Compare commits
1 Commits
0.2.16
...
feature/si
| Author | SHA1 | Date | |
|---|---|---|---|
|
4bb22d7043 |
35
.github/ISSUE_TEMPLATE/bug_report.md
vendored
35
.github/ISSUE_TEMPLATE/bug_report.md
vendored
@@ -7,37 +7,14 @@ assignees: ''
|
||||
|
||||
---
|
||||
|
||||
# IMPORTANT
|
||||
*** READ BEFORE POSTING ***
|
||||
|
||||
If you want help, you got to read this first, follow the instructions.
|
||||
|
||||
### Are you up-to-date?
|
||||
|
||||
Upgrade to the latest version and confirm the issue/bug is still there.
|
||||
Before posting an issue - please upgrade to the latest version and confirm the issue/bug is still there.
|
||||
|
||||
Upgrade using:
|
||||
`$ pip install yfinance --upgrade --no-cache-dir`
|
||||
|
||||
Confirm by running:
|
||||
Bug still there? Delete this content and submit your bug report here and provide the following, as best you can:
|
||||
|
||||
`import yfinance as yf ; print(yf.__version__)`
|
||||
|
||||
and comparing against [PIP](https://pypi.org/project/yfinance/#history).
|
||||
|
||||
### Does Yahoo actually have the data?
|
||||
|
||||
Are you spelling ticker *exactly* same as Yahoo?
|
||||
|
||||
Then visit `finance.yahoo.com` and confirm they have the data you want. Maybe your ticker was delisted, or your expectations of `yfinance` are wrong.
|
||||
|
||||
### Are you spamming Yahoo?
|
||||
|
||||
Yahoo Finance free service has rate-limiting depending on request type - roughly 60/minute for prices, 10/minute for info. Once limit hit, Yahoo can delay, block, or return bad data. Not a `yfinance` bug.
|
||||
|
||||
### Still think it's a bug?
|
||||
|
||||
Delete this default message (all of it) and submit your bug report here, providing the following as best you can:
|
||||
|
||||
- Simple code that reproduces your problem, that we can copy-paste-run
|
||||
- Exception message with full traceback, or proof `yfinance` returning bad data
|
||||
- `yfinance` version and Python version
|
||||
- Operating system type
|
||||
- Simple code that reproduces your problem
|
||||
- The error message
|
||||
|
||||
14
.github/ISSUE_TEMPLATE/feature_request.md
vendored
14
.github/ISSUE_TEMPLATE/feature_request.md
vendored
@@ -1,14 +0,0 @@
|
||||
---
|
||||
name: Feature request
|
||||
about: Request a new feature
|
||||
title: ''
|
||||
labels: ''
|
||||
assignees: ''
|
||||
|
||||
---
|
||||
|
||||
**Describe the problem**
|
||||
|
||||
**Describe the solution**
|
||||
|
||||
**Additional context**
|
||||
107
CHANGELOG.rst
107
CHANGELOG.rst
@@ -1,113 +1,8 @@
|
||||
Change Log
|
||||
===========
|
||||
|
||||
0.2.16
|
||||
------
|
||||
Fix 'fast_info deprecated' msg appearing at Ticker() init
|
||||
|
||||
0.2.15
|
||||
------
|
||||
Restore missing Ticker.info keys #1480
|
||||
|
||||
0.2.14
|
||||
------
|
||||
Fix Ticker.info dict by fetching from API #1461
|
||||
|
||||
0.2.13
|
||||
------
|
||||
Price bug fixes:
|
||||
- fetch big-interval with Capital Gains #1455
|
||||
- merging dividends & splits with prices #1452
|
||||
|
||||
0.2.12
|
||||
------
|
||||
Disable annoying 'backup decrypt' msg
|
||||
|
||||
0.2.11
|
||||
------
|
||||
Fix history_metadata accesses for unusual symbols #1411
|
||||
|
||||
0.2.10
|
||||
------
|
||||
General
|
||||
- allow using sqlite3 < 3.8.2 #1380
|
||||
- add another backup decrypt option #1379
|
||||
Prices
|
||||
- restore original download() timezone handling #1385
|
||||
- fix & improve price repair #1289 2a2928b 86d6acc
|
||||
- drop intraday intervals if in post-market but prepost=False #1311
|
||||
Info
|
||||
- fast_info improvements:
|
||||
- add camelCase keys, add dict functions values() & items() #1368
|
||||
- fix fast_info["previousClose"] #1383
|
||||
- catch TypeError Exception #1397
|
||||
|
||||
0.2.9
|
||||
-----
|
||||
- Fix fast_info bugs #1362
|
||||
|
||||
0.2.7
|
||||
-----
|
||||
- Fix Yahoo decryption, smarter this time #1353
|
||||
- Rename basic_info -> fast_info #1354
|
||||
|
||||
0.2.6
|
||||
-----
|
||||
- Fix Ticker.basic_info lazy-loading #1342
|
||||
|
||||
0.2.5
|
||||
-----
|
||||
- Fix Yahoo data decryption again #1336
|
||||
- New: Ticker.basic_info - faster Ticker.info #1317
|
||||
|
||||
0.2.4
|
||||
-----
|
||||
- Fix Yahoo data decryption #1297
|
||||
- New feature: 'Ticker.get_shares_full()' #1301
|
||||
- Improve caching of financials data #1284
|
||||
- Restore download() original alignment behaviour #1283
|
||||
- Fix the database lock error in multithread download #1276
|
||||
|
||||
0.2.3
|
||||
-----
|
||||
- Make financials API '_' use consistent
|
||||
|
||||
0.2.2
|
||||
-----
|
||||
- Restore 'financials' attribute (map to 'income_stmt')
|
||||
|
||||
0.2.1
|
||||
-----
|
||||
Release!
|
||||
|
||||
0.2.0rc5
|
||||
--------
|
||||
- Improve financials error handling #1243
|
||||
- Fix '100x price' repair #1244
|
||||
|
||||
0.2.0rc4
|
||||
--------
|
||||
- Access to old financials tables via `get_income_stmt(legacy=True)`
|
||||
- Optimise scraping financials & fundamentals, 2x faster
|
||||
- Add 'capital gains' alongside dividends & splits for ETFs, and metadata available via `history_metadata`, plus a bunch of price fixes
|
||||
For full list of changes see #1238
|
||||
|
||||
0.2.0rc2
|
||||
--------
|
||||
Financials
|
||||
- fix financials tables to match website #1128 #1157
|
||||
- lru_cache to optimise web requests #1147
|
||||
Prices
|
||||
- improve price repair #1148
|
||||
- fix merging dividends/splits with day/week/monthly prices #1161
|
||||
- fix the Yahoo DST fixes #1143
|
||||
- improve bad/delisted ticker handling #1140
|
||||
Misc
|
||||
- fix 'trailingPegRatio' #1138
|
||||
- improve error handling #1118
|
||||
|
||||
0.2.0rc1
|
||||
--------
|
||||
------
|
||||
Jumping to 0.2 for this big update. 0.1.* will continue to receive bug-fixes
|
||||
- timezone cache performance massively improved. Thanks @fredrik-corneliusson #1113 #1112 #1109 #1105 #1099
|
||||
- price repair feature #1110
|
||||
|
||||
212
README.md
212
README.md
@@ -42,11 +42,6 @@ Yahoo! finance API is intended for personal use only.**
|
||||
|
||||
---
|
||||
|
||||
## News [2023-01-27]
|
||||
Since December 2022 Yahoo has been encrypting the web data that `yfinance` scrapes for non-market data. Fortunately the decryption keys are available, although Yahoo moved/changed them several times hence `yfinance` breaking several times. `yfinance` is now better prepared for any future changes by Yahoo.
|
||||
|
||||
Why is Yahoo doing this? We don't know. Is it to stop scrapers? Maybe, so we've implemented changes to reduce load on Yahoo. In December we rolled out version 0.2 with optimised scraping. ~Then in 0.2.6 introduced `Ticker.fast_info`, providing much faster access to some `info` elements wherever possible e.g. price stats and forcing users to switch (sorry but we think necessary). `info` will continue to exist for as long as there are elements without a fast alternative.~ `info` now fixed and much faster than before.
|
||||
|
||||
## Quick Start
|
||||
|
||||
### The Ticker module
|
||||
@@ -58,42 +53,47 @@ import yfinance as yf
|
||||
|
||||
msft = yf.Ticker("MSFT")
|
||||
|
||||
# get all stock info
|
||||
# get stock info
|
||||
msft.info
|
||||
|
||||
# get historical market data
|
||||
hist = msft.history(period="1mo")
|
||||
|
||||
# show meta information about the history (requires history() to be called first)
|
||||
msft.history_metadata
|
||||
hist = msft.history(period="max")
|
||||
|
||||
# show actions (dividends, splits, capital gains)
|
||||
msft.actions
|
||||
|
||||
# show dividends
|
||||
msft.dividends
|
||||
|
||||
# show splits
|
||||
msft.splits
|
||||
msft.capital_gains # only for mutual funds & etfs
|
||||
|
||||
|
||||
# show capital gains (for mutual funds & etfs)
|
||||
msft.capital_gains
|
||||
|
||||
# show share count
|
||||
# - yearly summary:
|
||||
msft.shares
|
||||
# - accurate time-series count:
|
||||
msft.get_shares_full(start="2022-01-01", end=None)
|
||||
|
||||
# show financials:
|
||||
# - income statement
|
||||
# show income statement
|
||||
msft.income_stmt
|
||||
msft.quarterly_income_stmt
|
||||
# - balance sheet
|
||||
|
||||
# show balance sheet
|
||||
msft.balance_sheet
|
||||
msft.quarterly_balance_sheet
|
||||
# - cash flow statement
|
||||
|
||||
# show cash flow statement
|
||||
msft.cashflow
|
||||
msft.quarterly_cashflow
|
||||
# see `Ticker.get_income_stmt()` for more options
|
||||
|
||||
# show holders
|
||||
# show major holders
|
||||
msft.major_holders
|
||||
|
||||
# show institutional holders
|
||||
msft.institutional_holders
|
||||
|
||||
# show mutualfund holders
|
||||
msft.mutualfund_holders
|
||||
|
||||
# show earnings
|
||||
@@ -108,9 +108,9 @@ msft.recommendations
|
||||
msft.recommendations_summary
|
||||
# show analysts other work
|
||||
msft.analyst_price_target
|
||||
msft.revenue_forecasts
|
||||
msft.earnings_forecasts
|
||||
msft.earnings_trend
|
||||
mfst.revenue_forecasts
|
||||
mfst.earnings_forecasts
|
||||
mfst.earnings_trend
|
||||
|
||||
# show next event (earnings, etc)
|
||||
msft.calendar
|
||||
@@ -152,42 +152,6 @@ msft.option_chain(..., proxy="PROXY_SERVER")
|
||||
...
|
||||
```
|
||||
|
||||
### Multiple tickers
|
||||
|
||||
To initialize multiple `Ticker` objects, use
|
||||
|
||||
```python
|
||||
import yfinance as yf
|
||||
|
||||
tickers = yf.Tickers('msft aapl goog')
|
||||
|
||||
# access each ticker using (example)
|
||||
tickers.tickers['MSFT'].info
|
||||
tickers.tickers['AAPL'].history(period="1mo")
|
||||
tickers.tickers['GOOG'].actions
|
||||
```
|
||||
|
||||
To download price history into one table:
|
||||
|
||||
```python
|
||||
import yfinance as yf
|
||||
data = yf.download("SPY AAPL", start="2017-01-01", end="2017-04-30")
|
||||
```
|
||||
|
||||
`yf.download()` and `Ticker.history()` have many options for configuring fetching and processing, e.g.:
|
||||
|
||||
```python
|
||||
yf.download(tickers = "SPY AAPL", # list of tickers
|
||||
period = "1y", # time period
|
||||
interval = "1d", # trading interval
|
||||
prepost = False, # download pre/post market hours data?
|
||||
repair = True) # repair obvious price errors e.g. 100x?
|
||||
```
|
||||
|
||||
Review the [Wiki](https://github.com/ranaroussi/yfinance/wiki) for more options and detail.
|
||||
|
||||
### Smarter scraping
|
||||
|
||||
To use a custom `requests` session (for example to cache calls to the
|
||||
API or customize the `User-agent` header), pass a `session=` argument to
|
||||
the Ticker constructor.
|
||||
@@ -196,25 +160,89 @@ the Ticker constructor.
|
||||
import requests_cache
|
||||
session = requests_cache.CachedSession('yfinance.cache')
|
||||
session.headers['User-agent'] = 'my-program/1.0'
|
||||
ticker = yf.Ticker('msft', session=session)
|
||||
ticker = yf.Ticker('msft aapl goog', session=session)
|
||||
# The scraped response will be stored in the cache
|
||||
ticker.actions
|
||||
```
|
||||
|
||||
Combine a `requests_cache` with rate-limiting to avoid triggering Yahoo's rate-limiter/blocker that can corrupt data.
|
||||
```python
|
||||
from requests import Session
|
||||
from requests_cache import CacheMixin, SQLiteCache
|
||||
from requests_ratelimiter import LimiterMixin, MemoryQueueBucket
|
||||
from pyrate_limiter import Duration, RequestRate, Limiter
|
||||
class CachedLimiterSession(CacheMixin, LimiterMixin, Session):
|
||||
pass
|
||||
To initialize multiple `Ticker` objects, use
|
||||
|
||||
session = CachedLimiterSession(
|
||||
limiter=Limiter(RequestRate(2, Duration.SECOND*5), # max 2 requests per 5 seconds
|
||||
bucket_class=MemoryQueueBucket,
|
||||
backend=SQLiteCache("yfinance.cache"),
|
||||
)
|
||||
```python
|
||||
import yfinance as yf
|
||||
|
||||
tickers = yf.Tickers('msft aapl goog')
|
||||
# ^ returns a named tuple of Ticker objects
|
||||
|
||||
# access each ticker using (example)
|
||||
tickers.tickers['MSFT'].info
|
||||
tickers.tickers['AAPL'].history(period="1mo")
|
||||
tickers.tickers['GOOG'].actions
|
||||
```
|
||||
|
||||
### Fetching data for multiple tickers
|
||||
|
||||
```python
|
||||
import yfinance as yf
|
||||
data = yf.download("SPY AAPL", start="2017-01-01", end="2017-04-30")
|
||||
```
|
||||
|
||||
I've also added some options to make life easier :)
|
||||
|
||||
```python
|
||||
data = yf.download( # or pdr.get_data_yahoo(...
|
||||
# tickers list or string as well
|
||||
tickers = "SPY AAPL MSFT",
|
||||
|
||||
# use "period" instead of start/end
|
||||
# valid periods: 1d,5d,1mo,3mo,6mo,1y,2y,5y,10y,ytd,max
|
||||
# (optional, default is '1mo')
|
||||
period = "ytd",
|
||||
|
||||
# fetch data by interval (including intraday if period < 60 days)
|
||||
# valid intervals: 1m,2m,5m,15m,30m,60m,90m,1h,1d,5d,1wk,1mo,3mo
|
||||
# (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',
|
||||
|
||||
# adjust all OHLC automatically
|
||||
# (optional, default is False)
|
||||
auto_adjust = True,
|
||||
|
||||
# identify and attempt repair of currency unit mixups e.g. $/cents
|
||||
repair = False,
|
||||
|
||||
# download pre/post regular market hours data
|
||||
# (optional, default is False)
|
||||
prepost = True,
|
||||
|
||||
# use threads for mass downloading? (True/False/Integer)
|
||||
# (optional, default is True)
|
||||
threads = True,
|
||||
|
||||
# proxy URL scheme use use when downloading?
|
||||
# (optional, default is None)
|
||||
proxy = None
|
||||
)
|
||||
```
|
||||
|
||||
### Timezone cache store
|
||||
|
||||
When fetching price data, all dates are localized to stock exchange timezone.
|
||||
But timezone retrieval is relatively slow, so yfinance attemps to cache them
|
||||
in your users cache folder.
|
||||
You can direct cache to use a different location with `set_tz_cache_location()`:
|
||||
```python
|
||||
import yfinance as yf
|
||||
yf.set_tz_cache_location("custom/cache/location")
|
||||
...
|
||||
```
|
||||
|
||||
### Managing Multi-Level Columns
|
||||
@@ -232,7 +260,9 @@ yfinance?](https://stackoverflow.com/questions/63107801)
|
||||
- How to download single or multiple tickers into a single
|
||||
dataframe with single level column names and a ticker column
|
||||
|
||||
### `pandas_datareader` override
|
||||
---
|
||||
|
||||
## `pandas_datareader` override
|
||||
|
||||
If your code uses `pandas_datareader` and you want to download data
|
||||
faster, you can "hijack" `pandas_datareader.data.get_data_yahoo()`
|
||||
@@ -249,18 +279,6 @@ yf.pdr_override() # <== that's all it takes :-)
|
||||
data = pdr.get_data_yahoo("SPY", start="2017-01-01", end="2017-04-30")
|
||||
```
|
||||
|
||||
### Timezone cache store
|
||||
|
||||
When fetching price data, all dates are localized to stock exchange timezone.
|
||||
But timezone retrieval is relatively slow, so yfinance attemps to cache them
|
||||
in your users cache folder.
|
||||
You can direct cache to use a different location with `set_tz_cache_location()`:
|
||||
```python
|
||||
import yfinance as yf
|
||||
yf.set_tz_cache_location("custom/cache/location")
|
||||
...
