def fix_symbol(self, stock: str, factors: list or f,
start_date: datetime.date or str, end_date: datetime.date
or str):
start = time.time()
# 格式化参数
stock = convert_11code(stock)[0]
start_date = convert2datetime(start_date)
end_date = convert2datetime(end_date)
mark2factor_map = dis_mark2factor_map(factors, self.factor2mark_map)
# 初始化 ret
calendar = TradeCalendar()
calendar = calendar.calendar(start_date, end_date)
calendar = calendar[calendar['trade']]['date']
ret = numpy.array(calendar, dtype=[('date', 'U10')])
columns = list()
for mark in mark2factor_map:
instance = self.mark2instance_map.get(mark, None)
if instance:
sub_ret = instance.fix_symbol(stock, mark2factor_map[mark],
start_date, end_date)
sub_column = list(sub_ret.dtype.names)[1:]
columns = columns + sub_column
sub_ret = sub_ret[sub_column]
ret = rfn.merge_arrays((ret, sub_ret),
asrecarray=True,
flatten=True)
ret.dtype.names = ['date'] + columns
end = time.time()
print('fix_symbol耗时：', end - start)
return numpy.array(ret)
def fix_factor(self, stock_list: list, factor: f or list, start_date: str or datetime.date,
end_date: str or datetime.date):
# 格式化参数
stock_list = convert_11code(stock_list)
collection2factor_map = dis_collection2factor_map(factor, self.factor2collection_map)
start_date = convert2datetime(start_date)
end_date = convert2datetime(end_date)
end_date = end_date + datetime.timedelta(hours=23, minutes=59, seconds=59)
# 查询停牌时间
calendar = TradeCalendar().calendar(start_date.strftime("%Y%m%d"),
end_date.strftime("%Y%m%d"))
trading_calendar = calendar['date'][calendar['trade']]
trading_calendar_index = pandas.DataFrame(trading_calendar,
columns=['index']).set_index('index')
rett = trading_calendar_index.copy()
# 确定要查询的集合和字段值
collection, field = list(collection2factor_map.items())[0]
field = field[0].name
snap = ['SecuCode', 'PubDate', field]
doc_snap = {k: 1 for k in snap}
doc_snap["_id"] = 0
# 查询
db_coll = connect_coll(collection, self._db)
ret = db_coll.find({'SecuCode': {'$in': stock_list},
"PubDate": {"$gte": start_date, "$lte": end_date}}, doc_snap)
# 生成查询结果
data = pandas.DataFrame(list(ret))
# 对查询结果进行规范化
if not data.empty:
data[snap[1]] = data[snap[1]].map(lambda x: x.strftime('%Y-%m-%d'))
data = data[snap]
data.columns = ['stock', 'time', field]
data = pandas.crosstab(data['time'], data['stock'], values=data[field], aggfunc='last')
# 更新 rett
rett = data.merge(rett, left_index=True, right_index=True, how='outer')
rett = rett.fillna(method='pad') # 先向后填充数据
rett = rett.ix[trading_calendar_index.index] # 再以日历限制一次日期
to_concat_ret = pandas.DataFrame(dict(zip(stock_list, [1] * len(stock_list))),index=['1'])
rett = pandas.concat([rett, to_concat_ret])
rett = rett.drop(['1'])
# 整理结果
rett = rett.astype(float)
rett = rett.to_records()
rett.dtype.names = ['date'] + list(rett.dtype.names)[1:]
# 暂时返回structured array，后面可以让用户选择返回pandas
# 固定了因子的表格，表的行索引是股票，列索引是时间
return numpy.array(rett)
def fix_symbol(self, stock: str, factors: list or f, start_date: datetime.date or str,
end_date: datetime.date or str):
# 格式化参数
stock = convert_11code(stock)[0]
collection2factor_map = dis_collection2factor_map(factors, self.factor2collection_map)
start_date = convert2datetime(start_date)
end_date = convert2datetime(end_date)
end_date = end_date + datetime.timedelta(hours=23, minutes=59, seconds=59)
# 查询停牌时间
calendar = TradeCalendar().calendar(start_date.strftime("%Y%m%d"),
end_date.strftime("%Y%m%d"))
trading_calendar = calendar['date'][calendar['trade']]
trading_calendar_index = pandas.DataFrame(trading_calendar,
columns=['index']).set_index('index')
rett = trading_calendar_index.copy()
# 确定要查询的集合和字段值
_year = int(start_date.strftime("%Y")) - 1
start_date = datetime.datetime(_year, 1, 1, 0, 0, 0)
for collection in collection2factor_map:
factor_name_list = gen_factor_name_list(collection2factor_map[collection])
snap = ['PubDate', ]
snap.extend(factor_name_list)
