def get_moneyflow_data(provider: Provider, sleep, desc, pc, lock, region,
batch):
# 股票资金流向表
StockMoneyFlow.record_data(provider=provider,
share_para=(desc, pc, lock, True, region),
sleeping_time=sleep,
batch_size=batch)
def record(self, entity, start, end, size, timestamps, http_session):
# 上证
if entity.code == '000001':
all_df = StockMoneyFlow.query_data(
region=self.region,
provider=self.provider,
start_timestamp=start,
filters=[StockMoneyFlow.entity_id.like('stock_sh%')])
# 深证
elif entity.code == '399001':
all_df = StockMoneyFlow.query_data(
region=self.region,
provider=self.provider,
start_timestamp=start,
filters=[StockMoneyFlow.entity_id.like('stock_sz%')])
# 创业板
elif entity.code == '399006':
all_df = StockMoneyFlow.query_data(
region=self.region,
provider=self.provider,
start_timestamp=start,
filters=[StockMoneyFlow.code.like('300%')])
# 科创板
elif entity.code == '000688':
all_df = StockMoneyFlow.query_data(
region=self.region,
provider=self.provider,
start_timestamp=start,
filters=[StockMoneyFlow.code.like('688%')])
if pd_is_not_null(all_df):
return all_df
return None
def record(self, entity, start, end, size, timestamps):
# 上证
if entity.code == '000001':
all_df = StockMoneyFlow.query_data(
provider=self.provider,
start_timestamp=start,
filters=[StockMoneyFlow.entity_id.like('stock_sh%')])
# 深证
elif entity.code == '399001':
all_df = StockMoneyFlow.query_data(
provider=self.provider,
start_timestamp=start,
filters=[StockMoneyFlow.entity_id.like('stock_sz%')])
# 创业板
elif entity.code == '399006':
all_df = StockMoneyFlow.query_data(
provider=self.provider,
start_timestamp=start,
filters=[StockMoneyFlow.code.like('300%')])
if pd_is_not_null(all_df):
g = all_df.groupby('timestamp')
for timestamp, df in g:
se = pd.Series({
'id':
"{}_{}".format(entity.id, to_time_str(timestamp)),
'entity_id':
entity.id,
'timestamp':
timestamp,
'code':
entity.code,
'name':
entity.name
})
for col in [
'net_main_inflows', 'net_huge_inflows',
'net_big_inflows', 'net_medium_inflows',
'net_small_inflows'
]:
se[col] = df[col].sum()
for col in [
'net_main_inflow_rate', 'net_huge_inflow_rate',
'net_big_inflow_rate', 'net_medium_inflow_rate',
'net_small_inflow_rate'
]:
se[col] = df[col].sum() / len(df)
index_df = se.to_frame().T
self.logger.info(index_df)
df_to_db(df=index_df,
data_schema=self.data_schema,
provider=self.provider,
force_update=self.force_update)
return None
def test_stock_money_flow():
provider = "joinquant"
# Stock.record_data(provider=provider)
StockMoneyFlow.record_data(codes=["300999", "688981"],
provider=provider,
start_timestamp="2020-12-14",
compute_index_money_flow=False)
data_samples = [
{
"id": "stock_sz_300999_2020-12-14",
"timestamp": "2020-12-14",
"code": "300999",
"net_main_inflows": 46378.96 * 10000,
"net_main_inflow_rate": 9.3 / 100,
"net_huge_inflows": 50111.54 * 10000,
"net_huge_inflow_rate": 10.04 / 100,
"net_big_inflows": -3732.58 * 10000,
"net_big_inflow_rate": -0.75 / 100,
"net_medium_inflows": -23493.71 * 10000,
"net_medium_inflow_rate": -4.71 / 100,
"net_small_inflows": -22885.25 * 10000,
"net_small_inflow_rate": -4.59 / 100,
},
{
"id": "stock_sh_688981_2020-12-14",
"timestamp": "2020-12-14",
"code": "688981",
