df_bad.copy()
correct_df.loc["2022-11-01", "Open"] = 102.080002
Expand Down Expand Up @@ -753,6 +770,7 @@ def test_repair_zeroes_daily_adjClose(self):
dat = yf.Ticker(tkr, session=self.session)
tz_exchange = dat.fast_info["timezone"]
df.index = df.index.tz_localize(tz_exchange)
hist = dat._lazy_load_price_history()

rtol = 5e-3
for i in [0, 1, 2]:
Expand All @@ -761,7 +779,7 @@ def test_repair_zeroes_daily_adjClose(self):
df_slice_bad = df_slice.copy()
df_slice_bad.loc[df_slice_bad.index[j], "Adj Close"] = 0.0

df_slice_bad_repaired = dat._fix_zeroes(df_slice_bad, "1d", tz_exchange, prepost=False)
df_slice_bad_repaired = hist._fix_zeroes(df_slice_bad, "1d", tz_exchange, prepost=False)
for c in ["Close", "Adj Close"]:
self.assertTrue(_np.isclose(df_slice_bad_repaired[c], df_slice[c], rtol=rtol).all())
self.assertTrue("Repaired?" in df_slice_bad_repaired.columns)
Expand All @@ -771,8 +789,9 @@ def test_repair_zeroes_hourly(self):
tkr = "INTC"
dat = yf.Ticker(tkr, session=self.session)
tz_exchange = dat.fast_info["timezone"]
hist = dat._lazy_load_price_history()

correct_df = dat.history(period="1wk", interval="1h", auto_adjust=False, repair=True)
correct_df = hist.history(period="1wk", interval="1h", auto_adjust=False, repair=True)

df_bad = correct_df.copy()
bad_idx = correct_df.index[10]
Expand All @@ -783,7 +802,7 @@ def test_repair_zeroes_hourly(self):
df_bad.loc[bad_idx, "Adj Close"] = _np.nan
df_bad.loc[bad_idx, "Volume"] = 0

repaired_df = dat._fix_zeroes(df_bad, "1h", tz_exchange, prepost=False)
repaired_df = hist._fix_zeroes(df_bad, "1h", tz_exchange, prepost=False)

for c in ["Open", "Low", "High", "Close"]:
try:
Expand Down Expand Up @@ -812,11 +831,12 @@ def test_repair_bad_stock_split(self):
for interval in intervals:
dat = yf.Ticker(tkr, session=self.session)
tz_exchange = dat.fast_info["timezone"]
hist = dat._lazy_load_price_history()

_dp = os.path.dirname(__file__)
df_good = dat.history(start='2020-01-01', end=_dt.date.today(), interval=interval, auto_adjust=False)

repaired_df = dat._fix_bad_stock_split(df_good, interval, tz_exchange)
repaired_df = hist._fix_bad_stock_split(df_good, interval, tz_exchange)

# Expect no change from repair
df_good = df_good.sort_index()
Expand All @@ -836,6 +856,7 @@ def test_repair_bad_stock_split(self):
for tkr in bad_tkrs:
dat = yf.Ticker(tkr, session=self.session)
tz_exchange = dat.fast_info["timezone"]
hist = dat._lazy_load_price_history()

_dp = os.path.dirname(__file__)
interval = '1d'
Expand All @@ -846,7 +867,7 @@ def test_repair_bad_stock_split(self):
df_bad = _pd.read_csv(fp, index_col="Date")
df_bad.index = _pd.to_datetime(df_bad.index, utc=True)

repaired_df = dat._fix_bad_stock_split(df_bad, "1d", tz_exchange)
repaired_df = hist._fix_bad_stock_split(df_bad, "1d", tz_exchange)

fp = os.path.join(_dp, "data", tkr.replace('.','-')+'-'+interval+"-bad-stock-split-fixed.csv")
correct_df = _pd.read_csv(fp, index_col="Date")
Expand Down Expand Up @@ -876,11 +897,12 @@ def test_repair_bad_stock_split(self):
for interval in intervals:
dat = yf.Ticker(tkr, session=self.session)
tz_exchange = dat.fast_info["timezone"]
hist = dat._lazy_load_price_history()

_dp = os.path.dirname(__file__)
df_good = dat.history(start='2020-11-30', end='2021-04-01', interval=interval, auto_adjust=False)
df_good = hist.history(start='2020-11-30', end='2021-04-01', interval=interval, auto_adjust=False)

repaired_df = dat._fix_bad_stock_split(df_good, interval, tz_exchange)
repaired_df = hist._fix_bad_stock_split(df_good, interval, tz_exchange)

