def record_fund():
while True:
email_action = EmailInformer()
try:
# 基金和基金持仓数据
Fund.record_data(provider='joinquant', sleeping_time=1)
FundStock.record_data(provider='joinquant', sleeping_time=1)
# 股票周线后复权数据
Stock1wkHfqKdata.record_data(provider='joinquant', sleeping_time=0)
email_action.send_message(zvt_config['email_username'], 'joinquant record fund finished', '')
break
except Exception as e:
msg = f'joinquant record fund error:{e}'
logger.exception(msg)
email_action.send_message(zvt_config['email_username'], 'joinquant record fund error', msg)
time.sleep(60)
def get_top_fund_holding_stocks(timestamp=None, pct=0.3, by=None):
if not timestamp:
timestamp = now_pd_timestamp()
# 季报一般在report_date后1个月内公布，年报2个月内，年报4个月内
# 所以取时间点的最近的两个公布点，保证取到数据
# 所以，这是个滞后的数据，只是为了看个大概，毕竟模糊的正确better than 精确的错误
report_date = get_recent_report_date(timestamp, 1)
fund_cap_df = FundStock.query_data(
filters=[
FundStock.report_date >= report_date,
FundStock.timestamp <= timestamp,
],
columns=["stock_id", "market_cap"],
)
fund_cap_df = fund_cap_df.groupby(
"stock_id")["market_cap"].sum().sort_values(ascending=False)
# 直接根据持有市值返回
if not by:
s = fund_cap_df.iloc[:int(len(fund_cap_df) * pct)]
return s.to_frame()
# 按流通盘比例
if by == "trading":
columns = ["entity_id", "circulating_market_cap"]
# 按市值比例
elif by == "all":
columns = ["entity_id", "market_cap"]
entity_ids = fund_cap_df.index.tolist()
start_timestamp = next_date(timestamp, -30)
cap_df = StockValuation.query_data(
entity_ids=entity_ids,
filters=[
StockValuation.timestamp >= start_timestamp,
StockValuation.timestamp <= timestamp,
],
columns=columns,
)
if by == "trading":
cap_df = cap_df.rename(columns={"circulating_market_cap": "cap"})
elif by == "all":
cap_df = cap_df.rename(columns={"market_cap": "cap"})
cap_df = cap_df.groupby("entity_id").mean()
result_df = pd.concat([cap_df, fund_cap_df], axis=1, join="inner")
result_df["pct"] = result_df["market_cap"] / result_df["cap"]
pct_df = result_df["pct"].sort_values(ascending=False)
s = pct_df.iloc[:int(len(pct_df) * pct)]
return s.to_frame()
def get_top_fund_holding_stocks(timestamp=None, pct=0.3, by=None):
if not timestamp:
timestamp = now_pd_timestamp()
# 季报一般在report_date后1个月内公布，年报2个月内，年报4个月内
# 所以取时间点的最近的两个公布点，保证取到数据
# 所以，这是个滞后的数据，只是为了看个大概，毕竟模糊的正确better than 精确的错误
report_date = get_recent_report_date(timestamp, 1)
df = FundStock.query_data(region=Region.CHN,
filters=[
FundStock.report_date >= report_date,
FundStock.timestamp <= timestamp
],
columns=['stock_id', 'market_cap'])
fund_cap_df = fund_cap_df.groupby(
'stock_id')['market_cap'].sum().sort_values(ascending=False)
# 直接根据持有市值返回
if not by:
s = fund_cap_df.iloc[:int(len(fund_cap_df) * pct)]
return s.to_frame()
# 按流通盘比例
if by == 'trading':
columns = ['entity_id', 'circulating_market_cap']
# 按市值比例
elif by == 'all':
columns = ['entity_id', 'market_cap']
entity_ids = fund_cap_df.index.tolist()
start_timestamp = next_date(timestamp, -30)
cap_df = StockValuation.query_data(
entity_ids=entity_ids,
filters=[
StockValuation.timestamp >= start_timestamp,
StockValuation.timestamp <= timestamp
],
columns=columns)
if by == 'trading':
cap_df = cap_df.rename(columns={'circulating_market_cap': 'cap'})
elif by == 'all':
cap_df = cap_df.rename(columns={'market_cap': 'cap'})
cap_df = cap_df.groupby('entity_id').mean()
result_df = pd.concat([cap_df, fund_cap_df], axis=1, join='inner')
result_df['pct'] = result_df['market_cap'] / result_df['cap']
pct_df = result_df['pct'].sort_values(ascending=False)
s = pct_df.iloc[:int(len(pct_df) * pct)]
return s.to_frame()
def get_top_fund_holding_stocks(timestamp=None, pct=0.3):
if not timestamp:
timestamp = now_pd_timestamp()
# 季报一般在report_date后1个月内公布，年报2个月内，年报4个月内
# 所以取时间点的最近的两个公布点，保证取到数据
# 所以，这是个滞后的数据，只是为了看个大概，毕竟模糊的正确better than 精确的错误
report_date = get_recent_report_date(timestamp, 1)
df = FundStock.query_data(filters=[FundStock.report_date >= report_date, FundStock.timestamp <= timestamp])
g = df.groupby('stock_id')
market = g['market_cap'].sum().sort_values(ascending=False)
s = market.iloc[:int(len(market) * pct)]
return s.to_frame()