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Installation
|
||||
@@ -277,26 +295,18 @@ To install `yfinance` using `conda`, see
|
||||
### Requirements
|
||||
|
||||
- [Python](https://www.python.org) \>= 2.7, 3.4+
|
||||
- [Pandas](https://github.com/pydata/pandas) \>= 1.3.0
|
||||
- [Numpy](http://www.numpy.org) \>= 1.16.5
|
||||
- [requests](http://docs.python-requests.org/en/master) \>= 2.26
|
||||
- [lxml](https://pypi.org/project/lxml) \>= 4.9.1
|
||||
- [appdirs](https://pypi.org/project/appdirs) \>= 1.4.4
|
||||
- [pytz](https://pypi.org/project/pytz) \>=2022.5
|
||||
- [frozendict](https://pypi.org/project/frozendict) \>= 2.3.4
|
||||
- [beautifulsoup4](https://pypi.org/project/beautifulsoup4) \>= 4.11.1
|
||||
- [html5lib](https://pypi.org/project/html5lib) \>= 1.1
|
||||
- [cryptography](https://pypi.org/project/cryptography) \>= 3.3.2
|
||||
- [Pandas](https://github.com/pydata/pandas) (tested to work with
|
||||
\>=0.23.1)
|
||||
- [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`)
|
||||
### Optional (if you want to use `pandas_datareader`)
|
||||
|
||||
- [pandas\_datareader](https://github.com/pydata/pandas-datareader)
|
||||
\>= 0.4.0
|
||||
|
||||
## Developers: want to contribute?
|
||||
|
||||
`yfinance` relies on community to investigate bugs and contribute code. Developer guide: https://github.com/ranaroussi/yfinance/discussions/1084
|
||||
|
||||
---
|
||||
|
||||
### Legal Stuff
|
||||
|
||||
30
meta.yaml
30
meta.yaml
@@ -1,5 +1,5 @@
|
||||
{% set name = "yfinance" %}
|
||||
{% set version = "0.2.16" %}
|
||||
{% set version = "0.1.58" %}
|
||||
|
||||
package:
|
||||
name: "{{ name|lower }}"
|
||||
@@ -16,34 +16,22 @@ build:
|
||||
|
||||
requirements:
|
||||
host:
|
||||
- pandas >=1.3.0
|
||||
- pandas >=0.24.0
|
||||
- numpy >=1.16.5
|
||||
- requests >=2.26
|
||||
- requests >=2.21
|
||||
- multitasking >=0.0.7
|
||||
- lxml >=4.9.1
|
||||
- appdirs >=1.4.4
|
||||
- pytz >=2022.5
|
||||
- frozendict >=2.3.4
|
||||
- beautifulsoup4 >=4.11.1
|
||||
- html5lib >=1.1
|
||||
# - pycryptodome >=3.6.6
|
||||
- cryptography >=3.3.2
|
||||
- lxml >=4.5.1
|
||||
- appdirs >= 1.4.4
|
||||
- pip
|
||||
- python
|
||||
|
||||
run:
|
||||
- pandas >=1.3.0
|
||||
- pandas >=0.24.0
|
||||
- numpy >=1.16.5
|
||||
- requests >=2.26
|
||||
- requests >=2.21
|
||||
- multitasking >=0.0.7
|
||||
- lxml >=4.9.1
|
||||
- appdirs >=1.4.4
|
||||
- pytz >=2022.5
|
||||
- frozendict >=2.3.4
|
||||
- beautifulsoup4 >=4.11.1
|
||||
- html5lib >=1.1
|
||||
# - pycryptodome >=3.6.6
|
||||
- cryptography >=3.3.2
|
||||
- lxml >=4.5.1
|
||||
- appdirs >= 1.4.4
|
||||
- python
|
||||
|
||||
test:
|
||||
|
||||
@@ -1,11 +1,10 @@
|
||||
pandas>=1.3.0
|
||||
pandas>=1.1.0
|
||||
numpy>=1.16.5
|
||||
requests>=2.26
|
||||
multitasking>=0.0.7
|
||||
lxml>=4.9.1
|
||||
lxml>=4.5.1
|
||||
appdirs>=1.4.4
|
||||
pytz>=2022.5
|
||||
frozendict>=2.3.4
|
||||
beautifulsoup4>=4.11.1
|
||||
html5lib>=1.1
|
||||
cryptography>=3.3.2
|
||||
|
||||
8
setup.py
8
setup.py
@@ -59,12 +59,10 @@ setup(
|
||||
platforms=['any'],
|
||||
keywords='pandas, yahoo finance, pandas datareader',
|
||||
packages=find_packages(exclude=['contrib', 'docs', 'tests', 'examples']),
|
||||
install_requires=['pandas>=1.3.0', 'numpy>=1.16.5',
|
||||
install_requires=['pandas>=1.1.0', 'numpy>=1.15',
|
||||
'requests>=2.26', 'multitasking>=0.0.7',
|
||||
'lxml>=4.9.1', 'appdirs>=1.4.4', 'pytz>=2022.5',
|
||||
'frozendict>=2.3.4',
|
||||
# 'pycryptodome>=3.6.6',
|
||||
'cryptography>=3.3.2',
|
||||
'lxml>=4.5.1', 'appdirs>=1.4.4', 'pytz>=2022.5',
|
||||
'frozendict>=2.3.4',
|
||||
'beautifulsoup4>=4.11.1', 'html5lib>=1.1'],
|
||||
entry_points={
|
||||
'console_scripts': [
|
||||
|
||||
314
tests/prices.py
314
tests/prices.py
@@ -24,7 +24,9 @@ class TestPriceHistory(unittest.TestCase):
|
||||
|
||||
def test_daily_index(self):
|
||||
tkrs = ["BHP.AX", "IMP.JO", "BP.L", "PNL.L", "INTC"]
|
||||
|
||||
intervals = ["1d", "1wk", "1mo"]
|
||||
|
||||
for tkr in tkrs:
|
||||
dat = yf.Ticker(tkr, session=self.session)
|
||||
|
||||
@@ -34,25 +36,6 @@ class TestPriceHistory(unittest.TestCase):
|
||||
f = df.index.time == _dt.time(0)
|
||||
self.assertTrue(f.all())
|
||||
|
||||
def test_duplicatingHourly(self):
|
||||
tkrs = ["IMP.JO", "BHG.JO", "SSW.JO", "BP.L", "INTC"]
|
||||
for tkr in tkrs:
|
||||
dat = yf.Ticker(tkr, session=self.session)
|
||||
tz = dat._get_ticker_tz(debug_mode=False, proxy=None, timeout=None)
|
||||
|
||||
dt_utc = _tz.timezone("UTC").localize(_dt.datetime.utcnow())
|
||||
dt = dt_utc.astimezone(_tz.timezone(tz))
|
||||
start_d = dt.date() - _dt.timedelta(days=7)
|
||||
df = dat.history(start=start_d, interval="1h")
|
||||
|
||||
dt0 = df.index[-2]
|
||||
dt1 = df.index[-1]
|
||||
try:
|
||||
self.assertNotEqual(dt0.hour, dt1.hour)
|
||||
except:
|
||||
print("Ticker = ", tkr)
|
||||
raise
|
||||
|
||||
def test_duplicatingDaily(self):
|
||||
tkrs = ["IMP.JO", "BHG.JO", "SSW.JO", "BP.L", "INTC"]
|
||||
test_run = False
|
||||
@@ -107,27 +90,22 @@ class TestPriceHistory(unittest.TestCase):
|
||||
def test_intraDayWithEvents(self):
|
||||
# TASE dividend release pre-market, doesn't merge nicely with intra-day data so check still present
|
||||
|
||||
tase_tkrs = ["ICL.TA", "ESLT.TA", "ONE.TA", "MGDL.TA"]
|
||||
test_run = False
|
||||
for tkr in tase_tkrs:
|
||||
start_d = _dt.date.today() - _dt.timedelta(days=59)
|
||||
end_d = None
|
||||
df_daily = yf.Ticker(tkr, session=self.session).history(start=start_d, end=end_d, interval="1d", actions=True)
|
||||
df_daily_divs = df_daily["Dividends"][df_daily["Dividends"] != 0]
|
||||
if df_daily_divs.shape[0] == 0:
|
||||
# self.skipTest("Skipping test_intraDayWithEvents() because 'ICL.TA' has no dividend in last 60 days")
|
||||
continue
|
||||
tkr = "ICL.TA"
|
||||
# tkr = "ESLT.TA"
|
||||
# tkr = "ONE.TA"
|
||||
# tkr = "MGDL.TA"
|
||||
start_d = _dt.date.today() - _dt.timedelta(days=60)
|
||||
end_d = None
|
||||
df_daily = yf.Ticker(tkr, session=self.session).history(start=start_d, end=end_d, interval="1d", actions=True)
|
||||
df_daily_divs = df_daily["Dividends"][df_daily["Dividends"] != 0]
|
||||
if df_daily_divs.shape[0] == 0:
|
||||
self.skipTest("Skipping test_intraDayWithEvents() because 'ICL.TA' has no dividend in last 60 days")
|
||||
|
||||
last_div_date = df_daily_divs.index[-1]
|
||||
start_d = last_div_date.date()
|
||||
end_d = last_div_date.date() + _dt.timedelta(days=1)
|
||||
df = yf.Ticker(tkr, session=self.session).history(start=start_d, end=end_d, interval="15m", actions=True)
|
||||
self.assertTrue((df["Dividends"] != 0.0).any())
|
||||
test_run = True
|
||||
break
|
||||
|
||||
if not test_run:
|
||||
self.skipTest("Skipping test_intraDayWithEvents() because no tickers had a dividend in last 60 days")
|
||||
last_div_date = df_daily_divs.index[-1]
|
||||
start_d = last_div_date.date()
|
||||
end_d = last_div_date.date() + _dt.timedelta(days=1)
|
||||
df = yf.Ticker(tkr, session=self.session).history(start=start_d, end=end_d, interval="15m", actions=True)
|
||||
self.assertTrue((df["Dividends"] != 0.0).any())
|
||||
|
||||
def test_dailyWithEvents(self):
|
||||
# Reproduce issue #521
|
||||
@@ -230,13 +208,9 @@ class TestPriceHistory(unittest.TestCase):
|
||||
print("{}-without-events missing these dates: {}".format(tkr, missing_from_df2))
|
||||
raise
|
||||
|
||||
def test_monthlyWithEvents2(self):
|
||||
# Simply check no exception from internal merge
|
||||
tkr = "ABBV"
|
||||
yf.Ticker("ABBV").history(period="max", interval="1mo")
|
||||
|
||||
def test_tz_dst_ambiguous(self):
|
||||
# Reproduce issue #1100
|
||||
|
||||
try:
|
||||
yf.Ticker("ESLT.TA", session=self.session).history(start="2002-10-06", end="2002-10-09", interval="1d")
|
||||
except _tz.exceptions.AmbiguousTimeError:
|
||||
@@ -267,116 +241,6 @@ class TestPriceHistory(unittest.TestCase):
|
||||
print("Weekly data not aligned to Monday")
|
||||
raise
|
||||
|
||||
def test_prune_post_intraday_us(self):
|
||||
# Half-day before USA Thanksgiving. Yahoo normally
|
||||
# returns an interval starting when regular trading closes,
|
||||
# even if prepost=False.
|
||||
|
||||
# Setup
|
||||
tkr = "AMZN"
|
||||
interval = "1h"
|
||||
interval_td = _dt.timedelta(hours=1)
|
||||
time_open = _dt.time(9, 30)
|
||||
time_close = _dt.time(16)
|
||||
special_day = _dt.date(2022, 11, 25)
|
||||
time_early_close = _dt.time(13)
|
||||
dat = yf.Ticker(tkr, session=self.session)
|
||||
|
||||
# Run
|
||||
start_d = special_day - _dt.timedelta(days=7)
|
||||
end_d = special_day + _dt.timedelta(days=7)
|
||||
df = dat.history(start=start_d, end=end_d, interval=interval, prepost=False, keepna=True)
|
||||
tg_last_dt = df.loc[str(special_day)].index[-1]
|
||||
self.assertTrue(tg_last_dt.time() < time_early_close)
|
||||
|
||||
# Test no other afternoons (or mornings) were pruned
|
||||
start_d = _dt.date(special_day.year, 1, 1)
|
||||
end_d = _dt.date(special_day.year+1, 1, 1)
|
||||
df = dat.history(start=start_d, end=end_d, interval="1h", prepost=False, keepna=True)
|
||||
last_dts = _pd.Series(df.index).groupby(df.index.date).last()
|
||||
f_early_close = (last_dts+interval_td).dt.time < time_close
|
||||
early_close_dates = last_dts.index[f_early_close].values
|
||||
self.assertEqual(len(early_close_dates), 1)
|
||||
self.assertEqual(early_close_dates[0], special_day)
|
||||
|
||||
first_dts = _pd.Series(df.index).groupby(df.index.date).first()
|
||||
f_late_open = first_dts.dt.time > time_open
|
||||
late_open_dates = first_dts.index[f_late_open]
|
||||
self.assertEqual(len(late_open_dates), 0)
|
||||
|
||||
def test_prune_post_intraday_omx(self):
|
||||
# Half-day before Sweden Christmas. Yahoo normally
|
||||
# returns an interval starting when regular trading closes,
|
||||
# even if prepost=False.
|
||||
# If prepost=False, test that yfinance is removing prepost intervals.
|
||||
|
||||
# Setup
|
||||
tkr = "AEC.ST"
|
||||
interval = "1h"
|
||||
interval_td = _dt.timedelta(hours=1)
|
||||
time_open = _dt.time(9)
|
||||
time_close = _dt.time(17,30)
|
||||
special_day = _dt.date(2022, 12, 23)
|
||||
time_early_close = _dt.time(13, 2)
|
||||
dat = yf.Ticker(tkr, session=self.session)
|
||||
|
||||
# Half trading day Jan 5, Apr 14, May 25, Jun 23, Nov 4, Dec 23, Dec 30
|
||||
half_days = [_dt.date(special_day.year, x[0], x[1]) for x in [(1,5), (4,14), (5,25), (6,23), (11,4), (12,23), (12,30)]]
|
||||
|
||||
# Yahoo has incorrectly classified afternoon of 2022-04-13 as post-market.
|
||||
# Nothing yfinance can do because Yahoo doesn't return data with prepost=False.
|
||||
# But need to handle in this test.
|
||||
expected_incorrect_half_days = [_dt.date(2022,4,13)]
|
||||
half_days = sorted(half_days+expected_incorrect_half_days)
|
||||
|
||||
# Run
|
||||
start_d = special_day - _dt.timedelta(days=7)
|
||||
end_d = special_day + _dt.timedelta(days=7)
|
||||
df = dat.history(start=start_d, end=end_d, interval=interval, prepost=False, keepna=True)
|
||||
tg_last_dt = df.loc[str(special_day)].index[-1]
|
||||
self.assertTrue(tg_last_dt.time() < time_early_close)
|
||||
|
||||
# Test no other afternoons (or mornings) were pruned
|
||||
start_d = _dt.date(special_day.year, 1, 1)
|
||||
end_d = _dt.date(special_day.year+1, 1, 1)
|
||||
df = dat.history(start=start_d, end=end_d, interval="1h", prepost=False, keepna=True)
|
||||
last_dts = _pd.Series(df.index).groupby(df.index.date).last()
|
||||
f_early_close = (last_dts+interval_td).dt.time < time_close
|
||||
early_close_dates = last_dts.index[f_early_close].values
|
||||
unexpected_early_close_dates = [d for d in early_close_dates if not d in half_days]
|
||||
self.assertEqual(len(unexpected_early_close_dates), 0)
|
||||
self.assertEqual(len(early_close_dates), len(half_days))
|
||||
self.assertTrue(_np.equal(early_close_dates, half_days).all())
|
||||
|
||||
first_dts = _pd.Series(df.index).groupby(df.index.date).first()
|
||||
f_late_open = first_dts.dt.time > time_open
|
||||
late_open_dates = first_dts.index[f_late_open]
|
||||
self.assertEqual(len(late_open_dates), 0)
|
||||
|
||||
def test_prune_post_intraday_asx(self):
|
||||
# Setup
|
||||
tkr = "BHP.AX"
|
||||
interval = "1h"
|
||||
interval_td = _dt.timedelta(hours=1)
|
||||
time_open = _dt.time(10)
|
||||
time_close = _dt.time(16,12)
|
||||
# No early closes in 2022
|
||||
dat = yf.Ticker(tkr, session=self.session)
|
||||
|
||||
# Test no afternoons (or mornings) were pruned
|
||||
start_d = _dt.date(2022, 1, 1)
|
||||
end_d = _dt.date(2022+1, 1, 1)
|
||||
df = dat.history(start=start_d, end=end_d, interval="1h", prepost=False, keepna=True)
|
||||
last_dts = _pd.Series(df.index).groupby(df.index.date).last()
|
||||
f_early_close = (last_dts+interval_td).dt.time < time_close
|
||||
early_close_dates = last_dts.index[f_early_close].values
|
||||
self.assertEqual(len(early_close_dates), 0)
|
||||
|
||||
first_dts = _pd.Series(df.index).groupby(df.index.date).first()
|
||||
f_late_open = first_dts.dt.time > time_open
|
||||
late_open_dates = first_dts.index[f_late_open]
|
||||
self.assertEqual(len(late_open_dates), 0)
|
||||
|
||||
def test_weekly_2rows_fix(self):
|
||||
tkr = "AMZN"
|
||||
start = _dt.date.today() - _dt.timedelta(days=14)
|
||||
@@ -386,53 +250,15 @@ class TestPriceHistory(unittest.TestCase):
|
||||
df = dat.history(start=start, interval="1wk")
|
||||
self.assertTrue((df.index.weekday == 0).all())
|
||||
|
||||
def test_aggregate_capital_gains(self):
|
||||
# Setup
|
||||
tkr = "FXAIX"
|
||||
dat = yf.Ticker(tkr, session=self.session)
|
||||
start = "2017-12-31"
|
||||
end = "2019-12-31"
|
||||
interval = "3mo"
|
||||
def test_repair_weekly_100x(self):
|
||||
# Sometimes, Yahoo returns prices 100x the correct value.
|
||||
# Suspect mixup between £/pence or $/cents etc.
|
||||
# E.g. ticker PNL.L
|
||||
|
||||
df = dat.history(start=start, end=end, interval=interval)
|
||||
|
||||
class TestPriceRepair(unittest.TestCase):
|
||||
session = None
|
||||
|
||||
@classmethod
|
||||
def setUpClass(cls):
|
||||
cls.session = requests_cache.CachedSession(backend='memory')
|
||||
|
||||
@classmethod
|
||||
def tearDownClass(cls):
|
||||
if cls.session is not None:
|
||||
cls.session.close()
|
||||
|
||||
def test_reconstruct_2m(self):
|
||||
# 2m repair requires 1m data.
|
||||
# Yahoo restricts 1m fetches to 7 days max within last 30 days.
|
||||
# Need to test that '_reconstruct_intervals_batch()' can handle this.
|
||||
|
||||
tkrs = ["BHP.AX", "IMP.JO", "BP.L", "PNL.L", "INTC"]
|
||||
|
||||
dt_now = _pd.Timestamp.utcnow()
|
||||
td_7d = _dt.timedelta(days=7)
|
||||
td_60d = _dt.timedelta(days=60)
|
||||
|
||||
# Round time for 'requests_cache' reuse
|
||||
dt_now = dt_now.ceil("1h")
|
||||
|
||||
for tkr in tkrs:
|
||||
dat = yf.Ticker(tkr, session=self.session)
|
||||
end_dt = dt_now
|
||||
start_dt = end_dt - td_60d
|
||||
df = dat.history(start=start_dt, end=end_dt, interval="2m", repair=True)
|
||||
|
||||
def test_repair_100x_weekly(self):
|
||||
# Setup:
|
||||
tkr = "PNL.L"
|
||||
dat = yf.Ticker(tkr, session=self.session)
|
||||
tz_exchange = dat.fast_info["timezone"]
|
||||
tz_exchange = dat.info["exchangeTimezoneName"]
|
||||
|
||||
data_cols = ["Low", "High", "Open", "Close", "Adj Close"]
|
||||
df = _pd.DataFrame(data={"Open": [470.5, 473.5, 474.5, 470],
|
||||
@@ -441,32 +267,25 @@ class TestPriceRepair(unittest.TestCase):
|
||||
"Close": [475, 473.5, 472, 473.5],
|
||||
"Adj Close": [475, 473.5, 472, 473.5],
|
||||
"Volume": [2295613, 2245604, 3000287, 2635611]},
|
||||
index=_pd.to_datetime([_dt.date(2022, 10, 24),
|
||||
_dt.date(2022, 10, 17),
|
||||
_dt.date(2022, 10, 10),
|
||||
_dt.date(2022, 10, 3)]))
|
||||
df = df.sort_index()
|
||||
index=_pd.to_datetime([_dt.date(2022, 10, 23),
|
||||
_dt.date(2022, 10, 16),
|
||||
_dt.date(2022, 10, 9),
|
||||
_dt.date(2022, 10, 2)]))
|
||||
df.index.name = "Date"
|
||||
df_bad = df.copy()
|
||||
df_bad.loc["2022-10-24", "Close"] *= 100
|
||||
df_bad.loc["2022-10-17", "Low"] *= 100
|
||||
df_bad.loc["2022-10-03", "Open"] *= 100
|
||||
df_bad.loc["2022-10-23", "Close"] *= 100
|
||||
df_bad.loc["2022-10-16", "Low"] *= 100
|
||||
df_bad.loc["2022-10-2", "Open"] *= 100
|
||||
df.index = df.index.tz_localize(tz_exchange)
|
||||
df_bad.index = df_bad.index.tz_localize(tz_exchange)
|
||||
|
||||
# Run test
|
||||
|
||||
df_repaired = dat._fix_unit_mixups(df_bad, "1wk", tz_exchange, prepost=False)
|
||||
df_repaired = dat._fix_unit_mixups(df_bad, "1wk", tz_exchange)
|
||||
|
||||
# First test - no errors left
|
||||
for c in data_cols:
|
||||
try:
|
||||
self.assertTrue(_np.isclose(df_repaired[c], df[c], rtol=1e-2).all())
|
||||
except:
|
||||
print(df[c])
|
||||
print(df_repaired[c])
|
||||
raise
|
||||
|
||||
self.assertTrue(_np.isclose(df_repaired[c], df[c], rtol=1e-2).all())
|
||||
|
||||
# Second test - all differences should be either ~1x or ~100x
|
||||
ratio = df_bad[data_cols].values / df[data_cols].values
|
||||
@@ -479,12 +298,16 @@ class TestPriceRepair(unittest.TestCase):
|
||||
f_1 = ratio == 1
|
||||
self.assertTrue((f_100 | f_1).all())
|
||||
|
||||
def test_repair_100x_weekly_preSplit(self):
|
||||
def test_repair_weekly_preSplit_100x(self):
