def update_future_price():
data = Data()
try:
nh_future_price_daily = data.nh_future_price_daily.T
st_date = nh_future_price_daily.index[-1] - timedelta(10)
except Exception as e:
nh_future_price_daily = pd.DataFrame()
st_date = datetime(2010, 1, 1)
ed_date = datetime.today().strftime("%Y%m%d")
add_df = pd.DataFrame()
for key in NH_index_dict.keys():
df_tmp = pro.index_daily(ts_code=key,
start_date=st_date.strftime('%Y%m%d'),
end_date=ed_date)
df_tmp = df_tmp.set_index('trade_date')
df_tmp.index = pd.to_datetime(df_tmp.index)
df_tmp.sort_index(inplace=True)
add_df = pd.concat(
[add_df, pd.DataFrame({key: df_tmp['close']})], axis=1)
# nh_future_price_daily
to_del_index = [
i for i in add_df.index if i in nh_future_price_daily.index
]
nh_future_price_daily.drop(to_del_index, axis=0, inplace=True)
nh_future_price_daily = pd.concat([nh_future_price_daily, add_df], axis=0)
save_p = r'D:\commodity_datebase\price_data'
data.save(nh_future_price_daily,
'nh_future_price_daily.csv',
save_path=save_p)
def compute_future_beta():
# 存储地址为：D:\Datebase_Stock\Date\index\stock_future\sf_beta.csv
data = Data()
sf_close_daily = data.sf_close_daily
index_price_daily = data.index_price_daily.T
# 求一下日期的交集，避免日期不同的潜在问题
tt = list(set(sf_close_daily.columns) & set(index_price_daily.index))
tt.sort()
sf_close_daily = sf_close_daily[tt]
index_price_daily = index_price_daily.loc[tt, :]
sf_beta = pd.DataFrame()
for c, se in sf_close_daily.iterrows():
if 'IC' in c:
tmp_i = index_price_daily['ZZ500']
elif 'IF' in c:
tmp_i = index_price_daily['HS300']
elif 'IH' in c:
tmp_i = index_price_daily['SZ50']
else:
print('Code Bug')
raise ValueError
# 去掉Nan
tmp_c = se.dropna()
tmp_i = tmp_i[tmp_c.index]
if len(tmp_c) > 22:
bet = rolling_regress_1(tmp_i, tmp_c, window=22)
sf_beta = pd.concat([sf_beta, pd.DataFrame({c: bet}).T], axis=0)
p = os.path.join(data_dair, 'index', 'stock_future')
data.save(sf_beta, 'sf_beta', p)
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_daily_basic():
data = Data()
pb_df = data.pb_daily
pe_df = data.pe_daily
turnover_df = data.turnoverrate_daily
negotiablemv_df = data.negotiablemv_daily # 流通市值(万元)
totalmv_df = data.totalmv_daily # 总市值(万元)
st = np.min([
pb_df.columns[-1], pe_df.columns[-1], turnover_df.columns[-1],
negotiablemv_df.columns[-1], totalmv_df.columns[-1]
])
# turnover_rate_f float 换手率（自由流通股）
# total_mv float 总市值 （万元）
ed = datetime.today() - timedelta(1)
tds = trade_days()
days_to_update = [d for d in tds if st <= d <= ed]
if len(days_to_update) == 0:
print('日度指标数据：已经更新到最新数据，无需更新，自动退出')
return None
for d in days_to_update:
# d = days_to_update[0]
d_str = d.strftime("%Y%m%d")
tmp_df = pro.daily_basic(
ts_code='',
trade_date=d_str,
fields='ts_code,turnover_rate,pe,pb,total_mv,circ_mv')
tmp_df = tmp_df.set_index('ts_code').sort_index()
pb_df = insert_to_df(pb_df, pd.DataFrame({d: tmp_df['pb']}))
pe_df = insert_to_df(pe_df, pd.DataFrame({d: tmp_df['pe']}))
turnover_df = insert_to_df(turnover_df,
pd.DataFrame({d: tmp_df['turnover_rate']}))