doc_snap = {k: 1 for k in snap}
doc_snap["_id"] = 0
# 查询
db_coll = connect_coll(collection, self._db)
data = db_coll.find({'SecuCode': stock,
"PubDate": {"$gte": start_date, "$lte": end_date}}, doc_snap)
# 生成查询结果
data = pandas.DataFrame(list(data))
# 对查询结果进行规范化
if not data.empty:
data[snap[0]] = data[snap[0]].map(lambda x: x.strftime('%Y-%m-%d'))
data = data[snap]
data = data.set_index(snap[0])
# 循环更新 rett
rett = rett.merge(data, left_index=True, right_index=True, how='outer')
rett[factor_name_list] = rett[factor_name_list].fillna(method='pad') # 先向后填充数据
rett = rett.ix[trading_calendar_index.index] # 再以日历限制一次日期
# 整理结果
rett = rett.astype(float).to_records()
rett.dtype.names = ['date'] + list(rett.dtype.names)[1:]
return numpy.array(rett)
def fix_time(self, stock_list: list or str, factors: list or f,
trade_date: datetime.date or str):
# 格式化参数
start = time.time()
stock_list = convert_11code(stock_list)
mark2factor_map = dis_mark2factor_map(factors, self.factor2mark_map)
trade_date = convert2datetime(trade_date)
# 用股票列表来初始化 ret
ret = numpy.array(list(zip(stock_list)), dtype=[('stock', 'U11')])
columns = list()
for mark in mark2factor_map:
# instance 是一个实例化的三戟叉对象
instance = self.mark2instance_map.get(mark, None)
if instance:
sub_ret = instance.fix_time(stock_list, mark2factor_map[mark],
trade_date)
sub_column = list(sub_ret.dtype.names)[1:]
columns = columns + sub_column # 扩充columns名称
sub_ret = sub_ret[sub_column] # 只取字段值
# 将ret结果不断merge
ret = rfn.merge_arrays((ret, sub_ret),
asrecarray=True,
flatten=True)
ret.dtype.names = ['stock'] + columns
end = time.time()
print('fix_time耗时：', end - start)
# 把[numpy.recarray]对象转化为[numpy.ndarray]对象
return numpy.array(ret)
def fix_factor(self, stock_list: list or str, factor: f,
start_date: datetime.date or str, end_date: datetime.date
or str):
start = time.time()
# 格式化参数
stock_list = convert_11code(stock_list)
start_date = convert2datetime(start_date)
end_date = convert2datetime(end_date)
mark2factor_map = dis_mark2factor_map(factor, self.factor2mark_map)
if not mark2factor_map:
print('未收录因子' + factor.name + '，或您没有获取该因子权限，请联系管理员。')
return
mark = list(mark2factor_map.keys())[0]
instance = self.mark2instance_map.get(mark, None)
ret = instance.fix_factor(stock_list, factor, start_date,
end_date) if instance else None
end = time.time()
print(factor[0].name)
print('fix_factor耗时：', end - start)
# 这个接口不需要切片，也不需要转换对象格式
return ret
def fix_time(self, stock_list: list or str, factors: list or f,
trade_date: datetime.date or str):
# 格式化参数
stock_list = convert_11code(stock_list)
collection2factor_map = dis_collection2factor_map(factors, self.factor2collection_map)
start_date = convert2datetime(trade_date)
end_date = start_date + datetime.timedelta(hours=23, minutes=59, seconds=59)
# 补充缺失股票
rett = pandas.DataFrame(stock_list, columns=['stock']).set_index('stock')
# 确定要查询的集合和字段值
_year = int(start_date.strftime("%Y")) - 1
start_date = datetime.datetime(_year, 1, 1, 0, 0, 0)
for collection in collection2factor_map:
factor_name_list = gen_factor_name_list(collection2factor_map[collection])
snap = ['SecuCode', 'PubDate',]
snap.extend(factor_name_list)
doc_snap = {k: 1 for k in snap}
doc_snap["_id"] = 0
# 查询
db_coll = connect_coll(collection, self._db)
data = db_coll.find({'SecuCode': {'$in': stock_list},
"PubDate": {"$gte": start_date, "$lte": end_date}}, doc_snap)
# 生成查询结果
data = pandas.DataFrame(list(data))
# 对查询结果进行规范化
if not data.empty:
data = data[snap].set_index('PubDate')
data.columns = ['stock'] + factor_name_list
if len(data):
data = data.groupby('stock')
data = pandas.DataFrame([i[1].iloc[-1] for i in data]).set_index('stock')
else:
data = data.set_index('stock')
# 循环更新 rett
rett = rett.merge(data, left_index=True, right_index=True, how='outer')
# 整理结果
rett = rett.astype(float).to_records()
rett.dtype.names = ['stock'] + list(rett.dtype.names)[1:]
return numpy.array(rett)