|
||||
# Sometimes, Yahoo returns prices 100x the correct value.
|
||||
# Suspect mixup between £/pence or $/cents etc.
|
||||
# E.g. ticker PNL.L
|
||||
|
||||
# PNL.L has a stock-split in 2022. Sometimes requesting data before 2022 is not split-adjusted.
|
||||
|
||||
tkr = "PNL.L"
|
||||
dat = yf.Ticker(tkr, session=self.session)
|
||||
tz_exchange = dat.fast_info["timezone"]
|
||||
tz_exchange = dat.info["exchangeTimezoneName"]
|
||||
|
||||
data_cols = ["Low", "High", "Open", "Close", "Adj Close"]
|
||||
df = _pd.DataFrame(data={"Open": [400, 398, 392.5, 417],
|
||||
@@ -497,7 +320,6 @@ class TestPriceRepair(unittest.TestCase):
|
||||
_dt.date(2020, 3, 23),
|
||||
_dt.date(2020, 3, 16),
|
||||
_dt.date(2020, 3, 9)]))
|
||||
df = df.sort_index()
|
||||
# Simulate data missing split-adjustment:
|
||||
df[data_cols] *= 100.0
|
||||
df["Volume"] *= 0.01
|
||||
@@ -511,7 +333,7 @@ class TestPriceRepair(unittest.TestCase):
|
||||
df.index = df.index.tz_localize(tz_exchange)
|
||||
df_bad.index = df_bad.index.tz_localize(tz_exchange)
|
||||
|
||||
df_repaired = dat._fix_unit_mixups(df_bad, "1wk", tz_exchange, prepost=False)
|
||||
df_repaired = dat._fix_unit_mixups(df_bad, "1wk", tz_exchange)
|
||||
|
||||
# First test - no errors left
|
||||
for c in data_cols:
|
||||
@@ -536,10 +358,14 @@ class TestPriceRepair(unittest.TestCase):
|
||||
f_1 = ratio == 1
|
||||
self.assertTrue((f_100 | f_1).all())
|
||||
|
||||
def test_repair_100x_daily(self):
|
||||
def test_repair_daily_100x(self):
|
||||
# Sometimes, Yahoo returns prices 100x the correct value.
|
||||
# Suspect mixup between £/pence or $/cents etc.
|
||||
# E.g. ticker PNL.L
|
||||
|
||||
tkr = "PNL.L"
|
||||
dat = yf.Ticker(tkr, session=self.session)
|
||||
tz_exchange = dat.fast_info["timezone"]
|
||||
tz_exchange = dat.info["exchangeTimezoneName"]
|
||||
|
||||
data_cols = ["Low", "High", "Open", "Close", "Adj Close"]
|
||||
df = _pd.DataFrame(data={"Open": [478, 476, 476, 472],
|
||||
@@ -552,7 +378,6 @@ class TestPriceRepair(unittest.TestCase):
|
||||
_dt.date(2022, 10, 31),
|
||||
_dt.date(2022, 10, 28),
|
||||
_dt.date(2022, 10, 27)]))
|
||||
df = df.sort_index()
|
||||
df.index.name = "Date"
|
||||
df_bad = df.copy()
|
||||
df_bad.loc["2022-11-01", "Close"] *= 100
|
||||
@@ -561,7 +386,7 @@ class TestPriceRepair(unittest.TestCase):
|
||||
df.index = df.index.tz_localize(tz_exchange)
|
||||
df_bad.index = df_bad.index.tz_localize(tz_exchange)
|
||||
|
||||
df_repaired = dat._fix_unit_mixups(df_bad, "1d", tz_exchange, prepost=False)
|
||||
df_repaired = dat._fix_unit_mixups(df_bad, "1d", tz_exchange)
|
||||
|
||||
# First test - no errors left
|
||||
for c in data_cols:
|
||||
@@ -578,10 +403,13 @@ class TestPriceRepair(unittest.TestCase):
|
||||
f_1 = ratio == 1
|
||||
self.assertTrue((f_100 | f_1).all())
|
||||
|
||||
def test_repair_zeroes_daily(self):
|
||||
def test_repair_daily_zeroes(self):
|
||||
# Sometimes Yahoo returns price=0.0 when price obviously not zero
|
||||
# E.g. ticker BBIL.L
|
||||
|
||||
tkr = "BBIL.L"
|
||||
dat = yf.Ticker(tkr, session=self.session)
|
||||
tz_exchange = dat.fast_info["timezone"]
|
||||
tz_exchange = dat.info["exchangeTimezoneName"]
|
||||
|
||||
df_bad = _pd.DataFrame(data={"Open": [0, 102.04, 102.04],
|
||||
"High": [0, 102.1, 102.11],
|
||||
@@ -592,50 +420,18 @@ class TestPriceRepair(unittest.TestCase):
|
||||
index=_pd.to_datetime([_dt.datetime(2022, 11, 1),
|
||||
_dt.datetime(2022, 10, 31),
|
||||
_dt.datetime(2022, 10, 30)]))
|
||||
df_bad = df_bad.sort_index()
|
||||
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 = dat._fix_zero_prices(df_bad, "1d", tz_exchange)
|
||||
|
||||
correct_df = df_bad.copy()
|
||||
correct_df.loc["2022-11-01", "Open"] = 102.080002
|
||||
correct_df.loc["2022-11-01", "Low"] = 102.032501
|
||||
correct_df.loc["2022-11-01", "High"] = 102.080002
|
||||
correct_df.loc[correct_df.index[0], "Open"] = 102.080002
|
||||
correct_df.loc[correct_df.index[0], "Low"] = 102.032501
|
||||
correct_df.loc[correct_df.index[0], "High"] = 102.080002
|
||||
for c in ["Open", "Low", "High", "Close"]:
|
||||
self.assertTrue(_np.isclose(repaired_df[c], correct_df[c], rtol=1e-8).all())
|
||||
|
||||
def test_repair_zeroes_hourly(self):
|
||||
tkr = "INTC"
|
||||
dat = yf.Ticker(tkr, session=self.session)
|
||||
tz_exchange = dat.fast_info["timezone"]
|
||||
|
||||
correct_df = dat.history(period="1wk", interval="1h", auto_adjust=False, repair=True)
|
||||
|
||||
df_bad = correct_df.copy()
|
||||
bad_idx = correct_df.index[10]
|
||||
df_bad.loc[bad_idx, "Open"] = _np.nan
|
||||
df_bad.loc[bad_idx, "High"] = _np.nan
|
||||
df_bad.loc[bad_idx, "Low"] = _np.nan
|
||||
df_bad.loc[bad_idx, "Close"] = _np.nan
|
||||
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)
|
||||
|
||||
for c in ["Open", "Low", "High", "Close"]:
|
||||
try:
|
||||
self.assertTrue(_np.isclose(repaired_df[c], correct_df[c], rtol=1e-7).all())
|
||||
except:
|
||||
print("COLUMN", c)
|
||||
print("- repaired_df")
|
||||
print(repaired_df)
|
||||
print("- correct_df[c]:")
|
||||
print(correct_df[c])
|
||||
print("- diff:")
|
||||
print(repaired_df[c] - correct_df[c])
|
||||
raise
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
||||
|
||||
566
tests/ticker.py
566
tests/ticker.py
@@ -9,7 +9,6 @@ Specific test class:
|
||||
|
||||
"""
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
|
||||
from .context import yfinance as yf
|
||||
|
||||
@@ -52,16 +51,12 @@ class TestTicker(unittest.TestCase):
|
||||
def test_badTicker(self):
|
||||
# Check yfinance doesn't die when ticker delisted
|
||||
|
||||
tkr = "DJI" # typo of "^DJI"
|
||||
tkr = "AM2Z.TA"
|
||||
dat = yf.Ticker(tkr, session=self.session)
|
||||
dat.history(period="1wk")
|
||||
dat.history(start="2022-01-01")
|
||||
dat.history(start="2022-01-01", end="2022-03-01")
|
||||
yf.download([tkr], period="1wk")
|
||||
|
||||
for k in dat.fast_info:
|
||||
dat.fast_info[k]
|
||||
|
||||
dat.isin
|
||||
dat.major_holders
|
||||
dat.institutional_holders
|
||||
@@ -70,7 +65,6 @@ class TestTicker(unittest.TestCase):
|
||||
dat.splits
|
||||
dat.actions
|
||||
dat.shares
|
||||
dat.get_shares_full()
|
||||
dat.info
|
||||
dat.calendar
|
||||
dat.recommendations
|
||||
@@ -95,93 +89,52 @@ class TestTicker(unittest.TestCase):
|
||||
def test_goodTicker(self):
|
||||
# that yfinance works when full api is called on same instance of ticker
|
||||
|
||||
tkrs = ["IBM"]
|
||||
tkrs.append("QCSTIX") # weird ticker, no price history but has previous close
|
||||
for tkr in tkrs:
|
||||
dat = yf.Ticker(tkr, session=self.session)
|
||||
tkr = "IBM"
|
||||
dat = yf.Ticker(tkr, session=self.session)
|
||||
|
||||
dat.history(period="1wk")
|
||||
dat.history(start="2022-01-01")
|
||||
dat.history(start="2022-01-01", end="2022-03-01")
|
||||
yf.download([tkr], period="1wk")
|
||||
dat.isin
|
||||
dat.major_holders
|
||||
dat.institutional_holders
|
||||
dat.mutualfund_holders
|
||||
dat.dividends
|
||||
dat.splits
|
||||
dat.actions
|
||||
dat.shares
|
||||
dat.info
|
||||
dat.calendar
|
||||
dat.recommendations
|
||||
dat.earnings
|
||||
dat.quarterly_earnings
|
||||
dat.income_stmt
|
||||
dat.quarterly_income_stmt
|
||||
dat.balance_sheet
|
||||
dat.quarterly_balance_sheet
|
||||
dat.cashflow
|
||||
dat.quarterly_cashflow
|
||||
dat.recommendations_summary
|
||||
dat.analyst_price_target
|
||||
dat.revenue_forecasts
|
||||
dat.sustainability
|
||||
dat.options
|
||||
dat.news
|
||||
dat.earnings_trend
|
||||
dat.earnings_dates
|
||||
dat.earnings_forecasts
|
||||
|
||||
for k in dat.fast_info:
|
||||
dat.fast_info[k]
|
||||
|
||||
dat.isin
|
||||
dat.major_holders
|
||||
dat.institutional_holders
|
||||
dat.mutualfund_holders
|
||||
dat.dividends
|
||||
dat.splits
|
||||
dat.actions
|
||||
dat.shares
|
||||
dat.get_shares_full()
|
||||
dat.info
|
||||
dat.calendar
|
||||
dat.recommendations
|
||||
dat.earnings
|
||||
dat.quarterly_earnings
|
||||
dat.income_stmt
|
||||
dat.quarterly_income_stmt
|
||||
dat.balance_sheet
|
||||
dat.quarterly_balance_sheet
|
||||
dat.cashflow
|
||||
dat.quarterly_cashflow
|
||||
dat.recommendations_summary
|
||||
dat.analyst_price_target
|
||||
dat.revenue_forecasts
|
||||
dat.sustainability
|
||||
dat.options
|
||||
dat.news
|
||||
dat.earnings_trend
|
||||
dat.earnings_dates
|
||||
dat.earnings_forecasts
|
||||
dat.history(period="1wk")
|
||||
dat.history(start="2022-01-01")
|
||||
dat.history(start="2022-01-01", end="2022-03-01")
|
||||
yf.download([tkr], period="1wk")
|
||||
|
||||
|
||||
class TestTickerHistory(unittest.TestCase):
|
||||
session = None
|
||||
|
||||
@classmethod
|
||||
def setUpClass(cls):
|
||||
cls.session = requests_cache.CachedSession(backend='memory')
|
||||
|
||||
@classmethod
|
||||
def tearDownClass(cls):
|
||||
if cls.session is not None:
|
||||
cls.session.close()
|
||||
|
||||
def setUp(self):
|
||||
# use a ticker that has dividends
|
||||
self.ticker = yf.Ticker("IBM", session=self.session)
|
||||
self.ticker = yf.Ticker("IBM")
|
||||
|
||||
def tearDown(self):
|
||||
self.ticker = None
|
||||
|
||||
def test_history(self):
|
||||
with self.assertRaises(RuntimeError):
|
||||
self.ticker.history_metadata
|
||||
data = self.ticker.history("1y")
|
||||
self.assertIn("IBM", self.ticker.history_metadata.values(), "metadata missing")
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
|
||||
def test_no_expensive_calls_introduced(self):
|
||||
"""
|
||||
Make sure calling history to get price data has not introduced more calls to yahoo than absolutely necessary.
|
||||
As doing other type of scraping calls than "query2.finance.yahoo.com/v8/finance/chart" to yahoo website
|
||||
will quickly trigger spam-block when doing bulk download of history data.
|
||||
"""
|
||||
session = requests_cache.CachedSession(backend='memory')
|
||||
ticker = yf.Ticker("GOOGL", session=session)
|
||||
ticker.history("1y")
|
||||
actual_urls_called = tuple([r.url for r in session.cache.filter()])
|
||||
session.close()
|
||||
expected_urls = (
|
||||
'https://query2.finance.yahoo.com/v8/finance/chart/GOOGL?range=1y&interval=1d&includePrePost=False&events=div%2Csplits%2CcapitalGains',
|
||||
)
|
||||
self.assertEqual(expected_urls, actual_urls_called, "Different than expected url used to fetch history.")
|
||||
|
||||
def test_dividends(self):
|
||||
data = self.ticker.dividends
|
||||
self.assertIsInstance(data, pd.Series, "data has wrong type")
|
||||
@@ -199,19 +152,9 @@ class TestTickerHistory(unittest.TestCase):
|
||||
|
||||
|
||||
class TestTickerEarnings(unittest.TestCase):
|
||||
session = None
|
||||
|
||||
@classmethod
|
||||
def setUpClass(cls):
|
||||
cls.session = requests_cache.CachedSession(backend='memory')
|
||||
|
||||
@classmethod
|
||||
def tearDownClass(cls):
|
||||
if cls.session is not None:
|
||||
cls.session.close()
|
||||
|
||||
def setUp(self):
|
||||
self.ticker = yf.Ticker("GOOGL", session=self.session)
|
||||
self.ticker = yf.Ticker("GOOGL")
|
||||
|
||||
def tearDown(self):
|
||||
self.ticker = None
|
||||
@@ -270,19 +213,9 @@ class TestTickerEarnings(unittest.TestCase):
|
||||
|
||||
|
||||
class TestTickerHolders(unittest.TestCase):
|
||||
session = None
|
||||
|
||||
@classmethod
|
||||
def setUpClass(cls):
|
||||
cls.session = requests_cache.CachedSession(backend='memory')
|
||||
|
||||
@classmethod
|
||||
def tearDownClass(cls):
|
||||
if cls.session is not None:
|
||||
cls.session.close()
|
||||
|
||||
def setUp(self):
|
||||
self.ticker = yf.Ticker("GOOGL", session=self.session)
|
||||
self.ticker = yf.Ticker("GOOGL")
|
||||
|
||||
def tearDown(self):
|
||||
self.ticker = None
|
||||
@@ -313,291 +246,72 @@ class TestTickerHolders(unittest.TestCase):
|
||||
|
||||
|
||||
class TestTickerMiscFinancials(unittest.TestCase):
|
||||
session = None
|
||||
|
||||
@classmethod
|
||||
def setUpClass(cls):
|
||||
cls.session = requests_cache.CachedSession(backend='memory')
|
||||
|
||||
@classmethod
|
||||
def tearDownClass(cls):
|
||||
if cls.session is not None:
|
||||
cls.session.close()
|
||||
|
||||
def setUp(self):
|
||||
self.ticker = yf.Ticker("GOOGL", session=self.session)