totalmv_df = insert_to_df(totalmv_df,
pd.DataFrame({d: tmp_df['total_mv']}))
negotiablemv_df = insert_to_df(negotiablemv_df,
pd.DataFrame({d: tmp_df['circ_mv']}))
sleep(0.33)
history_file = os.path.join(date_dair, 'download_from_juyuan')
data.save(pb_df, 'pb_daily.csv', save_path=history_file)
data.save(pe_df, 'pe_daily.csv', save_path=history_file)
data.save(negotiablemv_df,
'NegotiableMV_daily.csv',
save_path=history_file)
data.save(totalmv_df, 'TotalMV_daily.csv', save_path=history_file)
data.save(turnover_df, 'TurnoverRate_daily.csv', save_path=history_file)
def compute_changepect_open_daily():
data = Data()
open_daily = data.openprice_daily
adjfactor = data.adjfactor
open_daily = open_daily * adjfactor
open_daily.dropna(axis=1, how='all', inplace=True)
open_daily_shift = open_daily.shift(1, axis=1)
changepect_open_daily = open_daily / open_daily_shift
changepect_open_daily = (changepect_open_daily - 1) * 100
changepect_open_daily.dropna(how='all', axis=1, inplace=True)
data.save(changepect_open_daily, 'changepect_open_daily'.upper())
def update_futmap():
data = Data()
try:
fut_map = data.fut_map.T
start_d = fut_map.index[-1].strftime("%Y%m%d")
except Exception as e:
fut_map = pd.DataFrame()
start_d = datetime(2009, 1, 1).strftime("%Y%m%d")
end_d = datetime.today().strftime("%Y%m%d")
domain_if = pro.fut_mapping(ts_code='IF.CFX',
start_date=start_d,
end_date=end_d)
domain_ih = pro.fut_mapping(ts_code='IH.CFX',
start_date=start_d,
end_date=end_d)
domain_ic = pro.fut_mapping(ts_code='IC.CFX',
start_date=start_d,
end_date=end_d)
domain_if.set_index('trade_date', inplace=True)
domain_ih.set_index('trade_date', inplace=True)
domain_ic.set_index('trade_date', inplace=True)
domain_if.drop('ts_code', axis=1, inplace=True)
domain_ih.drop('ts_code', axis=1, inplace=True)
domain_ic.drop('ts_code', axis=1, inplace=True)
domain_if.columns = ['IF']
domain_ih.columns = ['IH']
domain_ic.columns = ['IC']
domain_if.index = pd.to_datetime(domain_if.index)
domain_if.sort_index(inplace=True)
domain_ih.index = pd.to_datetime(domain_ih.index)
domain_ih.sort_index(inplace=True)
domain_ic.index = pd.to_datetime(domain_ic.index)
domain_ic.sort_index(inplace=True)
domain_fut = pd.concat([domain_if, domain_ih, domain_ic], axis=1)
domain_fut = domain_fut.applymap(lambda x: x.split('.CFX')[0] + '.CFE'
if isinstance(x, str) else x)
dupl = [i for i in domain_fut.index if i in fut_map.index]
domain_fut.drop(dupl, axis=0, inplace=True)
fut_map = pd.concat([fut_map, domain_fut], axis=0)
p = os.path.join(date_dair, 'index')
data.save(fut_map, 'fut_map', save_path=p)
print('期货主力合约映射表下载完毕')
def Rps(self):
data = Data()
all_codes = data.stock_basic_inform
all_codes = pd.to_datetime(all_codes['ipo_date'.upper()])
close_daily = data.closeprice_daily
adjfactor = data.adjfactor
close_price = close_daily * adjfactor
close_price.dropna(axis=1, how='all', inplace=True)
# 剔除上市一年以内的情况，把上市二年以内的股票数据都设为nan
for i, row in close_price.iterrows():
if i not in all_codes.index:
row[:] = np.nan
continue
d = all_codes[i]