# Expect no change from repair
df_good = df_good.sort_index()
Expand All @@ -900,12 +922,13 @@ def test_repair_missing_div_adjust(self):

dat = yf.Ticker(tkr, session=self.session)
tz_exchange = dat.fast_info["timezone"]
hist = dat._lazy_load_price_history()

_dp = os.path.dirname(__file__)
df_bad = _pd.read_csv(os.path.join(_dp, "data", tkr.replace('.','-')+"-1d-missing-div-adjust.csv"), index_col="Date")
df_bad.index = _pd.to_datetime(df_bad.index)

repaired_df = dat._fix_missing_div_adjust(df_bad, "1d", tz_exchange)
repaired_df = hist._fix_missing_div_adjust(df_bad, "1d", tz_exchange)

correct_df = _pd.read_csv(os.path.join(_dp, "data", tkr.replace('.','-')+"-1d-missing-div-adjust-fixed.csv"), index_col="Date")
correct_df.index = _pd.to_datetime(correct_df.index)
Expand Down
9 changes: 0 additions & 9 deletions tests/ticker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -247,15 +247,6 @@ def test_actions(self):
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
self.assertFalse(data.empty, "data is empty")

def test_reconstruct_intervals_batch(self):
data = self.ticker.history(period="3mo", interval="1d", prepost=True, repair=True)
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
self.assertFalse(data.empty, "data is empty")

reconstructed = self.ticker._reconstruct_intervals_batch(data, "1wk", True)
self.assertIsInstance(reconstructed, pd.DataFrame, "data has wrong type")
self.assertFalse(data.empty, "data is empty")


class TestTickerEarnings(unittest.TestCase):
session = None
Expand Down
24 changes: 13 additions & 11 deletions tests/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,8 @@
python -m unittest tests.utils.TestTicker

"""
from unittest import TestSuite

# import pandas as pd
# import numpy as np

Expand All @@ -34,16 +36,16 @@ def test_storeTzNoRaise(self):
tkr = 'AMZN'
tz1 = "America/New_York"
tz2 = "London/Europe"
cache = yf.utils.get_tz_cache()
cache = yf.cache.get_tz_cache()
cache.store(tkr, tz1)
cache.store(tkr, tz2)

def test_setTzCacheLocation(self):
self.assertEqual(yf.utils._DBManager.get_location(), self.tempCacheDir.name)
self.assertEqual(yf.cache._TzDBManager.get_location(), self.tempCacheDir.name)

tkr = 'AMZN'
tz1 = "America/New_York"
cache = yf.utils.get_tz_cache()
cache = yf.cache.get_tz_cache()
cache.store(tkr, tz1)

self.assertTrue(os.path.exists(os.path.join(self.tempCacheDir.name, "tkr-tz.db")))
Expand All @@ -60,30 +62,30 @@ def test_tzCacheRootStore(self):
tz1 = "America/New_York"

# During attempt to store, will discover cannot write
yf.utils.get_tz_cache().store(tkr, tz1)
yf.cache.get_tz_cache().store(tkr, tz1)

# Handling the store failure replaces cache with a dummy
cache = yf.utils.get_tz_cache()
cache = yf.cache.get_tz_cache()
self.assertTrue(cache.dummy)
cache.store(tkr, tz1)

def test_tzCacheRootLookup(self):
# Test that if cache path in read-only filesystem, no exception.
tkr = 'AMZN'
# During attempt to lookup, will discover cannot write
yf.utils.get_tz_cache().lookup(tkr)
yf.cache.get_tz_cache().lookup(tkr)

# Handling the lookup failure replaces cache with a dummy
cache = yf.utils.get_tz_cache()
cache = yf.cache.get_tz_cache()
self.assertTrue(cache.dummy)
cache.lookup(tkr)


def suite():
suite = unittest.TestSuite()
suite.addTest(TestCache('Test cache'))
suite.addTest(TestCacheNoPermission('Test cache no permission'))
return suite
ts: TestSuite = unittest.TestSuite()
ts.addTest(TestCache('Test cache'))
ts.addTest(TestCacheNoPermission('Test cache no permission'))
return ts


if __name__ == '__main__':
Expand Down
Loading
Loading