|
||||
|
||||
# For ticker 'BSE.AX' (and others), Yahoo not returning
|
||||
# full quarterly financials (usually cash-flow) with all entries,
|
||||
# instead returns a smaller version in different data store.
|
||||
self.ticker_old_fmt = yf.Ticker("BSE.AX", session=self.session)
|
||||
self.ticker = yf.Ticker("GOOGL")
|
||||
|
||||
def tearDown(self):
|
||||
self.ticker = None
|
||||
|
||||
def test_income_statement(self):
|
||||
expected_keys = ["Total Revenue", "Basic EPS"]
|
||||
expected_periods_days = 365
|
||||
|
||||
# Test contents of table
|
||||
data = self.ticker.get_income_stmt(pretty=True)
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
for k in expected_keys:
|
||||
self.assertIn(k, data.index, "Did not find expected row in index")
|
||||
period = abs((data.columns[0]-data.columns[1]).days)
|
||||
self.assertLess(abs(period-expected_periods_days), 20, "Not returning annual financials")
|
||||
|
||||
# Test property defaults
|
||||
data2 = self.ticker.income_stmt
|
||||
self.assertTrue(data.equals(data2), "property not defaulting to 'pretty=True'")
|
||||
|
||||
# Test pretty=False
|
||||
expected_keys = [k.replace(' ', '') for k in expected_keys]
|
||||
data = self.ticker.get_income_stmt(pretty=False)
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
for k in expected_keys:
|
||||
self.assertIn(k, data.index, "Did not find expected row in index")
|
||||
|
||||
# Test to_dict
|
||||
data = self.ticker.get_income_stmt(as_dict=True)
|
||||
self.assertIsInstance(data, dict, "data has wrong type")
|
||||
|
||||
|
||||
def test_quarterly_income_statement(self):
|
||||
expected_keys = ["Total Revenue", "Basic EPS"]
|
||||
expected_periods_days = 365//4
|
||||
|
||||
# Test contents of table
|
||||
data = self.ticker.get_income_stmt(pretty=True, freq="quarterly")
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
for k in expected_keys:
|
||||
self.assertIn(k, data.index, "Did not find expected row in index")
|
||||
period = abs((data.columns[0]-data.columns[1]).days)
|
||||
self.assertLess(abs(period-expected_periods_days), 20, "Not returning quarterly financials")
|
||||
|
||||
# Test property defaults
|
||||
data2 = self.ticker.quarterly_income_stmt
|
||||
self.assertTrue(data.equals(data2), "property not defaulting to 'pretty=True'")
|
||||
|
||||
# Test pretty=False
|
||||
expected_keys = [k.replace(' ', '') for k in expected_keys]
|
||||
data = self.ticker.get_income_stmt(pretty=False, freq="quarterly")
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
for k in expected_keys:
|
||||
self.assertIn(k, data.index, "Did not find expected row in index")
|
||||
|
||||
# Test to_dict
|
||||
data = self.ticker.get_income_stmt(as_dict=True)
|
||||
self.assertIsInstance(data, dict, "data has wrong type")
|
||||
|
||||
def test_quarterly_income_statement_old_fmt(self):
|
||||
expected_row = "TotalRevenue"
|
||||
data = self.ticker_old_fmt.get_income_stmt(freq="quarterly", legacy=True)
|
||||
data = self.ticker.income_stmt
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
self.assertIn(expected_row, data.index, "Did not find expected row in index")
|
||||
|
||||
data_cached = self.ticker_old_fmt.get_income_stmt(freq="quarterly", legacy=True)
|
||||
data_cached = self.ticker.income_stmt
|
||||
self.assertIs(data, data_cached, "data not cached")
|
||||
|
||||
def test_quarterly_income_statement(self):
|
||||
expected_row = "TotalRevenue"
|
||||
data = self.ticker.quarterly_income_stmt
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
self.assertIn(expected_row, data.index, "Did not find expected row in index")
|
||||
|
||||
data_cached = self.ticker.quarterly_income_stmt
|
||||
self.assertIs(data, data_cached, "data not cached")
|
||||
|
||||
def test_balance_sheet(self):
|
||||
expected_keys = ["Total Assets", "Net PPE"]
|
||||
expected_periods_days = 365
|
||||
|
||||
# Test contents of table
|
||||
data = self.ticker.get_balance_sheet(pretty=True)
|
||||
expected_row = "TotalAssets"
|
||||
data = self.ticker.balance_sheet
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
for k in expected_keys:
|
||||
self.assertIn(k, data.index, "Did not find expected row in index")
|
||||
period = abs((data.columns[0]-data.columns[1]).days)
|
||||
self.assertLess(abs(period-expected_periods_days), 20, "Not returning annual financials")
|
||||
self.assertIn(expected_row, data.index, "Did not find expected row in index")
|
||||
|
||||
# Test property defaults
|
||||
data2 = self.ticker.balance_sheet
|
||||
self.assertTrue(data.equals(data2), "property not defaulting to 'pretty=True'")
|
||||
|
||||
# Test pretty=False
|
||||
expected_keys = [k.replace(' ', '') for k in expected_keys]
|
||||
data = self.ticker.get_balance_sheet(pretty=False)
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
for k in expected_keys:
|
||||
self.assertIn(k, data.index, "Did not find expected row in index")
|
||||
|
||||
# Test to_dict
|
||||
data = self.ticker.get_balance_sheet(as_dict=True)
|
||||
self.assertIsInstance(data, dict, "data has wrong type")
|
||||
data_cached = self.ticker.balance_sheet
|
||||
self.assertIs(data, data_cached, "data not cached")
|
||||
|
||||
def test_quarterly_balance_sheet(self):
|
||||
expected_keys = ["Total Assets", "Net PPE"]
|
||||
expected_periods_days = 365//4
|
||||
|
||||
# Test contents of table
|
||||
data = self.ticker.get_balance_sheet(pretty=True, freq="quarterly")
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
for k in expected_keys:
|
||||
self.assertIn(k, data.index, "Did not find expected row in index")
|
||||
period = abs((data.columns[0]-data.columns[1]).days)
|
||||
self.assertLess(abs(period-expected_periods_days), 20, "Not returning quarterly financials")
|
||||
|
||||
# Test property defaults
|
||||
data2 = self.ticker.quarterly_balance_sheet
|
||||
self.assertTrue(data.equals(data2), "property not defaulting to 'pretty=True'")
|
||||
|
||||
# Test pretty=False
|
||||
expected_keys = [k.replace(' ', '') for k in expected_keys]
|
||||
data = self.ticker.get_balance_sheet(pretty=False, freq="quarterly")
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
for k in expected_keys:
|
||||
self.assertIn(k, data.index, "Did not find expected row in index")
|
||||
|
||||
# Test to_dict
|
||||
data = self.ticker.get_balance_sheet(as_dict=True, freq="quarterly")
|
||||
self.assertIsInstance(data, dict, "data has wrong type")
|
||||
|
||||
def test_quarterly_balance_sheet_old_fmt(self):
|
||||
expected_row = "TotalAssets"
|
||||
data = self.ticker_old_fmt.get_balance_sheet(freq="quarterly", legacy=True)
|
||||
data = self.ticker.quarterly_balance_sheet
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
self.assertIn(expected_row, data.index, "Did not find expected row in index")
|
||||
|
||||
data_cached = self.ticker_old_fmt.get_balance_sheet(freq="quarterly", legacy=True)
|
||||
data_cached = self.ticker.quarterly_balance_sheet
|
||||
self.assertIs(data, data_cached, "data not cached")
|
||||
|
||||
def test_cash_flow(self):
|
||||
expected_keys = ["Operating Cash Flow", "Net PPE Purchase And Sale"]
|
||||
expected_periods_days = 365
|
||||
|
||||
# Test contents of table
|
||||
data = self.ticker.get_cashflow(pretty=True)
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
for k in expected_keys:
|
||||
self.assertIn(k, data.index, "Did not find expected row in index")
|
||||
period = abs((data.columns[0]-data.columns[1]).days)
|
||||
self.assertLess(abs(period-expected_periods_days), 20, "Not returning annual financials")
|
||||
|
||||
# Test property defaults
|
||||
data2 = self.ticker.cashflow
|
||||
self.assertTrue(data.equals(data2), "property not defaulting to 'pretty=True'")
|
||||
|
||||
# Test pretty=False
|
||||
expected_keys = [k.replace(' ', '') for k in expected_keys]
|
||||
data = self.ticker.get_cashflow(pretty=False)
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
for k in expected_keys:
|
||||
self.assertIn(k, data.index, "Did not find expected row in index")
|
||||
|
||||
# Test to_dict
|
||||
data = self.ticker.get_cashflow(as_dict=True)
|
||||
self.assertIsInstance(data, dict, "data has wrong type")
|
||||
|
||||
def test_quarterly_cash_flow(self):
|
||||
expected_keys = ["Operating Cash Flow", "Net PPE Purchase And Sale"]
|
||||
expected_periods_days = 365//4
|
||||
|
||||
# Test contents of table
|
||||
data = self.ticker.get_cashflow(pretty=True, freq="quarterly")
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
for k in expected_keys:
|
||||
self.assertIn(k, data.index, "Did not find expected row in index")
|
||||
period = abs((data.columns[0]-data.columns[1]).days)
|
||||
self.assertLess(abs(period-expected_periods_days), 20, "Not returning quarterly financials")
|
||||
|
||||
# Test property defaults
|
||||
data2 = self.ticker.quarterly_cashflow
|
||||
self.assertTrue(data.equals(data2), "property not defaulting to 'pretty=True'")
|
||||
|
||||
# Test pretty=False
|
||||
expected_keys = [k.replace(' ', '') for k in expected_keys]
|
||||
data = self.ticker.get_cashflow(pretty=False, freq="quarterly")
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
for k in expected_keys:
|
||||
self.assertIn(k, data.index, "Did not find expected row in index")
|
||||
|
||||
# Test to_dict
|
||||
data = self.ticker.get_cashflow(as_dict=True)
|
||||
self.assertIsInstance(data, dict, "data has wrong type")
|
||||
|
||||
def test_quarterly_cashflow_old_fmt(self):
|
||||
expected_row = "NetIncome"
|
||||
data = self.ticker_old_fmt.get_cashflow(legacy=True, freq="quarterly")
|
||||
def test_cashflow(self):
|
||||
expected_row = "OperatingCashFlow"
|
||||
data = self.ticker.cashflow
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
self.assertIn(expected_row, data.index, "Did not find expected row in index")
|
||||
|
||||
data_cached = self.ticker_old_fmt.get_cashflow(legacy=True, freq="quarterly")
|
||||
data_cached = self.ticker.cashflow
|
||||
self.assertIs(data, data_cached, "data not cached")
|
||||
|
||||
def test_income_alt_names(self):
|
||||
i1 = self.ticker.income_stmt
|
||||
i2 = self.ticker.incomestmt
|
||||
self.assertTrue(i1.equals(i2))
|
||||
i3 = self.ticker.financials
|
||||
self.assertTrue(i1.equals(i3))
|
||||
def test_quarterly_cashflow(self):
|
||||
expected_row = "OperatingCashFlow"
|
||||
data = self.ticker.quarterly_cashflow
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
self.assertIn(expected_row, data.index, "Did not find expected row in index")
|
||||
|
||||
i1 = self.ticker.get_income_stmt()
|
||||
i2 = self.ticker.get_incomestmt()
|
||||
self.assertTrue(i1.equals(i2))
|
||||
i3 = self.ticker.get_financials()
|
||||
self.assertTrue(i1.equals(i3))
|
||||
|
||||
i1 = self.ticker.quarterly_income_stmt
|
||||
i2 = self.ticker.quarterly_incomestmt
|
||||
self.assertTrue(i1.equals(i2))
|
||||
i3 = self.ticker.quarterly_financials
|
||||
self.assertTrue(i1.equals(i3))
|
||||
|
||||
i1 = self.ticker.get_income_stmt(freq="quarterly")
|
||||
i2 = self.ticker.get_incomestmt(freq="quarterly")
|
||||
self.assertTrue(i1.equals(i2))
|
||||
i3 = self.ticker.get_financials(freq="quarterly")
|
||||
self.assertTrue(i1.equals(i3))
|
||||
|
||||
def test_balance_sheet_alt_names(self):
|
||||
i1 = self.ticker.balance_sheet
|
||||
i2 = self.ticker.balancesheet
|
||||
self.assertTrue(i1.equals(i2))
|
||||
|
||||
i1 = self.ticker.get_balance_sheet()
|
||||
i2 = self.ticker.get_balancesheet()
|
||||
self.assertTrue(i1.equals(i2))
|
||||
|
||||
i1 = self.ticker.quarterly_balance_sheet
|
||||
i2 = self.ticker.quarterly_balancesheet
|
||||
self.assertTrue(i1.equals(i2))
|
||||
|
||||
i1 = self.ticker.get_balance_sheet(freq="quarterly")
|
||||
i2 = self.ticker.get_balancesheet(freq="quarterly")
|
||||
self.assertTrue(i1.equals(i2))
|
||||
|
||||
def test_cash_flow_alt_names(self):
|
||||
i1 = self.ticker.cash_flow
|
||||
i2 = self.ticker.cashflow
|
||||
self.assertTrue(i1.equals(i2))
|
||||
|
||||
i1 = self.ticker.get_cash_flow()
|
||||
i2 = self.ticker.get_cashflow()
|
||||
self.assertTrue(i1.equals(i2))
|
||||
|
||||
i1 = self.ticker.quarterly_cash_flow
|
||||
i2 = self.ticker.quarterly_cashflow
|
||||
self.assertTrue(i1.equals(i2))
|
||||
|
||||
i1 = self.ticker.get_cash_flow(freq="quarterly")
|
||||
i2 = self.ticker.get_cashflow(freq="quarterly")
|
||||
self.assertTrue(i1.equals(i2))
|
||||
data_cached = self.ticker.quarterly_cashflow
|
||||
self.assertIs(data, data_cached, "data not cached")
|
||||
|
||||
def test_sustainability(self):
|
||||
data = self.ticker.sustainability
|
||||
@@ -665,145 +379,16 @@ class TestTickerMiscFinancials(unittest.TestCase):
|
||||
self.assertIsInstance(data, pd.DataFrame, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
|
||||
def test_shares_full(self):
|
||||
data = self.ticker.get_shares_full()
|
||||
self.assertIsInstance(data, pd.Series, "data has wrong type")
|
||||
self.assertFalse(data.empty, "data is empty")
|
||||
def test_info(self):
|
||||
data = self.ticker.info
|
||||
self.assertIsInstance(data, dict, "data has wrong type")
|
||||
self.assertIn("symbol", data.keys(), "Did not find expected key in info dict")
|
||||
self.assertEqual("GOOGL", data["symbol"], "Wrong symbol value in info dict")
|
||||
|
||||
def test_bad_freq_value_raises_exception(self):
|
||||
self.assertRaises(ValueError, lambda: self.ticker.get_cashflow(freq="badarg"))
|
||||
|
||||
|
||||
class TestTickerInfo(unittest.TestCase):
|
||||
session = None
|
||||
|
||||
@classmethod
|
||||
def setUpClass(cls):
|
||||
cls.session = requests_cache.CachedSession(backend='memory')
|
||||
|
||||
@classmethod
|
||||
def tearDownClass(cls):
|
||||
if cls.session is not None:
|
||||
cls.session.close()
|
||||
|
||||
def setUp(self):
|
||||
self.symbols = []
|
||||
self.symbols += ["ESLT.TA", "BP.L", "GOOGL"]
|
||||
self.symbols.append("QCSTIX") # good for testing, doesn't trade
|
||||
self.symbols += ["BTC-USD", "IWO", "VFINX", "^GSPC"]
|
||||
self.symbols += ["SOKE.IS", "ADS.DE"] # detected bugs
|
||||
self.tickers = [yf.Ticker(s, session=self.session) for s in self.symbols]
|
||||
|
||||
def tearDown(self):
|
||||
self.ticker = None
|
||||
|
||||
def test_info(self):
|
||||
data = self.tickers[0].info
|
||||
self.assertIsInstance(data, dict, "data has wrong type")
|
||||
self.assertIn("symbol", data.keys(), "Did not find expected key in info dict")
|
||||
self.assertEqual(self.symbols[0], data["symbol"], "Wrong symbol value in info dict")
|
||||
|
||||
def test_fast_info(self):
|
||||
yf.scrapers.quote.PRUNE_INFO = False
|
||||
|
||||
fast_info_keys = set()
|
||||
for ticker in self.tickers:
|
||||
fast_info_keys.update(set(ticker.fast_info.keys()))
|
||||
fast_info_keys = sorted(list(fast_info_keys))
|
||||
|
||||
key_rename_map = {}
|
||||
key_rename_map["currency"] = "currency"
|
||||
key_rename_map["quote_type"] = "quoteType"
|
||||
key_rename_map["timezone"] = "exchangeTimezoneName"
|
||||
|
||||
key_rename_map["last_price"] = ["currentPrice", "regularMarketPrice"]
|
||||
key_rename_map["open"] = ["open", "regularMarketOpen"]
|
||||
key_rename_map["day_high"] = ["dayHigh", "regularMarketDayHigh"]
|
||||
key_rename_map["day_low"] = ["dayLow", "regularMarketDayLow"]
|
||||
key_rename_map["previous_close"] = ["previousClose"]
|
||||
key_rename_map["regular_market_previous_close"] = ["regularMarketPreviousClose"]
|
||||
|
||||
key_rename_map["fifty_day_average"] = "fiftyDayAverage"
|
||||
key_rename_map["two_hundred_day_average"] = "twoHundredDayAverage"
|
||||
key_rename_map["year_change"] = ["52WeekChange", "fiftyTwoWeekChange"]
|
||||
key_rename_map["year_high"] = "fiftyTwoWeekHigh"
|
||||
key_rename_map["year_low"] = "fiftyTwoWeekLow"
|
||||
|
||||
key_rename_map["last_volume"] = ["volume", "regularMarketVolume"]
|
||||
key_rename_map["ten_day_average_volume"] = ["averageVolume10days", "averageDailyVolume10Day"]
|
||||
key_rename_map["three_month_average_volume"] = "averageVolume"
|
||||
|
||||
key_rename_map["market_cap"] = "marketCap"
|
||||
key_rename_map["shares"] = "sharesOutstanding"
|
||||
|
||||
for k in list(key_rename_map.keys()):
|
||||
if '_' in k:
|
||||
key_rename_map[yf.utils.snake_case_2_camelCase(k)] = key_rename_map[k]
|
||||
|
||||
# Note: share count items in info[] are bad. Sometimes the float > outstanding!
|
||||
# So often fast_info["shares"] does not match.
|
||||
# Why isn't fast_info["shares"] wrong? Because using it to calculate market cap always correct.
|
||||
bad_keys = {"shares"}
|
||||
|
||||
# Loose tolerance for averages, no idea why don't match info[]. Is info wrong?
|
||||
custom_tolerances = {}
|
||||
custom_tolerances["year_change"] = 1.0
|
||||
# custom_tolerances["ten_day_average_volume"] = 1e-3
|
||||
custom_tolerances["ten_day_average_volume"] = 1e-1
|
||||
# custom_tolerances["three_month_average_volume"] = 1e-2
|
||||
custom_tolerances["three_month_average_volume"] = 5e-1
|
||||
custom_tolerances["fifty_day_average"] = 1e-2
|
||||
custom_tolerances["two_hundred_day_average"] = 1e-2
|
||||
for k in list(custom_tolerances.keys()):
|
||||
if '_' in k:
|
||||
custom_tolerances[yf.utils.snake_case_2_camelCase(k)] = custom_tolerances[k]
|
||||
|
||||
for k in fast_info_keys:
|
||||
if k in key_rename_map:
|
||||
k2 = key_rename_map[k]
|
||||
else:
|
||||
k2 = k
|
||||
|
||||
if not isinstance(k2, list):
|
||||
k2 = [k2]
|
||||
|
||||
for m in k2:
|
||||
for ticker in self.tickers:
|
||||
if not m in ticker.info:
|
||||
# print(f"symbol={ticker.ticker}: fast_info key '{k}' mapped to info key '{m}' but not present in info")
|
||||
continue
|
||||
|
||||
if k in bad_keys:
|
||||
continue
|
||||
|
||||
if k in custom_tolerances:
|
||||
rtol = custom_tolerances[k]
|
||||
else:
|
||||
rtol = 5e-3
|
||||
# rtol = 1e-4
|
||||
|
||||
correct = ticker.info[m]
|
||||
test = ticker.fast_info[k]
|
||||
# print(f"Testing: symbol={ticker.ticker} m={m} k={k}: test={test} vs correct={correct}")
|
||||
if k in ["market_cap","marketCap"] and ticker.fast_info["currency"] in ["GBp", "ILA"]:
|
||||
# Adjust for currency to match Yahoo:
|
||||
test *= 0.01
|
||||
try:
|
||||
if correct is None:
|
||||
self.assertTrue(test is None or (not np.isnan(test)), f"{k}: {test} must be None or real value because correct={correct}")
|
||||
elif isinstance(test, float) or isinstance(correct, int):
|
||||
self.assertTrue(np.isclose(test, correct, rtol=rtol), f"{ticker.ticker} {k}: {test} != {correct}")
|
||||
else:
|
||||
self.assertEqual(test, correct, f"{k}: {test} != {correct}")
|
||||
except:
|
||||
if k in ["regularMarketPreviousClose"] and ticker.ticker in ["ADS.DE"]:
|
||||
# Yahoo is wrong, is returning post-market close not regular
|
||||
continue
|
||||
else:
|
||||
raise
|
||||
|
||||
|
||||
|
||||
def suite():
|
||||
suite = unittest.TestSuite()
|
||||
suite.addTest(TestTicker('Test ticker'))
|
||||
@@ -811,7 +396,6 @@ def suite():
|
||||
suite.addTest(TestTickerHolders('Test holders'))
|
||||
suite.addTest(TestTickerHistory('Test Ticker history'))
|
||||
suite.addTest(TestTickerMiscFinancials('Test misc financials'))
|
||||
suite.addTest(TestTickerInfo('Test info & fast_info'))
|
||||
return suite
|
||||
|
||||
|
||||
|
||||
953
yfinance/base.py
953
yfinance/base.py
File diff suppressed because it is too large
Load Diff
250
yfinance/data.py
250
yfinance/data.py
@@ -1,22 +1,8 @@
|
||||
import functools
|
||||
from functools import lru_cache
|
||||
|
||||
import hashlib
|
||||
from base64 import b64decode
|
||||
usePycryptodome = False # slightly faster
|
||||
# usePycryptodome = True
|
||||
if usePycryptodome:
|
||||
from Crypto.Cipher import AES
|
||||
from Crypto.Util.Padding import unpad
|
||||
else:
|
||||
from cryptography.hazmat.primitives import padding
|
||||
from cryptography.hazmat.primitives.ciphers import Cipher, algorithms, modes
|
||||
|
||||
import requests as requests
|
||||
import re
|
||||
from bs4 import BeautifulSoup
|
||||
import random
|
||||
import time
|
||||
|
||||
from frozendict import frozendict
|
||||
|
||||
@@ -49,124 +35,6 @@ def lru_cache_freezeargs(func):
|
||||
return wrapped
|
||||
|
||||
|
||||
def _extract_extra_keys_from_stores(data):
|
||||
new_keys = [k for k in data.keys() if k not in ["context", "plugins"]]
|
||||
new_keys_values = set([data[k] for k in new_keys])
|
||||
|
||||
# Maybe multiple keys have same value - keep one of each
|
||||
new_keys_uniq = []
|
||||
new_keys_uniq_values = set()
|
||||
for k in new_keys:
|
||||
v = data[k]
|
||||
if not v in new_keys_uniq_values:
|
||||
new_keys_uniq.append(k)
|
||||
new_keys_uniq_values.add(v)
|
||||
|
||||
return [data[k] for k in new_keys_uniq]
|
||||
|
||||
|
||||
def decrypt_cryptojs_aes_stores(data, keys=None):
|
||||
encrypted_stores = data['context']['dispatcher']['stores']
|
||||
|
||||
password = None
|
||||
if keys is not None:
|
||||
if not isinstance(keys, list):
|
||||
raise TypeError("'keys' must be list")
|
||||
candidate_passwords = keys
|
||||
else:
|
||||
candidate_passwords = []
|
||||
|
||||
if "_cs" in data and "_cr" in data:
|
||||
_cs = data["_cs"]
|
||||
_cr = data["_cr"]
|
||||
_cr = b"".join(int.to_bytes(i, length=4, byteorder="big", signed=True) for i in json.loads(_cr)["words"])
|
||||
password = hashlib.pbkdf2_hmac("sha1", _cs.encode("utf8"), _cr, 1, dklen=32).hex()
|
||||
|
||||
encrypted_stores = b64decode(encrypted_stores)
|
||||
assert encrypted_stores[0:8] == b"Salted__"
|
||||
salt = encrypted_stores[8:16]
|
||||
encrypted_stores = encrypted_stores[16:]
|
||||
|
||||
def _EVPKDF(password, salt, keySize=32, ivSize=16, iterations=1, hashAlgorithm="md5") -> tuple:
|
||||
"""OpenSSL EVP Key Derivation Function
|
||||
Args:
|
||||
password (Union[str, bytes, bytearray]): Password to generate key from.
