def cond_append_to_month(d_df):
month_ends = generate_months_ends()
# 在d_df里的月末日期
me_in_d = [me for me in month_ends if me in d_df.columns]
#
m_e_loc_list = [np.where(d_df.columns == me)[0][0] for me in me_in_d]
m_s_loc_list = [me + 1 for me in m_e_loc_list]
# 表头插入
m_s_loc_list = [0] + m_s_loc_list
# 删除最后一个
m_s_loc_list.pop()
# len(m_e_loc_list)
# len(m_s_loc_list)
res_df = pd.DataFrame()
pre_se = pd.Series(True, index=d_df.index)
for col, se in d_df.iteritems():
loc = np.where(d_df.columns == col)[0][0]
# 月初第一个交易日
if loc in m_s_loc_list:
pre_se = pd.Series(True, index=d_df.index)
res_se = pre_se & se
res_df = pd.concat([res_df, pd.DataFrame({col: res_se})], axis=1)
pre_se = res_se
return res_df
def update_f_data_from_wind(special_year=2015):
path = os.path.join(data_dair, 'download_from_juyuan')
w.start()
data = Data()
stock_basic_inform = data.stock_basic_inform
mes = generate_months_ends()
iterms = [ # StructWind('rd_exp', 'Q', 'unit=1;rptType=1;Days=Alldays'),
StructWind('west_netprofit_YOY', 'M')
]
codes_str = ''
for i in stock_basic_inform.index:
codes_str = codes_str + ',' + i
codes_str = codes_str[1:]
eds = datetime.today().strftime("%Y-%m-%d")
for it in iterms:
name = it.name
period = it.period
other = it.other
try:
tmp_df = eval('data.' + name.lower())
tds = tmp_df.columns[-1].strftime("%Y-%m-%d")
except Exception as e:
tmp_df = pd.DataFrame()
tds = datetime(2009, 1, 1).strftime("%Y-%m-%d")
# "unit=1;rptType=1;Period=Q;Days=Alldays"
if other:
oth = 'Period=' + period + ';' + other
else:
oth = 'Period=' + period
if special_year: # = 2019
mes0 = [m for m in mes if m.year == special_year]
tds = mes0[0].strftime("%Y-%m-%d")
eds = mes0[-1].strftime("%Y-%m-%d")
if not special_year and period == 'Q' and (datetime.today() -
tds).days < 110:
continue
elif not special_year and period == 'M' and (datetime.today() -
tds).days < 20:
continue
res_tmp = w.wsd(codes_str, name, tds, eds, oth, usedf=True)
res_tmp1 = res_tmp[1]
res_tmp1 = res_tmp1.T
tmp_df = pd.concat([tmp_df, res_tmp1], axis=1)
# 读取本地数据时和Wind提取数据时的时间格式可能不一样，统一一下才能排序
tmp_df.columns = pd.to_datetime(tmp_df.columns)
# 把columns排序
tt = list(tmp_df.columns)
tt.sort()
tmp_df = tmp_df[tt]
data.save(tmp_df, name.lower(), save_path=path)
def update_index_wei():
w.start()
data = Data()
zz500_wt = data.zz500_wt
hs300_wt = data.hs300_wt
mes = generate_months_ends()
# 先删除一些不是月末的数据
to_del = [c for c in zz500_wt.columns if c not in mes]
if len(to_del) > 0:
zz500_wt = zz500_wt.drop(to_del, axis=1)
to_del = [c for c in hs300_wt.columns if c not in mes]
if len(to_del) > 0:
hs300_wt = hs300_wt.drop(to_del, axis=1)
new_mes = [m for m in mes if m > zz500_wt.columns[-1]]
for m in new_mes:
m_str = m.strftime("%Y-%m-%d")
# 沪深300
res = w.wset("indexconstituent",
"date=" + m_str + ";windcode=000300.SH",
usedf=True)
res = res[1]
res.set_index('wind_code', inplace=True)
to_add = pd.DataFrame({m: res['i_weight']})
hs300_wt = pd.concat([hs300_wt, to_add], axis=1)
# 中证500
res = w.wset("indexconstituent",
"date=" + m_str + ";windcode=000905.SH",
usedf=True)
res = res[1]
res.set_index('wind_code', inplace=True)
to_add = pd.DataFrame({m: res['i_weight']})
zz500_wt = pd.concat([zz500_wt, to_add], axis=1)
data.save(hs300_wt,
'hs300_wt',
save_path=r'D:\pythoncode\IndexEnhancement\指数相关')
data.save(zz500_wt,
'zz500_wt',
save_path=r'D:\pythoncode\IndexEnhancement\指数相关')
def deal_daily_macro_data(daily_dat):
if '频率' in daily_dat.index:
daily_dat.drop('频率', axis=0, inplace=True)
# 先移动
daily_macro_data = daily_dat.shift(1)
# 再删除
daily_macro_data.dropna(how='all', inplace=True)
# 添加NAN
for i in range(1, len(daily_macro_data.index)):
for j in range(0, len(daily_macro_data.columns)):
if pd.isna(daily_macro_data.iloc[i, j]) and not pd.isna(
daily_macro_data.iloc[i - 1, j]):
daily_macro_data.iloc[i, j] = daily_macro_data.iloc[i - 1, j]
month_ends = generate_months_ends()
selected_index = [m for m in month_ends if m in daily_macro_data.index]
res_df = daily_macro_data.loc[selected_index, :]
res_df['利差'] = res_df['中债企业债到期收益率（AAA）：1年'] - res_df['中债国债到期收益率：1年']
res_df.drop('中债企业债到期收益率（AAA）：1年', axis=1, inplace=True)
return res_df
def __init__(self, status):
super().__init__()
# status = 'update' 表示仅对已有的因子值进行更新， ='all' 表示全部重新计算
self._mes = generate_months_ends()
self._status = status