def peg(self):
# PEG = PE / 过去12个月的EPS增长率
pe_daily = self.pe_daily
basicepsyoy = self.basicepsyoy
basicepsyoy = adjust_months(basicepsyoy)
epsyoy = append_df(basicepsyoy, target_feq='D', fill_type='preceding')
pe_daily = CALFUNC.del_dat_early_than(pe_daily, START_YEAR)
epsyoy = CALFUNC.del_dat_early_than(epsyoy, START_YEAR)
[pe_daily, epsyoy] = align(pe_daily, epsyoy)
[h, l] = pe_daily.shape
pe_ar = pe_daily.values
eps_ar = epsyoy.values
res = np.zeros([h, l])
for i in range(0, h):
for j in range(0, l):
if pd.isna(eps_ar[i, j]) or eps_ar[i, j] == 0:
res[i, j] = np.nan
else:
res[i, j] = pe_ar[i, j] / eps_ar[i, j]
res_df = pd.DataFrame(data=res,
index=pe_daily.index,
columns=pe_daily.columns)
return res_df
def mgmt_ben_top3m(self):
mgmt_ben_top3m = self.stmnote_mgmt_ben_top3m
mgmt_ben_top3m = np.log(mgmt_ben_top3m)
mgmt_ben_top3m = adjust_months(mgmt_ben_top3m, orig='Y')
mgmt_ben_top3m = append_df(mgmt_ben_top3m)
return mgmt_ben_top3m
def Profit_G_q(self): # qfa_yoyprofit：单季度.净利润同比增长率
netprofit = self.netprofitcut # 扣除非经常损益后的净利润
sig_season_netprofit = get_signal_season_value(netprofit)
p_g = CALFUNC.generate_yoygr(sig_season_netprofit)
p_g = adjust_months(p_g)
p_g = append_df(p_g)
profit_g_q = CALFUNC.del_dat_early_than(p_g, START_YEAR)
return profit_g_q
def ROE_G_q(self): # 单季度.ROE同比增长率
roe = self.roe
sig_season_roe = get_signal_season_value(roe)
roe_g = CALFUNC.generate_yoygr(sig_season_roe)
roe_g = adjust_months(roe_g)
roe_g = append_df(roe_g)
roe_g_q = CALFUNC.del_dat_early_than(roe_g, START_YEAR)
return roe_g_q
def grossprofitmargin_ttm(self):
gir = self.grossincomeratiottm
gir = adjust_months(gir)
# 用来扩展月度数据
gir = append_df(gir)
res = CALFUNC.del_dat_early_than(gir, START_YEAR)
return res
def Sales_G_q(self): # qfa_yoysales：单季度.营业收入同比增长率
operatingrevenue = self.operatingrevenue
sig_season_operatingrevenue = get_signal_season_value(operatingrevenue)
sales_g = CALFUNC.generate_yoygr(sig_season_operatingrevenue)
sales_g = adjust_months(sales_g)
sales_g = append_df(sales_g)
sales_g = CALFUNC.del_dat_early_than(sales_g, START_YEAR)
return sales_g
def totalassetturnover(self):
totalassettrate = self.totalassettrate
tmp0 = adjust_months(totalassettrate)
tmp1 = append_df(tmp0)
res = CALFUNC.del_dat_early_than(tmp1, START_YEAR)
return res
def ROA_q(self):
totalassets = self.totalassets
netprofit = self.netprofit
# 得到单季度 净利润
sig_season_netprofit = get_signal_season_value(netprofit)
# 得到季度平均总资产
s_mean_totalassets = get_season_mean_value(totalassets)
roa_q = (sig_season_netprofit / s_mean_totalassets) * 100
roa_q = adjust_months(roa_q)
roa_q = append_df(roa_q)
roa_q = CALFUNC.del_dat_early_than(roa_q, START_YEAR)
return roa_q
def ROE_q(self):
totalshareholderequity = self.totalshareholderequity
netprofit = self.netprofit
# 得到单季度 净利润
sig_season_netprofit = get_signal_season_value(netprofit)
# 得到季度平均总资产
s_mean_equity = get_season_mean_value(totalshareholderequity)
roe_q = (sig_season_netprofit / s_mean_equity) * 100
roe_q = adjust_months(roe_q)
roe_q = append_df(roe_q)
roe_q = CALFUNC.del_dat_early_than(roe_q, START_YEAR)
return roe_q
def assetturnover_q(self):
totalassets = self.totalassets
revenue = self.operatingrevenue
# 得到单季度 净利润
sig_season_revenue = get_signal_season_value(revenue)
# 得到季度平均总资产
s_mean_totalassets = get_season_mean_value(totalassets)