|
||||
salt (Union[bytes, bytearray]): Salt to use.
|
||||
keySize (int, optional): Output key length in bytes. Defaults to 32.
|
||||
ivSize (int, optional): Output Initialization Vector (IV) length in bytes. Defaults to 16.
|
||||
iterations (int, optional): Number of iterations to perform. Defaults to 1.
|
||||
hashAlgorithm (str, optional): Hash algorithm to use for the KDF. Defaults to 'md5'.
|
||||
Returns:
|
||||
key, iv: Derived key and Initialization Vector (IV) bytes.
|
||||
|
||||
Taken from: https://gist.github.com/rafiibrahim8/0cd0f8c46896cafef6486cb1a50a16d3
|
||||
OpenSSL original code: https://github.com/openssl/openssl/blob/master/crypto/evp/evp_key.c#L78
|
||||
"""
|
||||
|
||||
assert iterations > 0, "Iterations can not be less than 1."
|
||||
|
||||
if isinstance(password, str):
|
||||
password = password.encode("utf-8")
|
||||
|
||||
final_length = keySize + ivSize
|
||||
key_iv = b""
|
||||
block = None
|
||||
|
||||
while len(key_iv) < final_length:
|
||||
hasher = hashlib.new(hashAlgorithm)
|
||||
if block:
|
||||
hasher.update(block)
|
||||
hasher.update(password)
|
||||
hasher.update(salt)
|
||||
block = hasher.digest()
|
||||
for _ in range(1, iterations):
|
||||
block = hashlib.new(hashAlgorithm, block).digest()
|
||||
key_iv += block
|
||||
|
||||
key, iv = key_iv[:keySize], key_iv[keySize:final_length]
|
||||
return key, iv
|
||||
|
||||
def _decrypt(encrypted_stores, password, key, iv):
|
||||
if usePycryptodome:
|
||||
cipher = AES.new(key, AES.MODE_CBC, iv=iv)
|
||||
plaintext = cipher.decrypt(encrypted_stores)
|
||||
plaintext = unpad(plaintext, 16, style="pkcs7")
|
||||
else:
|
||||
cipher = Cipher(algorithms.AES(key), modes.CBC(iv))
|
||||
decryptor = cipher.decryptor()
|
||||
plaintext = decryptor.update(encrypted_stores) + decryptor.finalize()
|
||||
unpadder = padding.PKCS7(128).unpadder()
|
||||
plaintext = unpadder.update(plaintext) + unpadder.finalize()
|
||||
plaintext = plaintext.decode("utf-8")
|
||||
return plaintext
|
||||
|
||||
if not password is None:
|
||||
try:
|
||||
key, iv = _EVPKDF(password, salt, keySize=32, ivSize=16, iterations=1, hashAlgorithm="md5")
|
||||
except:
|
||||
raise Exception("yfinance failed to decrypt Yahoo data response")
|
||||
plaintext = _decrypt(encrypted_stores, password, key, iv)
|
||||
else:
|
||||
success = False
|
||||
for i in range(len(candidate_passwords)):
|
||||
# print(f"Trying candiate pw {i+1}/{len(candidate_passwords)}")
|
||||
password = candidate_passwords[i]
|
||||
try:
|
||||
key, iv = _EVPKDF(password, salt, keySize=32, ivSize=16, iterations=1, hashAlgorithm="md5")
|
||||
|
||||
plaintext = _decrypt(encrypted_stores, password, key, iv)
|
||||
|
||||
success = True
|
||||
break
|
||||
except:
|
||||
pass
|
||||
if not success:
|
||||
raise Exception("yfinance failed to decrypt Yahoo data response")
|
||||
|
||||
decoded_stores = json.loads(plaintext)
|
||||
return decoded_stores
|
||||
|
||||
|
||||
_SCRAPE_URL_ = 'https://finance.yahoo.com/quote'
|
||||
|
||||
|
||||
@@ -181,6 +49,8 @@ class TickerData:
|
||||
self.ticker = ticker
|
||||
self._session = session or requests
|
||||
|
||||
@lru_cache_freezeargs
|
||||
@lru_cache(maxsize=cache_maxsize)
|
||||
def get(self, url, user_agent_headers=None, params=None, proxy=None, timeout=30):
|
||||
proxy = self._get_proxy(proxy)
|
||||
response = self._session.get(
|
||||
@@ -191,11 +61,6 @@ class TickerData:
|
||||
headers=user_agent_headers or self.user_agent_headers)
|
||||
return response
|
||||
|
||||
@lru_cache_freezeargs
|
||||
@lru_cache(maxsize=cache_maxsize)
|
||||
def cache_get(self, url, user_agent_headers=None, params=None, proxy=None, timeout=30):
|
||||
return self.get(url, user_agent_headers, params, proxy, timeout)
|
||||
|
||||
def _get_proxy(self, proxy):
|
||||
# setup proxy in requests format
|
||||
if proxy is not None:
|
||||
@@ -204,72 +69,6 @@ class TickerData:
|
||||
proxy = {"https": proxy}
|
||||
return proxy
|
||||
|
||||
def get_raw_json(self, url, user_agent_headers=None, params=None, proxy=None, timeout=30):
|
||||
response = self.get(url, user_agent_headers=user_agent_headers, params=params, proxy=proxy, timeout=timeout)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
|
||||
def _get_decryption_keys_from_yahoo_js(self, soup):
|
||||
result = None
|
||||
|
||||
key_count = 4
|
||||
re_script = soup.find("script", string=re.compile("root.App.main")).text
|
||||
re_data = json.loads(re.search("root.App.main\s+=\s+(\{.*\})", re_script).group(1))
|
||||
re_data.pop("context", None)
|
||||
key_list = list(re_data.keys())
|
||||
if re_data.get("plugins"): # 1) attempt to get last 4 keys after plugins
|
||||
ind = key_list.index("plugins")
|
||||
if len(key_list) > ind+1:
|
||||
sub_keys = key_list[ind+1:]
|
||||
if len(sub_keys) == key_count:
|
||||
re_obj = {}
|
||||
missing_val = False
|
||||
for k in sub_keys:
|
||||
if not re_data.get(k):
|
||||
missing_val = True
|
||||
break
|
||||
re_obj.update({k: re_data.get(k)})
|
||||
if not missing_val:
|
||||
result = re_obj
|
||||
|
||||
if not result is None:
|
||||
return [''.join(result.values())]
|
||||
|
||||
re_keys = [] # 2) attempt scan main.js file approach to get keys
|
||||
prefix = "https://s.yimg.com/uc/finance/dd-site/js/main."
|
||||
tags = [tag['src'] for tag in soup.find_all('script') if prefix in tag.get('src', '')]
|
||||
for t in tags:
|
||||
response_js = self.cache_get(t)
|
||||
#
|
||||
if response_js.status_code != 200:
|
||||
time.sleep(random.randrange(10, 20))
|
||||
response_js.close()
|
||||
else:
|
||||
r_data = response_js.content.decode("utf8")
|
||||
re_list = [
|
||||
x.group() for x in re.finditer(r"context.dispatcher.stores=JSON.parse((?:.*?\r?\n?)*)toString", r_data)
|
||||
]
|
||||
for rl in re_list:
|
||||
re_sublist = [x.group() for x in re.finditer(r"t\[\"((?:.*?\r?\n?)*)\"\]", rl)]
|
||||
if len(re_sublist) == key_count:
|
||||
re_keys = [sl.replace('t["', '').replace('"]', '') for sl in re_sublist]
|
||||
break
|
||||
response_js.close()
|
||||
if len(re_keys) == key_count:
|
||||
break
|
||||
if len(re_keys) > 0:
|
||||
re_obj = {}
|
||||
missing_val = False
|
||||
for k in re_keys:
|
||||
if not re_data.get(k):
|
||||
missing_val = True
|
||||
break
|
||||
re_obj.update({k: re_data.get(k)})
|
||||
if not missing_val:
|
||||
return [''.join(re_obj.values())]
|
||||
|
||||
return []
|
||||
|
||||
@lru_cache_freezeargs
|
||||
@lru_cache(maxsize=cache_maxsize)
|
||||
def get_json_data_stores(self, sub_page: str = None, proxy=None) -> dict:
|
||||
@@ -281,50 +80,15 @@ class TickerData:
|
||||
else:
|
||||
ticker_url = "{}/{}".format(_SCRAPE_URL_, self.ticker)
|
||||
|
||||
response = self.get(url=ticker_url, proxy=proxy)
|
||||
html = response.text
|
||||
html = self.get(url=ticker_url, proxy=proxy).text
|
||||
|
||||
# The actual json-data for stores is in a javascript assignment in the webpage
|
||||
try:
|
||||
json_str = html.split('root.App.main =')[1].split(
|
||||
'(this)')[0].split(';\n}')[0].strip()
|
||||
except IndexError:
|
||||
# Fetch failed, probably because Yahoo spam triggered
|
||||
return {}
|
||||
|
||||
data = json.loads(json_str)
|
||||
|
||||
# Gather decryption keys:
|
||||
soup = BeautifulSoup(response.content, "html.parser")
|
||||
keys = self._get_decryption_keys_from_yahoo_js(soup)
|
||||
# if len(keys) == 0:
|
||||
# msg = "No decryption keys could be extracted from JS file."
|
||||
# if "requests_cache" in str(type(response)):
|
||||
# msg += " Try flushing your 'requests_cache', probably parsing old JS."
|
||||
# print("WARNING: " + msg + " Falling back to backup decrypt methods.")
|
||||
if len(keys) == 0:
|
||||
keys = []
|
||||
try:
|
||||
extra_keys = _extract_extra_keys_from_stores(data)
|
||||
keys = [''.join(extra_keys[-4:])]
|
||||
except:
|
||||
pass
|
||||
#
|
||||
keys_url = "https://github.com/ranaroussi/yfinance/raw/main/yfinance/scrapers/yahoo-keys.txt"
|
||||
response_gh = self.cache_get(keys_url)
|
||||
keys += response_gh.text.splitlines()
|
||||
|
||||
# Decrypt!
|
||||
stores = decrypt_cryptojs_aes_stores(data, keys)
|
||||
if stores is None:
|
||||
# Maybe Yahoo returned old format, not encrypted
|
||||
if "context" in data and "dispatcher" in data["context"]:
|
||||
stores = data['context']['dispatcher']['stores']
|
||||
if stores is None:
|
||||
raise Exception(f"{self.ticker}: Failed to extract data stores from web request")
|
||||
json_str = html.split('root.App.main =')[1].split(
|
||||
'(this)')[0].split(';\n}')[0].strip()
|
||||
data = json.loads(json_str)['context']['dispatcher']['stores']
|
||||
|
||||
# return data
|
||||
new_data = json.dumps(stores).replace('{}', 'null')
|
||||
new_data = json.dumps(data).replace('{}', 'null')
|
||||
new_data = re.sub(
|
||||
r'{[\'|\"]raw[\'|\"]:(.*?),(.*?)}', r'\1', new_data)
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
class YFinanceException(Exception):
|
||||
class YFianceException(Exception):
|
||||
pass
|
||||
|
||||
|
||||
class YFinanceDataException(YFinanceException):
|
||||
class YFianceDataException(YFianceException):
|
||||
pass
|
||||
|
||||
@@ -29,7 +29,7 @@ from . import Ticker, utils
|
||||
from . import shared
|
||||
|
||||
|
||||
def download(tickers, start=None, end=None, actions=False, threads=True, ignore_tz=None,
|
||||
def download(tickers, start=None, end=None, actions=False, threads=True, ignore_tz=True,
|
||||
group_by='column', auto_adjust=False, back_adjust=False, repair=False, keepna=False,
|
||||
progress=True, period="max", show_errors=True, interval="1d", prepost=False,
|
||||
proxy=None, rounding=False, timeout=10):
|
||||
@@ -44,13 +44,11 @@ def download(tickers, start=None, end=None, actions=False, threads=True, ignore_
|
||||
Valid intervals: 1m,2m,5m,15m,30m,60m,90m,1h,1d,5d,1wk,1mo,3mo
|
||||
Intraday data cannot extend last 60 days
|
||||
start: str
|
||||
Download start date string (YYYY-MM-DD) or _datetime, inclusive.
|
||||
Download start date string (YYYY-MM-DD) or _datetime.
|
||||
Default is 1900-01-01
|
||||
E.g. for start="2020-01-01", the first data point will be on "2020-01-01"
|
||||
end: str
|
||||
Download end date string (YYYY-MM-DD) or _datetime, exclusive.
|
||||
Download end date string (YYYY-MM-DD) or _datetime.
|
||||
Default is now
|
||||
E.g. for end="2023-01-01", the last data point will be on "2022-12-31"
|
||||
group_by : str
|
||||
Group by 'ticker' or 'column' (default)
|
||||
prepost : bool
|
||||
@@ -70,7 +68,7 @@ def download(tickers, start=None, end=None, actions=False, threads=True, ignore_
|
||||
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 depends on interval. Intraday = False. Day+ = True.
|
||||
Default is True
|
||||
proxy: str
|
||||
Optional. Proxy server URL scheme. Default is None
|
||||
rounding: bool
|
||||
@@ -82,14 +80,6 @@ def download(tickers, start=None, end=None, actions=False, threads=True, ignore_
|
||||
seconds. (Can also be a fraction of a second e.g. 0.01)
|
||||
"""
|
||||
|
||||
if ignore_tz is None:
|
||||
# Set default value depending on interval
|
||||
if interval[1:] in ['m', 'h']:
|
||||
# Intraday
|
||||
ignore_tz = False
|
||||
else:
|
||||
ignore_tz = True
|
||||
|
||||
# create ticker list
|
||||
tickers = tickers if isinstance(
|
||||
tickers, (list, set, tuple)) else tickers.replace(',', ' ').split()
|
||||
|
||||
@@ -2,11 +2,10 @@ import datetime
|
||||
import json
|
||||
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
|
||||
from yfinance import utils
|
||||
from yfinance.data import TickerData
|
||||
from yfinance.exceptions import YFinanceDataException, YFinanceException
|
||||
from yfinance.exceptions import YFianceDataException, YFianceException
|
||||
|
||||
|
||||
class Fundamentals:
|
||||
@@ -22,10 +21,10 @@ class Fundamentals:
|
||||
self._financials_data = None
|
||||
self._fin_data_quote = None
|
||||
self._basics_already_scraped = False
|
||||
self._financials = Financials(data)
|
||||
self._financials = Fiancials(data)
|
||||
|
||||
@property
|
||||
def financials(self) -> "Financials":
|
||||
def financials(self) -> "Fiancials":
|
||||
return self._financials
|
||||
|
||||
@property
|
||||
@@ -97,39 +96,32 @@ class Fundamentals:
|
||||
pass
|
||||
|
||||
|
||||
class Financials:
|
||||
class Fiancials:
|
||||
def __init__(self, data: TickerData):
|
||||
self._data = data
|
||||
self._income_time_series = {}
|
||||
self._balance_sheet_time_series = {}
|
||||
self._cash_flow_time_series = {}
|
||||
self._income_scraped = {}
|
||||
self._balance_sheet_scraped = {}
|
||||
self._cash_flow_scraped = {}
|
||||
self._income = {}
|
||||
self._balance_sheet = {}
|
||||
self._cash_flow = {}
|
||||
|
||||
def get_income_time_series(self, freq="yearly", proxy=None) -> pd.DataFrame:
|
||||
res = self._income_time_series
|
||||
def get_income(self, freq="yearly", proxy=None) -> pd.DataFrame:
|
||||
res = self._income
|
||||
if freq not in res:
|
||||
res[freq] = self._fetch_time_series("income", freq, proxy=None)
|
||||
res[freq] = self._scrape("income", freq, proxy=None)
|
||||
return res[freq]
|
||||
|
||||
def get_balance_sheet_time_series(self, freq="yearly", proxy=None) -> pd.DataFrame:
|
||||
res = self._balance_sheet_time_series
|
||||
def get_balance_sheet(self, freq="yearly", proxy=None) -> pd.DataFrame:
|
||||
res = self._balance_sheet
|
||||
if freq not in res:
|
||||
res[freq] = self._fetch_time_series("balance-sheet", freq, proxy=None)
|
||||
res[freq] = self._scrape("balance-sheet", freq, proxy=None)
|
||||
return res[freq]
|
||||
|
||||
def get_cash_flow_time_series(self, freq="yearly", proxy=None) -> pd.DataFrame:
|
||||
res = self._cash_flow_time_series
|
||||
def get_cash_flow(self, freq="yearly", proxy=None) -> pd.DataFrame:
|
||||
res = self._cash_flow
|
||||
if freq not in res:
|
||||
res[freq] = self._fetch_time_series("cash-flow", freq, proxy=None)
|
||||
res[freq] = self._scrape("cash-flow", freq, proxy=None)
|
||||
return res[freq]
|
||||
|
||||
def _fetch_time_series(self, name, timescale, proxy=None):