row[row.index[row.index < d + timedelta(200)]] = np.nan
ext_120 = close_price / close_price.shift(periods=120, axis=1)
ext_120.dropna(how='all', axis=1, inplace=True)
rps_120 = ext_120.apply(scaler, scaler_max=100, scaler_min=1)
rps = rps_120
rps.dropna(how='all', axis=1, inplace=True)
res = rps.apply(scaler, scaler_max=100, scaler_min=1)
res = CALFUNC.del_dat_early_than(res, START_YEAR)
return res
def month_return_compare_to_market_index(stock_list, his_month):
data = Data()
changePCT = data.changepct_monthly
ff = None
for c in changePCT.columns:
if c.year == his_month.year and c.month == his_month.month:
ff = c
break
res2 = changePCT.loc[stock_list, ff]
index_path = r'D:\pythoncode\IndexEnhancement\指数相关'
index_price = pd.read_csv(os.path.join(index_path, 'index_price_monthly.csv'), engine='python')
index_price = index_price.set_index(index_price.columns[0])
index_price.index = pd.to_datetime(index_price.index)
index_r = (index_price - index_price.shift(1)) / index_price.shift(1)
fff = None
for c in index_r.index:
if c.year == his_month.year and c.month == his_month.month:
fff = c
break
res1 = pd.DataFrame({fff: index_r.loc[fff, :].drop_duplicates()})
tt = pd.DataFrame(data=res2.mean(), index=['组合'], columns=[ff])
res1 = pd.concat([res1, tt], axis=0)
return res1, res2
def __init__(self, factor_path, save_path, sentinel=1000, update_only=False):
self.data = Data()
self.sentinel = sentinel
# if not update_only:
# self.dates_d = sorted(self.adjfactor.columns)
# self.dates_m = sorted(self.pct_chg_M.columns)
self.save_path = save_path
self.factor_path = factor_path
def del_market(stock_pool, to_del_mkt):
data = Data()
stock_basic = data.stock_basic_inform
mkt = stock_basic[['MKT']]
for col, v in stock_pool.iteritems():
si = [i for i in mkt[mkt[mkt.columns[0]] == to_del_mkt].index if i in stock_pool.index]
v[si] = False
return stock_pool
def eps_over_80(stock_pool):
data = Data()
rps = data.rps
tmp = rps[[rps.columns[-1]]]
stock_pool = pd.concat([stock_pool, tmp], axis=1, join='inner')
to_save = stock_pool.index[stock_pool[rps.columns[-1]] > 80]
stock_pool = stock_pool.loc[to_save, :]
return stock_pool
def name_to_code(names_list):
data = Data()
all_stocks_code = data.stock_basic_inform
all_stocks_code = all_stocks_code[['sec_name'.upper()]]
all_stocks_code['code'.upper()] = all_stocks_code.index
all_stocks_code = all_stocks_code.set_index('sec_name'.upper())
res = list(all_stocks_code.loc[names_list, 'code'.upper()])
return res
def Rps(self):
data = Data()
all_codes = data.stock_basic_inform
all_codes = pd.to_datetime(all_codes['ipo_date'.upper()])
close_daily = data.closeprice_daily
adjfactor = data.adjfactor
close_price = close_daily * adjfactor
close_price.dropna(axis=1, how='all', inplace=True)
# 剔除上市一年以内的情况，把上市二年以内的股票数据都设为nan
for i, row in close_price.iterrows():
if i not in all_codes.index:
row[:] = np.nan
continue
d = all_codes[i]
row[row.index[row.index < d + timedelta(200)]] = np.nan
if self._status == 'all':
ext_120 = close_price / close_price.shift(periods=120, axis=1)