"net_main_inflows": -14523.55 * 10000,
"net_main_inflow_rate": -10.77 / 100,
"net_huge_inflows": -17053.72 * 10000,
"net_huge_inflow_rate": -12.65 / 100,
"net_big_inflows": 2530.17 * 10000,
"net_big_inflow_rate": 1.88 / 100,
"net_medium_inflows": 6945.23 * 10000,
"net_medium_inflow_rate": 5.15 / 100,
"net_small_inflows": 7578.32 * 10000,
"net_small_inflow_rate": 5.62 / 100,
},
]
StockMoneyFlow.test_data_correctness(provider=provider,
data_samples=data_samples)
def test_stock_money_flow():
region = Region.CHN
provider = Provider.JoinQuant
StockMoneyFlow.record_data(codes=['300999', '688981'],
provider=provider,
start_timestamp='2020-12-14',
compute_index_money_flow=False)
data_samples = [{
"id": 'stock_sz_300999_2020-12-14',
"timestamp": '2020-12-14',
"code": "300999",
"net_main_inflows": 46378.96 * 10000,
"net_main_inflow_rate": 9.3 / 100,
"net_huge_inflows": 50111.54 * 10000,
"net_huge_inflow_rate": 10.04 / 100,
"net_big_inflows": -3732.58 * 10000,
"net_big_inflow_rate": -0.75 / 100,
"net_medium_inflows": -23493.71 * 10000,
"net_medium_inflow_rate": -4.71 / 100,
"net_small_inflows": -22885.25 * 10000,
"net_small_inflow_rate": -4.59 / 100
}, {
"id": 'stock_sh_688981_2020-12-14',
"timestamp": '2020-12-14',
"code": "688981",
"net_main_inflows": -14523.55 * 10000,
"net_main_inflow_rate": -10.77 / 100,
"net_huge_inflows": -17053.72 * 10000,
"net_huge_inflow_rate": -12.65 / 100,
"net_big_inflows": 2530.17 * 10000,
"net_big_inflow_rate": 1.88 / 100,
"net_medium_inflows": 6945.23 * 10000,
"net_medium_inflow_rate": 5.15 / 100,
"net_small_inflows": 7578.32 * 10000,
"net_small_inflow_rate": 5.62 / 100
}]
StockMoneyFlow.test_data_correctness(region=region,
provider=provider,
data_samples=data_samples)
def record(self, entity, start, end, size, timestamps):
# 上证
if entity.code == "000001":
all_df = StockMoneyFlow.query_data(
provider=self.provider, start_timestamp=start, filters=[StockMoneyFlow.entity_id.like("stock_sh%")]
)
# 深证
elif entity.code == "399001":
all_df = StockMoneyFlow.query_data(
provider=self.provider, start_timestamp=start, filters=[StockMoneyFlow.entity_id.like("stock_sz%")]
)
# 创业板
elif entity.code == "399006":
all_df = StockMoneyFlow.query_data(
provider=self.provider, start_timestamp=start, filters=[StockMoneyFlow.code.like("300%")]
)
# 科创板
elif entity.code == "000688":
all_df = StockMoneyFlow.query_data(
provider=self.provider, start_timestamp=start, filters=[StockMoneyFlow.code.like("688%")]
)
if pd_is_not_null(all_df):
g = all_df.groupby("timestamp")
for timestamp, df in g:
se = pd.Series(
{
"id": "{}_{}".format(entity.id, to_time_str(timestamp)),
"entity_id": entity.id,
"timestamp": timestamp,
"code": entity.code,
"name": entity.name,
}
)
for col in [
"net_main_inflows",
"net_huge_inflows",
"net_big_inflows",
"net_medium_inflows",
"net_small_inflows",
]:
se[col] = df[col].sum()
for col in [
"net_main_inflow_rate",
"net_huge_inflow_rate",
"net_big_inflow_rate",
"net_medium_inflow_rate",
"net_small_inflow_rate",
]:
se[col] = df[col].sum() / len(df)
index_df = se.to_frame().T
self.logger.info(index_df)
df_to_db(
df=index_df, data_schema=self.data_schema, provider=self.provider, force_update=self.force_update
)
return None