|
||||
# Fetching time series preferred over scraping 'QuoteSummaryStore',
|
||||
# because it matches what Yahoo shows. But for some tickers returns nothing,
|
||||
# despite 'QuoteSummaryStore' containing valid data.
|
||||
|
||||
def _scrape(self, name, timescale, proxy=None):
|
||||
allowed_names = ["income", "balance-sheet", "cash-flow"]
|
||||
allowed_timescales = ["yearly", "quarterly"]
|
||||
|
||||
@@ -140,11 +132,10 @@ class Financials:
|
||||
|
||||
try:
|
||||
statement = self._create_financials_table(name, timescale, proxy)
|
||||
|
||||
if statement is not None:
|
||||
return statement
|
||||
except YFinanceException as e:
|
||||
print(f"- {self._data.ticker}: Failed to create {name} financials table for reason: {repr(e)}")
|
||||
except YFianceException as e:
|
||||
print("Failed to create financials table for {} reason: {}".format(name, repr(e)))
|
||||
return pd.DataFrame()
|
||||
|
||||
def _create_financials_table(self, name, timescale, proxy):
|
||||
@@ -153,8 +144,14 @@ class Financials:
|
||||
name = "financials"
|
||||
|
||||
keys = self._get_datastore_keys(name, proxy)
|
||||
|
||||
try:
|
||||
# Developers note: TTM and template stuff allows for reproducing the nested structure
|
||||
# visible on Yahoo website. But more work needed to make it user-friendly! Ideally
|
||||
# return a tree data structure instead of Pandas MultiIndex
|
||||
# So until this is implemented, just return simple tables
|
||||
return self.get_financials_time_series(timescale, keys, proxy)
|
||||
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
@@ -177,10 +174,10 @@ class Financials:
|
||||
try:
|
||||
keys = _finditem1("key", data_stores['FinancialTemplateStore'])
|
||||
except KeyError as e:
|
||||
raise YFinanceDataException("Parsing FinancialTemplateStore failed, reason: {}".format(repr(e)))
|
||||
raise YFianceDataException("Parsing FinancialTemplateStore failed, reason: {}".format(repr(e)))
|
||||
|
||||
if not keys:
|
||||
raise YFinanceDataException("No keys in FinancialTemplateStore")
|
||||
raise YFianceDataException("No keys in FinancialTemplateStore")
|
||||
return keys
|
||||
|
||||
def get_financials_time_series(self, timescale, keys: list, proxy=None) -> pd.DataFrame:
|
||||
@@ -195,11 +192,11 @@ class Financials:
|
||||
url = ts_url_base + "&type=" + ",".join([timescale + k for k in keys])
|
||||
# Yahoo returns maximum 4 years or 5 quarters, regardless of start_dt:
|
||||
start_dt = datetime.datetime(2016, 12, 31)
|
||||
end = pd.Timestamp.utcnow().ceil("D")
|
||||
end = (datetime.datetime.now() + datetime.timedelta(days=366))
|
||||
url += "&period1={}&period2={}".format(int(start_dt.timestamp()), int(end.timestamp()))
|
||||
|
||||
# Step 3: fetch and reshape data
|
||||
json_str = self._data.cache_get(url=url, proxy=proxy).text
|
||||
json_str = self._data.get(url=url, proxy=proxy).text
|
||||
json_data = json.loads(json_str)
|
||||
data_raw = json_data["timeseries"]["result"]
|
||||
# data_raw = [v for v in data_raw if len(v) > 1] # Discard keys with no data
|
||||
@@ -231,89 +228,3 @@ class Financials:
|
||||
df = df[sorted(df.columns, reverse=True)]
|
||||
|
||||
return df
|
||||
|
||||
def get_income_scrape(self, freq="yearly", proxy=None) -> pd.DataFrame:
|
||||
res = self._income_scraped
|
||||
if freq not in res:
|
||||
res[freq] = self._scrape("income", freq, proxy=None)
|
||||
return res[freq]
|
||||
|
||||
def get_balance_sheet_scrape(self, freq="yearly", proxy=None) -> pd.DataFrame:
|
||||
res = self._balance_sheet_scraped
|
||||
if freq not in res:
|
||||
res[freq] = self._scrape("balance-sheet", freq, proxy=None)
|
||||
return res[freq]
|
||||
|
||||
def get_cash_flow_scrape(self, freq="yearly", proxy=None) -> pd.DataFrame:
|
||||
res = self._cash_flow_scraped
|
||||
if freq not in res:
|
||||
res[freq] = self._scrape("cash-flow", freq, proxy=None)
|
||||
return res[freq]
|
||||
|
||||
def _scrape(self, name, timescale, proxy=None):
|
||||
# Backup in case _fetch_time_series() fails to return data
|
||||
|
||||
allowed_names = ["income", "balance-sheet", "cash-flow"]
|
||||
allowed_timescales = ["yearly", "quarterly"]
|
||||
|
||||
if name not in allowed_names:
|
||||
raise ValueError("Illegal argument: name must be one of: {}".format(allowed_names))
|
||||
if timescale not in allowed_timescales:
|
||||
raise ValueError("Illegal argument: timescale must be one of: {}".format(allowed_names))
|
||||
|
||||
try:
|
||||
statement = self._create_financials_table_old(name, timescale, proxy)
|
||||
|
||||
if statement is not None:
|
||||
return statement
|
||||
except YFinanceException as e:
|
||||
print(f"- {self._data.ticker}: Failed to create financials table for {name} reason: {repr(e)}")
|
||||
return pd.DataFrame()
|
||||
|
||||
def _create_financials_table_old(self, name, timescale, proxy):
|
||||
data_stores = self._data.get_json_data_stores("financials", proxy)
|
||||
|
||||
# Fetch raw data
|
||||
if not "QuoteSummaryStore" in data_stores:
|
||||
raise YFinanceDataException(f"Yahoo not returning legacy financials data")
|
||||
data = data_stores["QuoteSummaryStore"]
|
||||
|
||||
if name == "cash-flow":
|
||||
key1 = "cashflowStatement"
|
||||
key2 = "cashflowStatements"
|
||||
elif name == "balance-sheet":
|
||||
key1 = "balanceSheet"
|
||||
key2 = "balanceSheetStatements"
|
||||
else:
|
||||
key1 = "incomeStatement"
|
||||
key2 = "incomeStatementHistory"
|
||||
key1 += "History"
|
||||
if timescale == "quarterly":
|
||||
key1 += "Quarterly"
|
||||
if key1 not in data or data[key1] is None or key2 not in data[key1]:
|
||||
raise YFinanceDataException(f"Yahoo not returning legacy {name} financials data")
|
||||
data = data[key1][key2]
|
||||
|
||||
# Tabulate
|
||||
df = pd.DataFrame(data)
|
||||
if len(df) == 0:
|
||||
raise YFinanceDataException(f"Yahoo not returning legacy {name} financials data")
|
||||
df = df.drop(columns=['maxAge'])
|
||||
for col in df.columns:
|
||||
df[col] = df[col].replace('-', np.nan)
|
||||
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': 'gainsLossesNotAffectingRetainedEarnings'}, inplace=True)
|
||||
|
||||
# Upper-case first letter, leave rest unchanged:
|
||||
s0 = df.index[0]
|
||||
df.index = [s[0].upper()+s[1:] for s in df.index]
|
||||
|
||||
return df
|
||||
|
||||
@@ -34,7 +34,7 @@ class Holders:
|
||||
def _scrape(self, proxy):
|
||||
ticker_url = "{}/{}".format(self._SCRAPE_URL_, self._data.ticker)
|
||||
try:
|
||||
resp = self._data.cache_get(ticker_url + '/holders', proxy)
|
||||
resp = self._data.get(ticker_url + '/holders', proxy)
|
||||
holders = pd.read_html(resp.text)
|
||||
except Exception:
|
||||
holders = []
|
||||
|
||||
@@ -7,530 +7,6 @@ from yfinance import utils
|
||||
from yfinance.data import TickerData
|
||||
|
||||
|
||||
info_retired_keys_price = {"currentPrice", "dayHigh", "dayLow", "open", "previousClose", "volume", "volume24Hr"}
|
||||
info_retired_keys_price.update({"regularMarket"+s for s in ["DayHigh", "DayLow", "Open", "PreviousClose", "Price", "Volume"]})
|
||||
info_retired_keys_price.update({"fiftyTwoWeekLow", "fiftyTwoWeekHigh", "fiftyTwoWeekChange", "52WeekChange", "fiftyDayAverage", "twoHundredDayAverage"})
|
||||
info_retired_keys_price.update({"averageDailyVolume10Day", "averageVolume10days", "averageVolume"})
|
||||
info_retired_keys_exchange = {"currency", "exchange", "exchangeTimezoneName", "exchangeTimezoneShortName", "quoteType"}
|
||||
info_retired_keys_marketCap = {"marketCap"}
|
||||
info_retired_keys_symbol = {"symbol"}
|
||||
info_retired_keys = info_retired_keys_price | info_retired_keys_exchange | info_retired_keys_marketCap | info_retired_keys_symbol
|
||||
|
||||
|
||||
PRUNE_INFO = True
|
||||
# PRUNE_INFO = False
|
||||
_BASIC_URL_ = "https://query2.finance.yahoo.com/v10/finance/quoteSummary"
|
||||
|
||||
|
||||
from collections.abc import MutableMapping
|
||||
class InfoDictWrapper(MutableMapping):
|
||||
""" Simple wrapper around info dict, intercepting 'gets' to
|
||||
print how-to-migrate messages for specific keys. Requires
|
||||
override dict API"""
|
||||
|
||||
def __init__(self, info):
|
||||
self.info = info
|
||||
|
||||
def keys(self):
|
||||
return self.info.keys()
|
||||
|
||||
def __str__(self):
|
||||
return self.info.__str__()
|
||||
|
||||
def __repr__(self):
|
||||
return self.info.__repr__()
|
||||
|
||||
def __contains__(self, k):
|
||||
return k in self.info.keys()
|
||||
|
||||
def __getitem__(self, k):
|
||||
if k in info_retired_keys_price:
|
||||
print(f"Price data removed from info (key='{k}'). Use Ticker.fast_info or history() instead")
|
||||
return None
|
||||
elif k in info_retired_keys_exchange:
|
||||
print(f"Exchange data removed from info (key='{k}'). Use Ticker.fast_info or Ticker.get_history_metadata() instead")
|
||||
return None
|
||||
elif k in info_retired_keys_marketCap:
|
||||
print(f"Market cap removed from info (key='{k}'). Use Ticker.fast_info instead")
|
||||
return None
|
||||
elif k in info_retired_keys_symbol:
|
||||
print(f"Symbol removed from info (key='{k}'). You know this already")
|
||||
return None
|
||||
return self.info[self._keytransform(k)]
|
||||
|
||||
def __setitem__(self, k, value):
|
||||
self.info[self._keytransform(k)] = value
|
||||
|
||||
def __delitem__(self, k):
|
||||
del self.info[self._keytransform(k)]
|
||||
|
||||
def __iter__(self):
|
||||
return iter(self.info)
|
||||
|
||||
def __len__(self):
|
||||
return len(self.info)
|
||||
|
||||
def _keytransform(self, k):
|
||||
return k
|
||||
|
||||
|
||||
class FastInfo:
|
||||
# Contain small subset of info[] items that can be fetched faster elsewhere.
|
||||
# Imitates a dict.
|
||||
def __init__(self, tickerBaseObject):
|
||||
utils.print_once("Note: 'info' dict is now fixed & improved, 'fast_info' no longer faster")
|
||||
|
||||
self._tkr = tickerBaseObject
|
||||
|
||||
self._prices_1y = None
|
||||
self._prices_1wk_1h_prepost = None
|
||||
self._prices_1wk_1h_reg = None
|
||||
self._md = None
|
||||
|
||||
self._currency = None
|
||||
self._quote_type = None
|
||||
self._exchange = None
|
||||
self._timezone = None
|
||||
|
||||
self._shares = None
|
||||
self._mcap = None
|
||||
|
||||
self._open = None
|
||||
self._day_high = None
|
||||
self._day_low = None
|
||||
self._last_price = None
|
||||
self._last_volume = None
|
||||
|
||||
self._prev_close = None
|
||||
|
||||
self._reg_prev_close = None
|
||||
|
||||
self._50d_day_average = None
|
||||
self._200d_day_average = None
|
||||
self._year_high = None
|
||||
self._year_low = None
|
||||
self._year_change = None
|
||||
|
||||
self._10d_avg_vol = None
|
||||
self._3mo_avg_vol = None
|
||||
|
||||
# attrs = utils.attributes(self)
|
||||
# self.keys = attrs.keys()
|
||||
# utils.attributes is calling each method, bad! Have to hardcode
|
||||
_properties = ["currency", "quote_type", "exchange", "timezone"]
|
||||
_properties += ["shares", "market_cap"]
|
||||
_properties += ["last_price", "previous_close", "open", "day_high", "day_low"]
|
||||
_properties += ["regular_market_previous_close"]
|
||||
_properties += ["last_volume"]
|
||||
_properties += ["fifty_day_average", "two_hundred_day_average", "ten_day_average_volume", "three_month_average_volume"]
|
||||
_properties += ["year_high", "year_low", "year_change"]
|
||||
|
||||
# Because released before fixing key case, need to officially support
|
||||
# camel-case but also secretly support snake-case
|
||||
base_keys = [k for k in _properties if not '_' in k]
|
||||
|
||||
sc_keys = [k for k in _properties if '_' in k]
|
||||
|
||||
self._sc_to_cc_key = {k:utils.snake_case_2_camelCase(k) for k in sc_keys}
|
||||
self._cc_to_sc_key = {v:k for k,v in self._sc_to_cc_key.items()}
|
||||
|
||||
self._public_keys = sorted(base_keys + list(self._sc_to_cc_key.values()))
|
||||
self._keys = sorted(self._public_keys + sc_keys)
|
||||
|
||||
# dict imitation:
|
||||
def keys(self):
|
||||
return self._public_keys
|
||||
def items(self):
|
||||
return [(k,self[k]) for k in self._public_keys]
|
||||
def values(self):
|
||||
return [self[k] for k in self._public_keys]
|
||||
def get(self, key, default=None):
|
||||
if key in self.keys():
|
||||
if key in self._cc_to_sc_key:
|
||||
key = self._cc_to_sc_key[key]
|
||||
return self[key]
|
||||
return default
|
||||
def __getitem__(self, k):
|
||||
if not isinstance(k, str):
|
||||
raise KeyError(f"key must be a string")
|
||||
if not k in self._keys:
|
||||
raise KeyError(f"'{k}' not valid key. Examine 'FastInfo.keys()'")
|
||||
if k in self._cc_to_sc_key:
|
||||
k = self._cc_to_sc_key[k]
|
||||
return getattr(self, k)
|
||||
def __contains__(self, k):
|
||||
return k in self.keys()
|
||||
def __iter__(self):
|
||||
return iter(self.keys())
|
||||
|
||||
def __str__(self):
|
||||
return "lazy-loading dict with keys = " + str(self.keys())
|
||||
def __repr__(self):
|
||||
return self.__str__()
|
||||
|
||||
def toJSON(self, indent=4):
|
||||
d = {k:self[k] for k in self.keys()}
|
||||
return _json.dumps({k:self[k] for k in self.keys()}, indent=indent)
|
||||
|
||||
def _get_1y_prices(self, fullDaysOnly=False):
|
||||
if self._prices_1y is None:
|
||||
self._prices_1y = self._tkr.history(period="380d", auto_adjust=False, debug=False, keepna=True)
|
||||
self._md = self._tkr.get_history_metadata()
|
||||
try:
|
||||
ctp = self._md["currentTradingPeriod"]
|
||||
self._today_open = pd.to_datetime(ctp["regular"]["start"], unit='s', utc=True).tz_convert(self.timezone)
|
||||
self._today_close = pd.to_datetime(ctp["regular"]["end"], unit='s', utc=True).tz_convert(self.timezone)
|
||||
self._today_midnight = self._today_close.ceil("D")
|
||||
except:
|
||||
self._today_open = None
|
||||
self._today_close = None
|
||||
self._today_midnight = None
|
||||
raise
|
||||
|
||||
if self._prices_1y.empty:
|
||||
return self._prices_1y
|
||||
|
||||
dnow = pd.Timestamp.utcnow().tz_convert(self.timezone).date()
|
||||
d1 = dnow
|
||||
d0 = (d1 + datetime.timedelta(days=1)) - utils._interval_to_timedelta("1y")
|
||||
if fullDaysOnly and self._exchange_open_now():
|
||||
# Exclude today
|
||||
d1 -= utils._interval_to_timedelta("1d")
|
||||
return self._prices_1y.loc[str(d0):str(d1)]
|
||||
|
||||
def _get_1wk_1h_prepost_prices(self):
|
||||
if self._prices_1wk_1h_prepost is None:
|
||||
self._prices_1wk_1h_prepost = self._tkr.history(period="1wk", interval="1h", auto_adjust=False, prepost=True, debug=False)
|
||||
return self._prices_1wk_1h_prepost
|
||||
|
||||
def _get_1wk_1h_reg_prices(self):
|
||||
if self._prices_1wk_1h_reg is None:
|
||||
self._prices_1wk_1h_reg = self._tkr.history(period="1wk", interval="1h", auto_adjust=False, prepost=False, debug=False)
|
||||
return self._prices_1wk_1h_reg
|
||||
|
||||
def _get_exchange_metadata(self):
|
||||
if self._md is not None:
|
||||
return self._md
|
||||
|
||||
self._get_1y_prices()
|
||||
self._md = self._tkr.get_history_metadata()
|
||||
return self._md
|
||||
|
||||
def _exchange_open_now(self):
|
||||
t = pd.Timestamp.utcnow()
|
||||
self._get_exchange_metadata()
|
||||
|
||||
# if self._today_open is None and self._today_close is None:
|
||||
# r = False
|
||||
# else:
|
||||
# r = self._today_open <= t and t < self._today_close
|
||||
|
||||
# if self._today_midnight is None:
|
||||
# r = False
|
||||
# elif self._today_midnight.date() > t.tz_convert(self.timezone).date():
|
||||
# r = False
|
||||
# else:
|
||||
# r = t < self._today_midnight
|
||||
|
||||
last_day_cutoff = self._get_1y_prices().index[-1] + datetime.timedelta(days=1)
|
||||
last_day_cutoff += datetime.timedelta(minutes=20)
|
||||
r = t < last_day_cutoff
|
||||
|
||||
# print("_exchange_open_now() returning", r)
|
||||
return r
|
||||
|
||||
@property
|
||||
def currency(self):
|
||||
if self._currency is not None:
|
||||
return self._currency
|
||||
|
||||
if self._tkr._history_metadata is None:
|
||||
self._get_1y_prices()
|
||||
md = self._tkr.get_history_metadata()
|
||||
self._currency = md["currency"]
|
||||
return self._currency
|
||||
|
||||
@property
|
||||
def quote_type(self):
|
||||
if self._quote_type is not None:
|
||||
return self._quote_type
|
||||
|
||||
if self._tkr._history_metadata is None:
|
||||
self._get_1y_prices()
|
||||
md = self._tkr.get_history_metadata()
|
||||
self._quote_type = md["instrumentType"]
|
||||
return self._quote_type
|
||||
|
||||
@property
|
||||
def exchange(self):
|
||||
if self._exchange is not None:
|
||||
return self._exchange
|
||||
|
||||
self._exchange = self._get_exchange_metadata()["exchangeName"]
|
||||
return self._exchange
|
||||
|
||||
@property
|
||||
def timezone(self):
|
||||
if self._timezone is not None:
|
||||
return self._timezone
|
||||
|
||||
self._timezone = self._get_exchange_metadata()["exchangeTimezoneName"]
|
||||
return self._timezone
|
||||
|
||||
@property
|
||||
def shares(self):
|
||||
if self._shares is not None:
|
||||
return self._shares
|
||||
|
||||
shares = self._tkr.get_shares_full(start=pd.Timestamp.utcnow().date()-pd.Timedelta(days=548))
|
||||
if shares is None:
|
||||
# Requesting 18 months failed, so fallback to shares which should include last year
|
||||
shares = self._tkr.get_shares()
|
||||
if shares is not None:
|
||||
if isinstance(shares, pd.DataFrame):
|
||||
shares = shares[shares.columns[0]]
|
||||
self._shares = int(shares.iloc[-1])
|
||||
return self._shares
|
||||
|
||||
@property
|
||||
def last_price(self):
|
||||
if self._last_price is not None:
|
||||
return self._last_price
|
||||
prices = self._get_1y_prices()
|
||||
if prices.empty:
|
||||
md = self._get_exchange_metadata()
|
||||
if "regularMarketPrice" in md:
|
||||
self._last_price = md["regularMarketPrice"]
|
||||
else:
|
||||
self._last_price = float(prices["Close"].iloc[-1])
|
||||
if _np.isnan(self._last_price):
|
||||
md = self._get_exchange_metadata()
|
||||
if "regularMarketPrice" in md:
|
||||
self._last_price = md["regularMarketPrice"]
|
||||
return self._last_price
|
||||
|
||||
@property
|
||||
def previous_close(self):
|
||||
if self._prev_close is not None:
|
||||
return self._prev_close
|
||||
prices = self._get_1wk_1h_prepost_prices()
|
||||
fail = False
|
||||
if prices.empty:
|
||||
fail = True
|
||||
else:
|
||||
prices = prices[["Close"]].groupby(prices.index.date).last()
|
||||
if prices.shape[0] < 2:
|
||||
# Very few symbols have previousClose despite no
|
||||
# no trading data e.g. 'QCSTIX'.
|
||||
fail = True
|
||||
else:
|
||||
self._prev_close = float(prices["Close"].iloc[-2])
|
||||
if fail:
|
||||
# Fallback to original info[] if available.
|
||||
self._tkr.info # trigger fetch
|
||||
k = "previousClose"
|
||||
if self._tkr._quote._retired_info is not None and k in self._tkr._quote._retired_info:
|
||||
self._prev_close = self._tkr._quote._retired_info[k]
|
||||
return self._prev_close
|
||||
|
||||
@property
|
||||
def regular_market_previous_close(self):
|
||||
if self._reg_prev_close is not None:
|
||||
return self._reg_prev_close
|
||||
prices = self._get_1y_prices()
|
||||
if prices.shape[0] == 1:
|
||||
# Tiny % of tickers don't return daily history before last trading day,
|
||||
# so backup option is hourly history:
|
||||
prices = self._get_1wk_1h_reg_prices()
|
||||
prices = prices[["Close"]].groupby(prices.index.date).last()
|
||||
if prices.shape[0] < 2:
|
||||
# Very few symbols have regularMarketPreviousClose despite no
|
||||
# no trading data. E.g. 'QCSTIX'.
|
||||
# So fallback to original info[] if available.
|
||||
self._tkr.info # trigger fetch
|
||||
k = "regularMarketPreviousClose"
|
||||
if self._tkr._quote._retired_info is not None and k in self._tkr._quote._retired_info:
|
||||
self._reg_prev_close = self._tkr._quote._retired_info[k]
|
||||
else:
|
||||
self._reg_prev_close = float(prices["Close"].iloc[-2])
|
||||
return self._reg_prev_close
|
||||
|
||||
@property
|
||||
def open(self):
|
||||
if self._open is not None:
|
||||
return self._open
|
||||
prices = self._get_1y_prices()
|
||||
if prices.empty:
|
||||
self._open = None
|
||||
else:
|
||||
self._open = float(prices["Open"].iloc[-1])
|
||||
if _np.isnan(self._open):
|
||||
self._open = None
|
||||
return self._open
|
||||
|
||||
@property
|
||||
def day_high(self):
|
||||
if self._day_high is not None:
|
||||
return self._day_high
|
||||
prices = self._get_1y_prices()
|
||||
if prices.empty:
|
||||
self._day_high = None
|
||||
else:
|
||||
self._day_high = float(prices["High"].iloc[-1])
|
||||
if _np.isnan(self._day_high):
|
||||
self._day_high = None
|
||||
return self._day_high
|
||||
|
||||
@property
|
||||
def day_low(self):
|
||||
if self._day_low is not None:
|
||||
return self._day_low
|
||||
prices = self._get_1y_prices()
|
||||
if prices.empty:
|
||||
self._day_low = None
|
||||
else:
|
||||
self._day_low = float(prices["Low"].iloc[-1])
|
||||
if _np.isnan(self._day_low):
|
||||
self._day_low = None
|
||||
return self._day_low
|
||||
|
||||
@property
|
||||
def last_volume(self):
|
||||
if self._last_volume is not None:
|
||||
return self._last_volume
|
||||
prices = self._get_1y_prices()
|
||||
self._last_volume = None if prices.empty else int(prices["Volume"].iloc[-1])
|
||||
return self._last_volume
|
||||
|
||||
@property
|
||||
def fifty_day_average(self):
|
||||
if self._50d_day_average is not None:
|
||||
return self._50d_day_average
|
||||
|
||||
prices = self._get_1y_prices(fullDaysOnly=True)
|
||||
if prices.empty:
|
||||
self._50d_day_average = None
|
||||
else:
|
||||
n = prices.shape[0]
|
||||
a = n-50
|
||||
b = n
|
||||
if a < 0:
|
||||
a = 0
|
||||
self._50d_day_average = float(prices["Close"].iloc[a:b].mean())
|
||||
|
||||
return self._50d_day_average
|
||||
|
||||
@property
|
||||
def two_hundred_day_average(self):
|
||||
if self._200d_day_average is not None:
|
||||
return self._200d_day_average
|
||||
|
||||
prices = self._get_1y_prices(fullDaysOnly=True)
|
||||
if prices.empty:
|
||||
self._200d_day_average = None
|
||||
else:
|
||||
n = prices.shape[0]
|
||||
a = n-200
|
||||
b = n
|
||||
if a < 0:
|
||||
a = 0
|
||||
|
||||
self._200d_day_average = float(prices["Close"].iloc[a:b].mean())
|
||||
|
||||
return self._200d_day_average
|
||||
|
||||
@property
|
||||
def ten_day_average_volume(self):
|
||||
if self._10d_avg_vol is not None:
|
||||
return self._10d_avg_vol
|
||||
|
||||
prices = self._get_1y_prices(fullDaysOnly=True)
|
||||
if prices.empty:
|
||||
self._10d_avg_vol = None
|
||||
else:
|
||||
n = prices.shape[0]
|
||||
a = n-10
|
||||
b = n
|
||||
if a < 0:
|
||||
a = 0
|
||||
self._10d_avg_vol = int(prices["Volume"].iloc[a:b].mean())
|
||||
|
||||
return self._10d_avg_vol
|
||||
|
||||
@property
|
||||
def three_month_average_volume(self):
|
||||
if self._3mo_avg_vol is not None:
|
||||
return self._3mo_avg_vol
|
||||
|
||||
prices = self._get_1y_prices(fullDaysOnly=True)
|
||||
if prices.empty:
|
||||
self._3mo_avg_vol = None
|
||||
else:
|
||||
dt1 = prices.index[-1]
|
||||
dt0 = dt1 - utils._interval_to_timedelta("3mo") + utils._interval_to_timedelta("1d")
|
||||
self._3mo_avg_vol = int(prices.loc[dt0:dt1, "Volume"].mean())
|
||||
|
||||
return self._3mo_avg_vol
|
||||
|
||||
@property
|
||||
def year_high(self):
|
||||
if self._year_high is not None:
|
||||
return self._year_high
|
||||
|
||||
prices = self._get_1y_prices(fullDaysOnly=True)
|
||||
if prices.empty:
|
||||
prices = self._get_1y_prices(fullDaysOnly=False)
|
||||
self._year_high = float(prices["High"].max())
|
||||
return self._year_high
|
||||
|
||||
@property
|
||||
def year_low(self):
|
||||
if self._year_low is not None:
|
||||
return self._year_low
|
||||
|
||||
prices = self._get_1y_prices(fullDaysOnly=True)
|
||||
if prices.empty:
|
||||
prices = self._get_1y_prices(fullDaysOnly=False)
|
||||
self._year_low = float(prices["Low"].min())
|
||||
return self._year_low
|
||||
|
||||
@property
|
||||
def year_change(self):
|
||||
if self._year_change is not None:
|
||||
return self._year_change
|
||||
|
||||
prices = self._get_1y_prices(fullDaysOnly=True)
|
||||
if prices.shape[0] >= 2:
|
||||
self._year_change = (prices["Close"].iloc[-1] - prices["Close"].iloc[0]) / prices["Close"].iloc[0]
|
||||
self._year_change = float(self._year_change)
|
||||
return self._year_change
|
||||
|
||||
@property
|
||||
def market_cap(self):
|
||||
if self._mcap is not None:
|
||||
return self._mcap
|
||||
|
||||
try:
|
||||
shares = self.shares
|
||||
except Exception as e:
|
||||
if "Cannot retrieve share count" in str(e):
|
||||
shares = None
|
||||
else:
|
||||
raise
|
||||
|
||||
if shares is None:
|
||||
# Very few symbols have marketCap despite no share count.
|
||||
# E.g. 'BTC-USD'
|
||||
# So fallback to original info[] if available.
|
||||
self._tkr.info
|
||||
k = "marketCap"
|
||||
if self._tkr._quote._retired_info is not None and k in self._tkr._quote._retired_info:
|
||||
self._mcap = self._tkr._quote._retired_info[k]
|
||||
else:
|
||||
self._mcap = float(shares * self.last_price)
|
||||
return self._mcap
|
||||
|
||||
|
||||
class Quote:
|
||||
|
||||
def __init__(self, data: TickerData, proxy=None):
|
||||
@@ -538,22 +14,18 @@ class Quote:
|
||||
self.proxy = proxy
|
||||
|
||||
self._info = None
|
||||
self._retired_info = None
|
||||
self._sustainability = None
|
||||
self._recommendations = None
|
||||
self._calendar = None
|
||||
|
||||
self._already_scraped = False
|
||||
self._already_fetched = False
|
||||
self._already_fetched_complementary = False
|
||||
self._already_scraped_complementary = False
|
||||
|
||||
@property
|
||||
def info(self) -> dict:
|
||||
if self._info is None:
|
||||
# self._scrape(self.proxy) # decrypt broken
|
||||
self._fetch(self.proxy)
|
||||
|
||||
self._fetch_complementary(self.proxy)
|
||||
self._scrape(self.proxy)
|
||||
self._scrape_complementary(self.proxy)
|
||||
|
||||
return self._info
|
||||
|
||||
@@ -658,19 +130,6 @@ class Quote:
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Delete redundant info[] keys, because values can be accessed faster
|
||||
# elsewhere - e.g. price keys. Hope is reduces Yahoo spam effect.
|
||||
# But record the dropped keys, because in rare cases they are needed.
|
||||
self._retired_info = {}
|
||||
for k in info_retired_keys:
|
||||
if k in self._info:
|
||||
self._retired_info[k] = self._info[k]
|
||||
if PRUNE_INFO:
|
||||
del self._info[k]
|
||||
if PRUNE_INFO:
|
||||
# InfoDictWrapper will explain how to access above data elsewhere
|
||||
self._info = InfoDictWrapper(self._info)
|
||||
|
||||
# events
|
||||
try:
|
||||
cal = pd.DataFrame(quote_summary_store['calendarEvents']['earnings'])
|
||||
@@ -696,56 +155,12 @@ class Quote:
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _fetch(self, proxy):
|
||||
if self._already_fetched:
|
||||
def _scrape_complementary(self, proxy):
|
||||
if self._already_scraped_complementary:
|
||||
return
|
||||
self._already_fetched = True
|
||||
modules = ['summaryProfile', 'financialData', 'quoteType',
|
||||
'defaultKeyStatistics', 'assetProfile', 'summaryDetail']
|
||||
result = self._data.get_raw_json(
|
||||
_BASIC_URL_ + f"/{self._data.ticker}", params={"modules": ",".join(modules), "ssl": "true"}, proxy=proxy
|
||||
)
|
||||
result["quoteSummary"]["result"][0]["symbol"] = self._data.ticker
|
||||
query1_info = next(
|
||||
(info for info in result.get("quoteSummary", {}).get("result", []) if info["symbol"] == self._data.ticker),
|
||||
None,
|
||||
)
|
||||
# Most keys that appear in multiple dicts have same value. Except 'maxAge' because
|
||||
# Yahoo not consistent with days vs seconds. Fix it here:
|
||||
for k in query1_info:
|
||||
if "maxAge" in query1_info[k] and query1_info[k]["maxAge"] == 1:
|
||||
query1_info[k]["maxAge"] = 86400
|
||||
query1_info = {
|
||||
k1: v1
|
||||
for k, v in query1_info.items()
|
||||
if isinstance(v, dict)
|
||||
for k1, v1 in v.items()
|
||||
if v1
|
||||
}
|
||||
# recursively format but only because of 'companyOfficers'
|
||||
def _format(k, v):
|
||||
if isinstance(v, dict) and "raw" in v and "fmt" in v:
|
||||
v2 = v["fmt"] if k in {"regularMarketTime", "postMarketTime"} else v["raw"]
|
||||
elif isinstance(v, list):
|
||||
v2 = [_format(None, x) for x in v]
|
||||
elif isinstance(v, dict):
|
||||
v2 = {k:_format(k, x) for k, x in v.items()}
|
||||
elif isinstance(v, str):
|
||||
v2 = v.replace("\xa0", " ")
|
||||
else:
|
||||
v2 = v
|
||||
return v2
|
||||
for k, v in query1_info.items():
|
||||
query1_info[k] = _format(k, v)
|
||||
self._info = query1_info
|
||||
self._already_scraped_complementary = True
|
||||
|
||||
def _fetch_complementary(self, proxy):
|
||||
if self._already_fetched_complementary:
|
||||
return
|
||||
self._already_fetched_complementary = True
|
||||
|
||||
# self._scrape(proxy) # decrypt broken
|
||||
self._fetch(proxy)
|
||||
self._scrape(proxy)
|
||||
if self._info is None:
|
||||
return
|
||||
|
||||
@@ -779,22 +194,17 @@ class Quote:
|
||||
for k in keys:
|
||||
url += "&type=" + k
|
||||
# Request 6 months of data
|
||||
start = pd.Timestamp.utcnow().floor("D") - datetime.timedelta(days=365 // 2)
|
||||
start = int(start.timestamp())
|
||||
end = pd.Timestamp.utcnow().ceil("D")
|
||||
end = int(end.timestamp())
|
||||
url += f"&period1={start}&period2={end}"
|
||||
url += "&period1={}".format(
|
||||
int((datetime.datetime.now() - datetime.timedelta(days=365 // 2)).timestamp()))
|
||||
url += "&period2={}".format(int((datetime.datetime.now() + datetime.timedelta(days=1)).timestamp()))
|
||||
|
||||
json_str = self._data.cache_get(url=url, proxy=proxy).text
|
||||
json_str = self._data.get(url=url, proxy=proxy).text
|
||||
json_data = json.loads(json_str)
|
||||
try:
|
||||
key_stats = json_data["timeseries"]["result"][0]
|
||||
if k not in key_stats:
|
||||
# Yahoo website prints N/A, indicates Yahoo lacks necessary data to calculate
|
||||
v = None
|
||||
else:
|
||||
# Select most recent (last) raw value in list:
|
||||
v = key_stats[k][-1]["reportedValue"]["raw"]
|
||||
except Exception:
|
||||
key_stats = json_data["timeseries"]["result"][0]
|
||||
if k not in key_stats:
|
||||
# Yahoo website prints N/A, indicates Yahoo lacks necessary data to calculate
|
||||
v = None
|
||||
else:
|
||||
# Select most recent (last) raw value in list:
|
||||
v = key_stats[k][-1]["reportedValue"]["raw"]
|
||||
self._info[k] = v
|
||||
|
||||
@@ -1,8 +0,0 @@
|
||||
daf93e37cbf219cd4c1f3f74ec4551265ec5565b99e8c9322dccd6872941cf13c818cbb88cba6f530e643b4e2329b17ec7161f4502ce6a02bb0dbbe5fc0d0474
|
||||
ad4d90b3c9f2e1d156ef98eadfa0ff93e4042f6960e54aa2a13f06f528e6b50ba4265a26a1fd5b9cd3db0d268a9c34e1d080592424309429a58bce4adc893c87
|
||||
e9a8ab8e5620b712ebc2fb4f33d5c8b9c80c0d07e8c371911c785cf674789f1747d76a909510158a7b7419e86857f2d7abbd777813ff64840e4cbc514d12bcae
|
||||
6ae2523aeafa283dad746556540145bf603f44edbf37ad404d3766a8420bb5eb1d3738f52a227b88283cca9cae44060d5f0bba84b6a495082589f5fe7acbdc9e
|
||||
3365117c2a368ffa5df7313a4a84988f73926a86358e8eea9497c5ff799ce27d104b68e5f2fbffa6f8f92c1fef41765a7066fa6bcf050810a9c4c7872fd3ebf0
|
||||
15d8f57919857d5a5358d2082c7ef0f1129cfacd2a6480333dcfb954b7bb67d820abefebfdb0eaa6ef18a1c57f617b67d7e7b0ec040403b889630ae5db5a4dbb
|
||||
db9630d707a7d0953ac795cd8db1ca9ca6c9d8239197cdfda24b4e0ec9c37eaec4db82dab68b8f606ab7b5b4af3e65dab50606f8cf508269ec927e6ee605fb78
|
||||
3c895fb5ddcc37d20d3073ed74ee3efad59bcb147c8e80fd279f83701b74b092d503dcd399604c6d8be8f3013429d3c2c76ed5b31b80c9df92d5eab6d3339fce
|
||||
@@ -155,35 +155,19 @@ class Ticker(TickerBase):
|
||||
|
||||
@property
|
||||
def income_stmt(self) -> _pd.DataFrame:
|
||||
return self.get_income_stmt(pretty=True)
|
||||
return self.get_income_stmt()
|
||||
|
||||
@property
|
||||
def quarterly_income_stmt(self) -> _pd.DataFrame:
|
||||
return self.get_income_stmt(pretty=True, freq='quarterly')
|
||||
|
||||
@property
|
||||
def incomestmt(self) -> _pd.DataFrame:
|
||||
return self.income_stmt
|
||||
|
||||
@property
|
||||
def quarterly_incomestmt(self) -> _pd.DataFrame:
|
||||
return self.quarterly_income_stmt
|
||||
|
||||
@property
|
||||
def financials(self) -> _pd.DataFrame:
|
||||
return self.income_stmt
|
||||
|
||||
@property
|
||||
def quarterly_financials(self) -> _pd.DataFrame:
|
||||
return self.quarterly_income_stmt
|
||||
return self.get_income_stmt(freq='quarterly')
|
||||
|
||||
@property
|
||||
def balance_sheet(self) -> _pd.DataFrame:
|
||||
return self.get_balance_sheet(pretty=True)
|
||||
return self.get_balance_sheet()
|
||||
|
||||
@property
|
||||
def quarterly_balance_sheet(self) -> _pd.DataFrame:
|
||||
return self.get_balance_sheet(pretty=True, freq='quarterly')
|
||||
return self.get_balance_sheet(freq='quarterly')
|
||||
|
||||
@property
|
||||
def balancesheet(self) -> _pd.DataFrame:
|
||||
@@ -193,21 +177,13 @@ class Ticker(TickerBase):
|
||||
def quarterly_balancesheet(self) -> _pd.DataFrame:
|
||||
return self.quarterly_balance_sheet
|
||||
|
||||
@property
|
||||
def cash_flow(self) -> _pd.DataFrame:
|
||||
return self.get_cash_flow(pretty=True, freq="yearly")
|
||||
|
||||
@property
|
||||
def quarterly_cash_flow(self) -> _pd.DataFrame:
|
||||
return self.get_cash_flow(pretty=True, freq='quarterly')
|
||||
|
||||
@property
|
||||
def cashflow(self) -> _pd.DataFrame:
|
||||
return self.cash_flow
|
||||
return self.get_cashflow(freq="yearly")
|
||||
|
||||
@property
|
||||
def quarterly_cashflow(self) -> _pd.DataFrame:
|
||||
return self.quarterly_cash_flow
|
||||
return self.get_cashflow(freq='quarterly')
|
||||
|
||||
@property
|
||||
def recommendations_summary(self):
|
||||
@@ -246,7 +222,3 @@ class Ticker(TickerBase):
|
||||
@property
|
||||
def earnings_forecasts(self) -> _pd.DataFrame:
|
||||
return self.get_earnings_forecast()
|
||||
|
||||
@property
|
||||
def history_metadata(self) -> dict:
|
||||
return self.get_history_metadata()
|
||||
|
||||
@@ -34,8 +34,12 @@ class Tickers:
|
||||
tickers = tickers if isinstance(
|
||||
tickers, list) else tickers.replace(',', ' ').split()
|
||||
self.symbols = [ticker.upper() for ticker in tickers]
|
||||
self.tickers = {ticker:Ticker(ticker, session=session) for ticker in self.symbols}
|
||||
ticker_objects = {}
|
||||
|
||||
for ticker in self.symbols:
|
||||
ticker_objects[ticker] = Ticker(ticker, session=session)
|
||||
|
||||
self.tickers = ticker_objects
|
||||
# self.tickers = _namedtuple(
|
||||
# "Tickers", ticker_objects.keys(), rename=True
|
||||
# )(*ticker_objects.values())
|
||||
|
||||
@@ -23,7 +23,7 @@ from __future__ import print_function
|
||||
|
||||
import datetime as _datetime
|
||||
import dateutil as _dateutil
|
||||
from typing import Dict, Union, List, Optional
|
||||
from typing import Dict, Union
|
||||
|
||||
import pytz as _tz
|
||||
import requests as _requests
|
||||
@@ -35,7 +35,6 @@ import os as _os
|
||||
import appdirs as _ad
|
||||
import sqlite3 as _sqlite3
|
||||
import atexit as _atexit
|
||||
from functools import lru_cache
|
||||
|
||||
from threading import Lock
|
||||
|
||||
@@ -50,25 +49,6 @@ user_agent_headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
|
||||
|
||||
|
||||
# From https://stackoverflow.com/a/59128615
|
||||
from types import FunctionType
|
||||
from inspect import getmembers
|
||||
def attributes(obj):
|
||||
disallowed_names = {
|
||||
name for name, value in getmembers(type(obj))
|
||||
if isinstance(value, FunctionType)}
|
||||
return {
|
||||
name: getattr(obj, name) for name in dir(obj)
|
||||
if name[0] != '_' and name not in disallowed_names and hasattr(obj, name)}
|
||||
|
||||
|
||||
@lru_cache(maxsize=20)
|
||||
def print_once(msg):