ext_120.dropna(how='all', axis=1, inplace=True)
rps_120 = ext_120.apply(scaler, scaler_max=100, scaler_min=1)
rps = rps_120
rps.dropna(how='all', axis=1, inplace=True)
res = rps.apply(scaler, scaler_max=100, scaler_min=1)
res = CALFUNC.del_dat_early_than(res, START_YEAR)
elif self._status == 'update':
hased_rps = data.RPS
to_update = [
col for col in close_price.columns
if col not in hased_rps.columns and col > hased_rps.columns[-1]
]
if len(to_update) == 0:
print('RPS无需要更新的部分')
return hased_rps
st = to_update[0]
st_loc = np.where(close_price.columns == st)[0][0]
st_loc = st_loc - 121
close_price_new = close_price.iloc[:, st_loc:]
ext_120 = close_price_new / close_price_new.shift(periods=120,
axis=1)
ext_120.dropna(how='all', axis=1, inplace=True)
rps_120 = ext_120.apply(scaler, scaler_max=100, scaler_min=1)
rps_120.dropna(how='all', axis=1, inplace=True)
res0 = rps_120.apply(scaler, scaler_max=100, scaler_min=1)
hased_rps[res0.columns] = res0
res = hased_rps
return res
def main(p_dict, fp, is_ind_neu, is_size_neu, is_plate_neu, special_plate=None,
selection=None):
"""
is_ind_neu : 是否做行业中性化处理，对股票多因子需要，做行业多因子时不需要
输出： 预处理后的因子截面数据（如2009-01-23.csv文件）
顺序：缺失值填充、去极值、中性化、标准化
（因输入的截面数据中所含财务类因子默认已经过
财务日期对齐处理，故在此不再进行该步处理）
注：针对无需处理的因子，如Rps，把因子名称添加到constant文件中的info_cols变量中，相关函数会通过import该变量的方式导入
并跳过处理过程
"""
file_path = p_dict['file_path']
save_path = p_dict['save_path']
# 读取原始因子截面数据
try:
data = pd.read_csv(os.path.join(file_path, fp), engine='python',
encoding='gbk')
except Exception as e:
print('debug')
if 'No' in data.columns:
data = data.set_index('No')
# 若针对特定板块，则删除其他板块的股票数据
if special_plate:
data_ = Data()
stock_basic = data_.stock_basic_inform
sw_1 = stock_basic[['申万一级行业']]
stock_list = list(sw_1.index[sw_1[sw_1.columns[0]] == special_plate])
codes = [i for i in data.index if data.loc[i, 'Code'] in stock_list]
data = data.loc[codes, :]
data.index = range(0, len(data))
# 历史回测：删除一些未上市的股票、下个月未开盘的股票
# 跟踪：无动作
data_to_process = drop_some(data)
# 预处理步骤依次进行
data_to_process = fill_na(data_to_process) # 缺失值填充
if len(data_to_process) == 0:
print('debug')
data_to_process = winsorize(data_to_process) # 去极值
if is_ind_neu or is_size_neu:
data_to_process = neutralize(data_to_process, ind_neu=is_ind_neu, size_neu=is_size_neu) # 中性化
data_to_process = standardize(data_to_process) # 标准化
data_final = data_to_process
if data_final.index.name != 'No':
data_final.index = range(1, len(data_final)+1)
data_final.index.name = 'No'
data_final.to_csv(os.path.join(save_path, fp), encoding='gbk')
def get_latest_updated_date():
data = Data()
c = data.closeprice_daily
o = data.openprice_daily
adj = data.adjfactor
mv = data.negotiablemv_daily
pe = data.pe_daily
res = np.min([c.columns[-1], o.columns[-1], adj.columns[-1], mv.columns[-1], pe.columns[-1]])
return res
def del_industry(stock_pool, to_del_indus):
data = Data()
stock_basic = data.stock_basic_inform
sw_1 = stock_basic[['申万一级行业']]
for col, v in stock_pool.iteritems():
for ind in to_del_indus:
si = [i for i in sw_1[sw_1[sw_1.columns[0]] == ind].index if i in stock_pool.index]
v[si] = False
return stock_pool
def get_net_buy_rate():
data = Data()
negotiablemv = data.negotiablemv_daily
main_net_buy_amount = data.main_net_buy_amount
dat_pd = main_net_buy_amount / negotiablemv
dat_pd.dropna(how='all', axis=1, inplace=True)
save_path = r'D:\pythoncode\IndexEnhancement\barra_cne6\download_from_juyuan'
dat_pd.to_csv(os.path.join(save_path, 'main_net_buy_ratio.csv'),
encoding='gbk')
def form_stock2_second_indus(panel_path, save_path):
'''
:param panel_path: 月度数据的存储地址
:param save_path: 目标文件的存储地址
:return:
'''
# 把股票的月度数据转换为行业的形式
data = Data()
indus_infor = data.secondindustryname
indus_infor = data.reindex(indus_infor)
dirlist = os.listdir(panel_path)
indux_wei_total = pd.DataFrame()
for f in dirlist:
stock_wei = pd.read_csv(os.path.join(panel_path, f),
encoding='gbk',
engine='python')
stock_wei = stock_wei.set_index('wind_code')
if f.split('.')[0] in indus_infor.columns:
stock_wei['second_indus'] = indus_infor[f.split('.')[0]]
else:
stock_wei['second_indus'] = indus_infor[indus_infor.columns[-1]]
stock_wei = stock_wei.dropna(axis=0, how='any')
stock_wei['i_weight'] = 100 * stock_wei['i_weight'] / np.sum(
stock_wei['i_weight'])
grouped = stock_wei[['i_weight',
'second_indus']].groupby('second_indus')
indus_wei = grouped.sum()
indus_wei = indus_wei.T
indus_wei.index = [f.split('.')[0]]
indux_wei_total = pd.concat([indux_wei_total, indus_wei], axis=0)
indux_wei_total = indux_wei_total.fillna(0)
indux_wei_total.to_csv(os.path.join(save_path, '二级行业权重.csv'),
encoding='gbk')
def rps_factor(rps_min=50, rps_max=100):
data = Data()
rps = data.RPS
rps.fillna(0, inplace=True)
rps_cond = float_2_bool_df(rps, min_para=rps_min, max_para=rps_max)
# 用于回测,向右移动一期
rps = rps.shift(1, axis=1)
rps_cond = rps_cond.shift(1, axis=1)
rps.dropna(axis=1, how='all', inplace=True)
rps_cond.dropna(axis=1, how='all', inplace=True)
return rps_cond
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=os.path.join(data_dair, 'index'))
data.save(zz500_wt, 'zz500_wt', save_path=os.path.join(data_dair, 'index'))
def __init__(self,
alpha_factor_names=industry_factor_names,
update_only=True,
max_num=20):
self._data = Data()
self.stock_factor_path = os.path.join(root_dair, '因子预处理模块', '因子')
self.industry_factor_path = os.path.join(root_dair, '行业多因子', '申万三级',
'因子')
self.save_path = os.path.join(root_dair, '行业多因子', '申万三级')
self.icir_e = None
self.factors = alpha_factor_names
self.update_only = update_only
self.max_num = max_num
self.indus_selected = None
def from_stock_wei_2_industry_wei(wei_df):
data = Data()
all_stocks_code = data.stock_basic_inform
all_stocks_code = all_stocks_code[['申万一级行业']]
wei_df = wei_df.fillna(0)
res = pd.DataFrame()
for col, se in wei_df.iteritems():
tmp_df = pd.DataFrame({col: se})
to_group = pd.concat([tmp_df, all_stocks_code], axis=1)
to_group.fillna(0, inplace=True)
grouped = to_group.groupby('申万一级行业').sum()
if 0 in grouped.index:
grouped.drop(0, axis=0, inplace=True)
res = pd.concat([res, grouped], axis=1)
