def test_transaction():
engine = Engine(best_ip=True, thread_num=1)
with engine.connect():
df = engine.get_k_data('000001', '20170601', '20171231', '1m')
df = engine.get_security_bars(['000001', '000521'],
'1d',
start=pd.to_datetime('20180102'))
def transactions():
eg = Engine(best_ip=True)
eg.connect()
m1 = eg.get_security_bars('000001', '1m')
df = eg.time_and_price('000001')
ohlcv = df.price.resample('1 Min', label='right', closed='left').ohlc()
ohlcv['volume'] = df.vol.resample('1 Min', label='right',
closed='left').sum()
def engine_func(best_ip, thread_num):
engine = Engine(best_ip=best_ip, thread_num=thread_num)
with engine.connect():
assert engine.best_ip is not None
assert engine.gbbq is not None
assert engine.security_list is not None
assert engine.stock_quotes() is not None
assert engine.customer_block is not None
assert engine.quotes('000001') is not None
assert engine.get_security_bars('000001', '1m') is not None
assert engine.get_security_bars('000001', '1d') is not None
assert engine.get_security_bars('000300', '1m', index=True) is not None
assert engine.get_security_bars('000300', '1d', index=True) is not None
assert engine.concept is not None
assert engine.fengge is not None
assert engine.index is not None
assert engine.stock_list is not None
def ensure_benchmark_data(symbol, first_date, last_date, now, trading_day):
"""
Ensure we have benchmark data for `symbol` from `first_date` to `last_date`
Parameters
----------
symbol : str
The symbol for the benchmark to load.
first_date : pd.Timestamp
First required date for the cache.
last_date : pd.Timestamp
Last required date for the cache.
now : pd.Timestamp
The current time. This is used to prevent repeated attempts to
re-download data that isn't available due to scheduling quirks or other
failures.
trading_day : pd.CustomBusinessDay
A trading day delta. Used to find the day before first_date so we can
get the close of the day prior to first_date.
We attempt to download data unless we already have data stored at the data
cache for `symbol` whose first entry is before or on `first_date` and whose
last entry is on or after `last_date`.
If we perform a download and the cache criteria are not satisfied, we wait
at least one hour before attempting a redownload. This is determined by
comparing the current time to the result of os.path.getmtime on the cache
path.
"""
path = get_data_filepath(get_benchmark_filename(symbol))
# If the path does not exist, it means the first download has not happened
# yet, so don't try to read from 'path'.
if os.path.exists(path):
try:
data = pd.Series.from_csv(path).tz_localize('UTC')
if has_data_for_dates(data, first_date, last_date):
return data
# Don't re-download if we've successfully downloaded and written a
# file in the last hour.
last_download_time = last_modified_time(path)
if (now - last_download_time) <= ONE_HOUR:
logger.warn(
"Refusing to download new benchmark data because a "
"download succeeded at %s." % last_download_time)
return data
except (OSError, IOError, ValueError) as e:
# These can all be raised by various versions of pandas on various
# classes of malformed input. Treat them all as cache misses.
logger.info(
"Loading data for {path} failed with error [{error}].".format(
path=path,
error=e,
))
logger.info(
"Cache at {path} does not have data from {start} to {end}.\n"
"Downloading benchmark data for '{symbol}'.",
start=first_date,
end=last_date,
symbol=symbol,
path=path,
)
engine = Engine(auto_retry=True, multithread=True, thread_num=8)
engine.connect()
data = engine.get_security_bars(symbol, '1d', index=True)
data = data['close'].sort_index().tz_localize('UTC').pct_change(1).iloc[1:]
data.index = data.index.shift(-15,
'1H') # change datetime at 15:00 to midnight
data.to_csv(path)
return data
print(grouped.sort_values('up_limit', ascending=False))
def minute_time_data():
stock_list = engine.stock_list.index.tolist()
now = datetime.datetime.now()
for stock in stock_list:
fs = engine.api.to_df(
engine.api.get_minute_time_data(stock[0], stock[1]))
# print(fs)
print((datetime.datetime.now() - now).total_seconds())
def quotes():
start_dt = datetime.datetime.now()
quote = engine.stock_quotes()
print(datetime.datetime.now() - start_dt).total_seconds()
process_quotes(quote)
if __name__ == '__main__':
engine = Engine(best_ip=True)
with engine.connect():
print(
engine.get_security_bars('002920', '1d',
pd.to_datetime('20170701')))
def main():
engine = Engine(best_ip=True, thread_num=1)
with engine.connect():
engine.get_k_data('000001', '20161201', '20171231', '1m')
def test_transaction():
engine = Engine(best_ip=True, thread_num=1)
with engine.connect():
df = engine.get_k_data('000001', '20170601', '20171231', '1m')
df = engine.get_security_bars(['000001', '000521'],
'1d',
start=pd.to_datetime('20180102'))
if __name__ == '__main__':
engine = Engine(best_ip=True, thread_num=1)
with engine.connect():
print(engine.api.get_security_count(0))
print(engine.api.get_security_count(1))
lists = engine.stock_list
print(
engine.get_security_bars('300737', '1d',
pd.to_datetime('20161201'),
pd.to_datetime('20171231')))
print(engine.get_k_data('300737', '20161201', '20171231', '1d'))
print(timeit.timeit(test_transaction, number=1))
print(timeit.timeit(main, number=1))
def ensure_benchmark_data(symbol, first_date, last_date, now, trading_day):
"""
Ensure we have benchmark data for `symbol` from `first_date` to `last_date`
Parameters
----------
symbol : str
The symbol for the benchmark to load.
first_date : pd.Timestamp
First required date for the cache.
last_date : pd.Timestamp
Last required date for the cache.
now : pd.Timestamp
The current time. This is used to prevent repeated attempts to
re-download data that isn't available due to scheduling quirks or other
failures.
trading_day : pd.CustomBusinessDay
A trading day delta. Used to find the day before first_date so we can
get the close of the day prior to first_date.
We attempt to download data unless we already have data stored at the data
cache for `symbol` whose first entry is before or on `first_date` and whose
last entry is on or after `last_date`.
If we perform a download and the cache criteria are not satisfied, we wait
at least one hour before attempting a redownload. This is determined by
comparing the current time to the result of os.path.getmtime on the cache
path.
"""
path = get_data_filepath(get_benchmark_filename(symbol))
# If the path does not exist, it means the first download has not happened
# yet, so don't try to read from 'path'.
if os.path.exists(path):
try:
data = pd.Series.from_csv(path).tz_localize('UTC')
if has_data_for_dates(data, first_date, last_date):
return data
# Don't re-download if we've successfully downloaded and written a
# file in the last hour.
last_download_time = last_modified_time(path)
if (now - last_download_time) <= ONE_HOUR:
logger.warn(
"Refusing to download new benchmark data because a "
"download succeeded at %s." % last_download_time
)
return data
except (OSError, IOError, ValueError) as e:
# These can all be raised by various versions of pandas on various
# classes of malformed input. Treat them all as cache misses.
logger.info(
"Loading data for {path} failed with error [{error}].".format(
path=path, error=e,
)
)
logger.info(
"Cache at {path} does not have data from {start} to {end}.\n"
"Downloading benchmark data for '{symbol}'.",
start=first_date,
end=last_date,
symbol=symbol,
path=path,
)
engine = Engine(auto_retry=True, multithread=True, thread_num=8, best_ip=True)
engine.connect()
data = engine.get_security_bars(symbol, '1d',index=True)
data = data['close'].sort_index().tz_localize('UTC').pct_change(1).iloc[1:]
data.index = data.index.normalize() # change datetime at 15:00 to midnight
data.to_csv(path)
return data