def add_factor_to_163(security_item):
path_163 = get_kdata_path(security_item, source='163', fuquan='bfq')
df_163 = pd_read_csv(path_163)
if 'factor' in df_163.columns:
df = df_163[df_163['factor'].isna()]
if df.empty:
logger.info("{} 163 factor is ok", security_item['code'])
return
path_sina = get_kdata_path(security_item, source='sina', fuquan='hfq')
df_sina = pd_read_csv(path_sina)
df_sina = df_sina[~df_sina.index.duplicated(keep='first')]
df_163['factor'] = df_sina['factor']
df_163.to_csv(path_163, index=False)
def get_event(security_item,
event_type='finance_forecast',
start_date=None,
end_date=None,
index='timestamp'):
"""
get forecast items.
Parameters
----------
security_item : SecurityItem or str
the security item,id or code
event_type : str
{'finance_forecast','finance_report'}
start_date: Timestamp str or Timestamp
the start date for the event
end_date: Timestamp str or Timestamp
the end date for the event
Returns
-------
DataFrame
"""
security_item = to_security_item(security_item)
path = get_event_path(security_item, event_type)
if os.path.exists(path):
df = pd_utils.pd_read_csv(path, index=index, generate_id=True)
df = df_for_date_range(df, start_date=start_date, end_date=end_date)
else:
df = pd.DataFrame()
return df
def get_kdata(security_item,
exchange=None,
the_date=None,
start_date=None,
end_date=None,
fuquan='bfq',
source=None,
level='day',
generate_id=False):
"""
get kdata.
Parameters
----------
security_item : SecurityItem or str
the security item,id or code
exchange : str
the exchange,set this for cryptocurrency
the_date : TimeStamp str or TimeStamp
get the kdata for the exact date
start_date : TimeStamp str or TimeStamp
start date
end_date : TimeStamp str or TimeStamp
end date
fuquan : str
{"qfq","hfq","bfq"},default:"bfq"
source : str
the data source,{'163','sina','exchange'},just used for internal merge
level : str or int
the kdata level,{1,5,15,30,60,'day','week','month'},default : 'day'
Returns
-------
DataFrame
"""
# 由于数字货币的交易所太多，必须指定exchange
security_item = to_security_item(security_item, exchange)
source = adjust_source(security_item, source)
# 163的数据是合并过的,有复权因子,都存在'bfq'目录下,只需从一个地方取数据,并做相应转换
if source == '163':
the_path = files_contract.get_kdata_path(security_item,
source=source,
fuquan='bfq')
else:
the_path = files_contract.get_kdata_path(security_item,
source=source,
fuquan=fuquan)
if os.path.isfile(the_path):
df = pd_utils.pd_read_csv(the_path, generate_id=generate_id)
if 'factor' in df.columns and source == '163' and security_item[
'type'] == 'stock':
df_kdata_has_factor = df[df['factor'].notna()]
if df_kdata_has_factor.shape[0] > 0:
latest_factor = df_kdata_has_factor.tail(1).factor.iat[0]
else:
latest_factor = None
if the_date:
if the_date in df.index:
df = df.loc[the_date:the_date, :]
else:
return None
else:
if start_date or end_date:
df = df_for_date_range(df,
start_date=start_date,
end_date=end_date)
# 复权处理
if source == '163' and security_item['type'] == 'stock':
if 'factor' in df.columns:
# 后复权是不变的
df['hfqClose'] = df.close * df.factor
df['hfqOpen'] = df.open * df.factor
df['hfqHigh'] = df.high * df.factor
df['hfqLow'] = df.low * df.factor
# 前复权需要根据最新的factor往回算,当前价格不变
if latest_factor:
df['qfqClose'] = df.hfqClose / latest_factor
df['qfqOpen'] = df.hfqOpen / latest_factor
df['qfqHigh'] = df.hfqHigh / latest_factor
df['qfqLow'] = df.hfqLow / latest_factor
else:
logger.exception("missing latest factor for {}".format(
security_item['id']))
return df
return pd.DataFrame()