return res
def RDtosales(self):
data = Data()
rd_exp = data.rd_exp
revenue = data.operatingrevenue
rd_exp = CALFUNC.del_dat_early_than(rd_exp, 2018)
revenue = CALFUNC.del_dat_early_than(revenue, 2018)
res = rd_exp / revenue
res = adjust_months(res)
res = append_df(res)
to_del = res.columns[res.isna().sum() / len(res) > 0.9]
res.drop(to_del, axis=1, inplace=True)
return res
def update_pct_monthly():
data = Data()
close_price = data.closeprice_daily
adj = data.adjfactor
months_ends = generate_months_ends()
close_price = adj * close_price
new_columns = [c for c in close_price.columns if c >= datetime(2006, 1, 1)]
close_price = close_price[new_columns]
new_columns = [c for c in close_price.columns if c in months_ends]
close_me = close_price[new_columns]
pct_monthly_pd = close_me / close_me.shift(1, axis=1) - 1
history_file = os.path.join(date_dair, 'download_from_juyuan')
pct_monthly_pd.to_csv(os.path.join(history_file, 'ChangePCT_monthly.csv'),
encoding='gbk')
def compute_month_value():
data = Data()
basic_path = r'D:\pythoncode\IndexEnhancement\barra_cne6\download_from_juyuan'
months_ends = generate_months_ends()
pb_daily = data.pb_daily
my_cols = [m for m in months_ends if m in pb_daily.columns]
pb_monthly = pb_daily[my_cols]
pb_monthly.to_csv(os.path.join(basic_path, 'pb_monthly.csv'),
encoding='gbk')
pe_daily = data.pe_daily
my_cols = [m for m in months_ends if m in pe_daily.columns]
pe_monthly = pe_daily[my_cols]
pe_monthly.to_csv(os.path.join(basic_path, 'pe_monthly.csv'),
encoding='gbk')
def compute_month_value():
data = Data()
basic_path = os.path.join(date_dair, 'download_from_juyuan')
months_ends = generate_months_ends()
pb_daily = data.pb_daily
my_cols = [m for m in months_ends if m in pb_daily.columns]
pb_monthly = pb_daily[my_cols]
pb_monthly.to_csv(os.path.join(basic_path, 'pb_monthly.csv'),
encoding='gbk')
pe_daily = data.pe_daily
my_cols = [m for m in months_ends if m in pe_daily.columns]
pe_monthly = pe_daily[my_cols]
pe_monthly.to_csv(os.path.join(basic_path, 'pe_monthly.csv'),
encoding='gbk')
def update_pct_monthly():
data = Data()
close_price = data.closeprice_daily
adj = data.adjfactor
months_ends = generate_months_ends()
close_price = adj * close_price
new_columns = [c for c in close_price.columns if c >= datetime(2006, 1, 1)]
close_price = close_price[new_columns]
new_columns = [c for c in close_price.columns if c in months_ends]
close_me = close_price[new_columns]
pct_monthly_pd = close_me / close_me.shift(1, axis=1) - 1
basic_path = r'D:\pythoncode\IndexEnhancement\barra_cne6\download_from_juyuan'
pct_monthly_pd.to_csv(os.path.join(basic_path, 'ChangePCT_monthly.csv'),
encoding='gbk')
def easy_bt(wei_stocks, basic_return_infor):
data = Data()
changepct_daily = data.CHANGEPECT_OPEN_DAILY
changepct_daily = changepct_daily.shift(-1, axis=1)
changepct_daily.dropna(how='all', axis=1, inplace=True)
changepct_daily = changepct_daily / 100
wei_stocks, changepct_daily = align(wei_stocks, changepct_daily)