|
||||
# 'warnings' module suppression of repeat messages does not work.
|
||||
# This function replicates correct behaviour
|
||||
print(msg)
|
||||
|
||||
|
||||
def is_isin(string):
|
||||
return bool(_re.match("^([A-Z]{2})([A-Z0-9]{9})([0-9]{1})$", string))
|
||||
|
||||
@@ -237,7 +217,7 @@ def format_annual_financial_statement(level_detail, annual_dicts, annual_order,
|
||||
else:
|
||||
_statement = Annual
|
||||
|
||||
_statement.index = camel2title(_statement.T.index)
|
||||
_statement.index = camel2title(_statement.T)
|
||||
_statement['level_detail'] = level_detail
|
||||
_statement = _statement.set_index([_statement.index, 'level_detail'])
|
||||
_statement = _statement[sorted(_statement.columns, reverse=True)]
|
||||
@@ -262,55 +242,8 @@ def format_quarterly_financial_statement(_statement, level_detail, order):
|
||||
return _statement
|
||||
|
||||
|
||||
def camel2title(strings: List[str], sep: str = ' ', acronyms: Optional[List[str]] = None) -> List[str]:
|
||||
if isinstance(strings, str) or not hasattr(strings, '__iter__'):
|
||||
raise TypeError("camel2title() 'strings' argument must be iterable of strings")
|
||||
if len(strings) == 0:
|
||||
return strings
|
||||
if not isinstance(strings[0], str):
|
||||
raise TypeError("camel2title() 'strings' argument must be iterable of strings")
|
||||
if not isinstance(sep, str) or len(sep) != 1:
|
||||
raise ValueError(f"camel2title() 'sep' argument = '{sep}' must be single character")
|
||||
if _re.match("[a-zA-Z0-9]", sep):
|
||||
raise ValueError(f"camel2title() 'sep' argument = '{sep}' cannot be alpha-numeric")
|
||||
if _re.escape(sep) != sep and sep not in {' ', '-'}:
|
||||
# Permit some exceptions, I don't understand why they get escaped
|
||||
raise ValueError(f"camel2title() 'sep' argument = '{sep}' cannot be special character")
|
||||
|
||||
if acronyms is None:
|
||||
pat = "([a-z])([A-Z])"
|
||||
rep = rf"\g<1>{sep}\g<2>"
|
||||
return [_re.sub(pat, rep, s).title() for s in strings]
|
||||
|
||||
# Handling acronyms requires more care. Assumes Yahoo returns acronym strings upper-case
|
||||
if isinstance(acronyms, str) or not hasattr(acronyms, '__iter__') or not isinstance(acronyms[0], str):
|
||||
raise TypeError("camel2title() 'acronyms' argument must be iterable of strings")
|
||||
for a in acronyms:
|
||||
if not _re.match("^[A-Z]+$", a):
|
||||
raise ValueError(f"camel2title() 'acronyms' argument must only contain upper-case, but '{a}' detected")
|
||||
|
||||
# Insert 'sep' between lower-then-upper-case
|
||||
pat = "([a-z])([A-Z])"
|
||||
rep = rf"\g<1>{sep}\g<2>"
|
||||
strings = [_re.sub(pat, rep, s) for s in strings]
|
||||
|
||||
# Insert 'sep' after acronyms
|
||||
for a in acronyms:
|
||||
pat = f"({a})([A-Z][a-z])"
|
||||
rep = rf"\g<1>{sep}\g<2>"
|
||||
strings = [_re.sub(pat, rep, s) for s in strings]
|
||||
|
||||
# Apply str.title() to non-acronym words
|
||||
strings = [s.split(sep) for s in strings]
|
||||
strings = [[j.title() if not j in acronyms else j for j in s] for s in strings]
|
||||
strings = [sep.join(s) for s in strings]
|
||||
|
||||
return strings
|
||||
|
||||
|
||||
def snake_case_2_camelCase(s):
|
||||
sc = s.split('_')[0] + ''.join(x.title() for x in s.split('_')[1:])
|
||||
return sc
|
||||
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):
|
||||
@@ -332,19 +265,14 @@ def _parse_user_dt(dt, exchange_tz):
|
||||
|
||||
def _interval_to_timedelta(interval):
|
||||
if interval == "1mo":
|
||||
return _dateutil.relativedelta.relativedelta(months=1)
|
||||
elif interval == "3mo":
|
||||
return _dateutil.relativedelta.relativedelta(months=3)
|
||||
elif interval == "1y":
|
||||
return _dateutil.relativedelta.relativedelta(years=1)
|
||||
return _dateutil.relativedelta(months=1)
|
||||
elif interval == "1wk":
|
||||
return _pd.Timedelta(days=7, unit='d')
|
||||
else:
|
||||
else:
|
||||
return _pd.Timedelta(interval)
|
||||
|
||||
|
||||
def auto_adjust(data):
|
||||
col_order = data.columns
|
||||
df = data.copy()
|
||||
ratio = df["Close"] / df["Adj Close"]
|
||||
df["Adj Open"] = df["Open"] / ratio
|
||||
@@ -360,13 +288,13 @@ def auto_adjust(data):
|
||||
"Adj Low": "Low", "Adj Close": "Close"
|
||||
}, inplace=True)
|
||||
|
||||
return df[[c for c in col_order if c in df.columns]]
|
||||
df = df[["Open", "High", "Low", "Close", "Volume"]]
|
||||
return df[["Open", "High", "Low", "Close", "Volume"]]
|
||||
|
||||
|
||||
def back_adjust(data):
|
||||
""" back-adjusted data to mimic true historical prices """
|
||||
|
||||
col_order = data.columns
|
||||
df = data.copy()
|
||||
ratio = df["Adj Close"] / df["Close"]
|
||||
df["Adj Open"] = df["Open"] * ratio
|
||||
@@ -382,7 +310,7 @@ def back_adjust(data):
|
||||
"Adj Low": "Low"
|
||||
}, inplace=True)
|
||||
|
||||
return df[[c for c in col_order if c in df.columns]]
|
||||
return df[["Open", "High", "Low", "Close", "Volume"]]
|
||||
|
||||
|
||||
def parse_quotes(data):
|
||||
@@ -456,35 +384,6 @@ def set_df_tz(df, interval, tz):
|
||||
return df
|
||||
|
||||
|
||||
def fix_Yahoo_returning_prepost_unrequested(quotes, interval, metadata):
|
||||
# Sometimes Yahoo returns post-market data despite not requesting it.
|
||||
# Normally happens on half-day early closes.
|
||||
#
|
||||
# And sometimes returns pre-market data despite not requesting it.
|
||||
# E.g. some London tickers.
|
||||
tps_df = metadata["tradingPeriods"]
|
||||
tps_df["_date"] = tps_df.index.date
|
||||
quotes["_date"] = quotes.index.date
|
||||
idx = quotes.index.copy()
|
||||
quotes = quotes.merge(tps_df, how="left", validate="many_to_one")
|
||||
quotes.index = idx
|
||||
# "end" = end of regular trading hours (including any auction)
|
||||
f_drop = quotes.index >= quotes["end"]
|
||||
f_drop = f_drop | (quotes.index < quotes["start"])
|
||||
if f_drop.any():
|
||||
# When printing report, ignore rows that were already NaNs:
|
||||
f_na = quotes[["Open","Close"]].isna().all(axis=1)
|
||||
n_nna = quotes.shape[0] - _np.sum(f_na)
|
||||
n_drop_nna = _np.sum(f_drop & ~f_na)
|
||||
quotes_dropped = quotes[f_drop]
|
||||
# if debug and n_drop_nna > 0:
|
||||
# print(f"Dropping {n_drop_nna}/{n_nna} intervals for falling outside regular trading hours")
|
||||
quotes = quotes[~f_drop]
|
||||
metadata["tradingPeriods"] = tps_df.drop(["_date"], axis=1)
|
||||
quotes = quotes.drop(["_date", "start", "end"], axis=1)
|
||||
return quotes
|
||||
|
||||
|
||||
def fix_Yahoo_returning_live_separate(quotes, interval, tz_exchange):
|
||||
# Yahoo bug fix. If market is open today then Yahoo normally returns
|
||||
# todays data as a separate row from rest-of week/month interval in above row.
|
||||
@@ -513,7 +412,7 @@ def fix_Yahoo_returning_live_separate(quotes, interval, tz_exchange):
|
||||
elif interval == "3mo":
|
||||
last_rows_same_interval = dt1.year == dt2.year and dt1.quarter == dt2.quarter
|
||||
else:
|
||||
last_rows_same_interval = (dt1-dt2) < _pd.Timedelta(interval)
|
||||
last_rows_same_interval = False
|
||||
|
||||
if last_rows_same_interval:
|
||||
# Last two rows are within same interval
|
||||
@@ -560,7 +459,7 @@ def safe_merge_dfs(df_main, df_sub, interval):
|
||||
|
||||
df["_NewIndex"] = new_index
|
||||
# Duplicates present within periods but can aggregate
|
||||
if data_col_name in ["Dividends", "Capital Gains"]:
|
||||
if data_col_name == "Dividends":
|
||||
# Add
|
||||
df = df.groupby("_NewIndex").sum()
|
||||
df.index.name = None
|
||||
@@ -592,7 +491,7 @@ def safe_merge_dfs(df_main, df_sub, interval):
|
||||
new_index = None
|
||||
|
||||
if new_index is not None:
|
||||
new_index = new_index.tz_localize(df.index.tz, ambiguous=True, nonexistent='shift_forward')
|
||||
new_index = new_index.tz_localize(df.index.tz, ambiguous=True)
|
||||
df_sub = _reindex_events(df_sub, new_index, data_col)
|
||||
df = df_main.join(df_sub)
|
||||
|
||||
@@ -662,15 +561,13 @@ def safe_merge_dfs(df_main, df_sub, interval):
|
||||
## Not always possible to match events with trading, e.g. when released pre-market.
|
||||
## So have to append to bottom with nan prices.
|
||||
## But should only be impossible with intra-day price data.
|
||||
if interval.endswith('m') or interval.endswith('h') or interval == "1d":
|
||||
# Update: is possible with daily data when dividend very recent
|
||||
if interval.endswith('m') or interval.endswith('h'):
|
||||
f_missing = ~df_sub.index.isin(df.index)
|
||||
df_sub_missing = df_sub[f_missing].copy()
|
||||
df_sub_missing = df_sub[f_missing]
|
||||
keys = {"Adj Open", "Open", "Adj High", "High", "Adj Low", "Low", "Adj Close",
|
||||
"Close"}.intersection(df.columns)
|
||||
df_sub_missing[list(keys)] = _np.nan
|
||||
col_ordering = df.columns
|
||||
df = _pd.concat([df, df_sub_missing], sort=True)[col_ordering]
|
||||
df = _pd.concat([df, df_sub_missing], sort=True)
|
||||
else:
|
||||
raise Exception("Lost data during merge despite all attempts to align data (see above)")
|
||||
|
||||
@@ -698,71 +595,6 @@ def is_valid_timezone(tz: str) -> bool:
|
||||
return True
|
||||
|
||||
|
||||
def format_history_metadata(md):
|
||||
if not isinstance(md, dict):
|
||||
return md
|
||||
if len(md) == 0:
|
||||
return md
|
||||
|
||||
tz = md["exchangeTimezoneName"]
|
||||
|
||||
for k in ["firstTradeDate", "regularMarketTime"]:
|
||||
if k in md and md[k] is not None:
|
||||
md[k] = _pd.to_datetime(md[k], unit='s', utc=True).tz_convert(tz)
|
||||
|
||||
if "currentTradingPeriod" in md:
|
||||
for m in ["regular", "pre", "post"]:
|
||||
if m in md["currentTradingPeriod"]:
|
||||
for t in ["start", "end"]:
|
||||
md["currentTradingPeriod"][m][t] = \
|
||||
_pd.to_datetime(md["currentTradingPeriod"][m][t], unit='s', utc=True).tz_convert(tz)
|
||||
del md["currentTradingPeriod"][m]["gmtoffset"]
|
||||
del md["currentTradingPeriod"][m]["timezone"]
|
||||
|
||||
if "tradingPeriods" in md:
|
||||
if md["tradingPeriods"] == {"pre":[], "post":[]}:
|
||||
del md["tradingPeriods"]
|
||||
|
||||
if "tradingPeriods" in md:
|
||||
tps = md["tradingPeriods"]
|
||||
if isinstance(tps, list):
|
||||
# Only regular times
|
||||
regs_dict = [tps[i][0] for i in range(len(tps))]
|
||||
pres_dict = None
|
||||
posts_dict = None
|
||||
elif isinstance(tps, dict):
|
||||
# Includes pre- and post-market
|
||||
pres_dict = [tps["pre"][i][0] for i in range(len(tps["pre"]))]
|
||||
posts_dict = [tps["post"][i][0] for i in range(len(tps["post"]))]
|
||||
regs_dict = [tps["regular"][i][0] for i in range(len(tps["regular"]))]
|
||||
else:
|
||||
raise Exception()
|
||||
|
||||
def _dict_to_table(d):
|
||||
df = _pd.DataFrame.from_dict(d).drop(["timezone", "gmtoffset"], axis=1)
|
||||
df["end"] = _pd.to_datetime(df["end"], unit='s', utc=True).dt.tz_convert(tz)
|
||||
df["start"] = _pd.to_datetime(df["start"], unit='s', utc=True).dt.tz_convert(tz)
|
||||
df.index = _pd.to_datetime(df["start"].dt.date)
|
||||
df.index = df.index.tz_localize(tz)
|
||||
return df
|
||||
|
||||
df = _dict_to_table(regs_dict)
|
||||
df_cols = ["start", "end"]
|
||||
if pres_dict is not None:
|
||||
pre_df = _dict_to_table(pres_dict)
|
||||
df = df.merge(pre_df.rename(columns={"start":"pre_start", "end":"pre_end"}), left_index=True, right_index=True)
|
||||
df_cols = ["pre_start", "pre_end"]+df_cols
|
||||
if posts_dict is not None:
|
||||
post_df = _dict_to_table(posts_dict)
|
||||
df = df.merge(post_df.rename(columns={"start":"post_start", "end":"post_end"}), left_index=True, right_index=True)
|
||||
df_cols = df_cols+["post_start", "post_end"]
|
||||
df = df[df_cols]
|
||||
df.index.name = "Date"
|
||||
|
||||
md["tradingPeriods"] = df
|
||||
|
||||
return md
|
||||
|
||||
class ProgressBar:
|
||||
def __init__(self, iterations, text='completed'):
|
||||
self.text = text
|
||||
@@ -825,14 +657,7 @@ class _KVStore:
|
||||
with self._cache_mutex:
|
||||
self.conn = _sqlite3.connect(filename, timeout=10, check_same_thread=False)
|
||||
self.conn.execute('pragma journal_mode=wal')
|
||||
try:
|
||||
self.conn.execute('create table if not exists "kv" (key TEXT primary key, value TEXT) without rowid')
|
||||
except Exception as e:
|
||||
if 'near "without": syntax error' in str(e):
|
||||
# "without rowid" requires sqlite 3.8.2. Older versions will raise exception
|
||||
self.conn.execute('create table if not exists "kv" (key TEXT primary key, value TEXT)')
|
||||
else:
|
||||
raise
|
||||
self.conn.execute('create table if not exists "kv" (key TEXT primary key, value TEXT) without rowid')
|
||||
self.conn.commit()
|
||||
_atexit.register(self.close)
|
||||
|
||||
@@ -873,10 +698,8 @@ class _TzCache:
|
||||
"""Simple sqlite file cache of ticker->timezone"""
|
||||
|
||||
def __init__(self):
|
||||
self._tz_db = None
|
||||
self._setup_cache_folder()
|
||||
# Must init db here, where is thread-safe
|
||||
self._tz_db = _KVStore(_os.path.join(self._db_dir, "tkr-tz.db"))
|
||||
self._migrate_cache_tkr_tz()
|
||||
|
||||
def _setup_cache_folder(self):
|
||||
if not _os.path.isdir(self._db_dir):
|
||||
@@ -908,6 +731,11 @@ class _TzCache:
|
||||
|
||||
@property
|
||||
def tz_db(self):
|
||||
# lazy init
|
||||
if self._tz_db is None:
|
||||
self._tz_db = _KVStore(_os.path.join(self._db_dir, "tkr-tz.db"))
|
||||
self._migrate_cache_tkr_tz()
|
||||
|
||||
return self._tz_db
|
||||
|
||||
def _migrate_cache_tkr_tz(self):
|
||||
|
||||
@@ -1 +1 @@
|
||||
version = "0.2.16"
|
||||
version = "0.2.0rc1"
|
||||
|
||||
Reference in New Issue
Block a user