# fee_type='No_fee' 不计算佣金和印花税， 'fee_1'计算佣金和印花税，不计算冲击成本
daily_return, net_value = back_test(changepct_daily, wei_stocks, fee_type='fee_1')
# plt.plot(net_cpd)
# 若有基准日度收益率，则计算累计超额收益率
if isinstance(basic_return_infor, str):
# 有基准收益，算超额收益
basic_return = pd.read_csv(basic_return_infor, engine='python')
basic_return = basic_return.set_index('date')
if 'daily_return' in basic_return.columns:
daily_excess_r = daily_return['daily_return'] - basic_return['daily_return']
# 若没有日度收益数据，则根据日度净值数据计算出日度收益收益数据
elif 'daily_return' not in basic_return.columns and 'net_value' in basic_return.columns:
basic_return['daily_return'] = basic_return['net_value']/basic_return['net_value'].shift(1) - 1
daily_excess_r = daily_return['daily_return'] - basic_return['daily_return']
daily_excess_r.dropna(inplace=True)
daily_excess_cum = (daily_excess_r + 1).cumprod()
cum_excess_df = pd.DataFrame({'cum_excess_ret': daily_excess_cum})
elif isinstance(basic_return_infor, pd.DataFrame):
if 'daily_return' not in basic_return_infor.columns and 'net_value' in basic_return_infor.columns:
basic_return_infor['daily_return'] = basic_return_infor['net_value'] / \
basic_return_infor['net_value'].shift(1) - 1
daily_excess_r = daily_return['daily_return'] - basic_return_infor['daily_return']
daily_excess_r.dropna(inplace=True)
daily_excess_cum = (daily_excess_r + 1).cumprod()
cum_excess_df = pd.DataFrame({'cum_excess_ret': daily_excess_cum})
else:
cum_excess_df = None
return daily_return, net_value, cum_excess_df
def latest_pool(self, method, add_infor=False):
self.get_stock_pool()
stock_pool = self.rov_of_all_stocks(method)
if stock_pool.empty:
return None
tmp = stock_pool[stock_pool.columns[-1]]
tmp = tmp[tmp.index[tmp != 0]]
tmp.sort_values(inplace=True)
s_list = list(tmp.index)
# 添加股票名称
data = Data()
stock_basic = data.stock_basic_inform
res = stock_basic.loc[s_list, 'SEC_NAME']
res_df = pd.DataFrame({'SEC_NAME': res})
res_df.index.name = 'CODE'
# res_df.to_csv('D://库存表.csv', encoding='gbk') TODO
# 是否添加概念数据和调入股票池时间数据
if add_infor:
# 添加调入股票池日期数据
res_df['跳入股票池日期'] = None
for k, v in stock_pool.loc[s_list, :].iterrows():
for i in range(len(v) - 1, -1, -1):
if not v[i]:
res_df.loc[k, '跳入股票池日期'] = v.index[i + 1]
break
# 添加概念数据。
concept = data.concept
res_df = pd.concat([res_df, concept], axis=1, join='inner')
for k, v in res_df['CONCEPT'].items():
try:
res_df.loc[k, 'CONCEPT'] = v.replace('[', '').replace(
']', '').replace('\'', '')
except Exception:
pass
return res_df, stock_pool
def keep_industry(stock_pool, to_keep_indus_list, industry_type='sw'):
data = Data()
stock_basic = data.stock_basic_inform
if industry_type == 'sw':
industry_df = stock_basic[['申万一级行业']]
elif industry_type == 'zx':
industry_df = stock_basic[['中信一级行业']]
for col, v in stock_pool.iteritems():
for ind in to_keep_indus_list:
# 选出该行业的股票
tmp = industry_df[industry_df[industry_df.columns[0]] == ind].index
# 也在stock_pool的index里面
si = [i for i in tmp if i in stock_pool.index]
# 其余行业的股票
se = list(set(stock_pool.index).difference(set(si)))
# 均为否
v[se] = False
return stock_pool