turnover_q = (sig_season_revenue / s_mean_totalassets) * 100
turnover_q = adjust_months(turnover_q)
turnover_q = append_df(turnover_q)
turnover_q = CALFUNC.del_dat_early_than(turnover_q, START_YEAR)
return turnover_q
def grossprofitmargin_diff(self):
revenue = self.operatingrevenue # 营业收入
cost = self.operatingcost # 营业成本
# 财务指标常规处理，移动月份，改月末日期
revenue_q = get_signal_season_value(revenue)
cost_q = get_signal_season_value(cost)
gross_q = (revenue_q - cost_q) / revenue_q
gir_d = CALFUNC.generate_diff(gross_q)
gir_d = adjust_months(gir_d)
# 用来扩展月度数据
gir_d = append_df(gir_d)
res = CALFUNC.del_dat_early_than(gir_d, START_YEAR)
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 grossprofitmargin_q(self):
'''
计算公示：（营业收入 - 营业成本） / 营业收入 * 100 %
计算单季度指标，应该先对 营业收入 和 营业成本 分别计算单季度指标，再计算
'''
revenue = self.operatingrevenue # 营业收入
cost = self.operatingcost # 营业成本
# 财务指标常规处理，移动月份，改月末日期
revenue_q = get_signal_season_value(revenue)
cost_q = get_signal_season_value(cost)
gross_q = (revenue_q - cost_q) / revenue_q
# 调整为公告日期
tmp = adjust_months(gross_q)
# 用来扩展月度数据
tmp = append_df(tmp)
res = CALFUNC.del_dat_early_than(tmp, START_YEAR)
return res
def Profitmargin_q(self): # 单季度净利润率
'''
1.qfa_deductedprofit：单季度.扣除非经常损益后的净利润
2.qfa_oper_rev： 单季度.营业收入
:return:
'''
netprofit = self.netprofitcut # 扣除非经常损益后的净利润
operatingrevenue = self.operatingrevenue
sig_season_netprofit = get_signal_season_value(netprofit)
sig_season_operatingrevenue = get_signal_season_value(operatingrevenue)
profitmargin_q = sig_season_netprofit / sig_season_operatingrevenue
profitmargin_q = adjust_months(profitmargin_q)
profitmargin_q = append_df(profitmargin_q)
pq = CALFUNC.del_dat_early_than(profitmargin_q, START_YEAR)
return pq
def REVSU(self):
netprofit = self.totaloperatingrevenueps
# 得到单季度的数据。
sig_season_va = get_signal_season_value(netprofit)
cols = pd.DataFrame([i for i in sig_season_va.columns])
revsu = pd.DataFrame()
rolling_cols = rolling_windows(cols, 6)
for roll in rolling_cols:
res = _calculate_su_simple(sig_season_va[roll])
res = pd.DataFrame(res.values, index=res.index, columns=[roll[-1]])
revsu = pd.concat([revsu, res], axis=1)
revsu.dropna(how='all', axis=0, inplace=True)
revsu = adjust_months(revsu)
revsu = append_df(revsu)
return revsu
def SUE(self):
# 使用原始的财务数据
eps = self.basiceps
# 得到单季度的数据。
sig_season_va = get_signal_season_value(eps)
cols = pd.DataFrame([i for i in sig_season_va.columns])
sue = pd.DataFrame()
rolling_cols = rolling_windows(cols, 6)
for roll in rolling_cols:
res = _calculate_su_simple(sig_season_va[roll])
res = pd.DataFrame(res.values, index=res.index, columns=[roll[-1]])
sue = pd.concat([sue, res], axis=1)
sue.dropna(how='all', axis=0, inplace=True)
sue = adjust_months(sue)
sue = append_df(sue)
return sue
def layer_test(factor_name, pool):
para_dict = {'因子名称': factor_name,
'max_para': 30,
'min_para': 1,
}
pool_tmp = test_mode(pool, para_dict)
pool_tmp = append_df(pool_tmp, target_feq='D')
pool_wei_tmp = get_wei(pool_tmp)
pool_wei_tmp = append_df(pool_wei_tmp, target_feq='D')
# 简单回测
daily_return_bottom, net_cpd_1_30, cum_excess_df = easy_bt(pool_wei_tmp, basic_return_path=None)
para_dict = {'因子名称': factor_name,
'max_para': 69,
'min_para': 31,
}
pool_tmp = test_mode(pool, para_dict)
pool_tmp = append_df(pool_tmp, target_feq='D')
pool_wei_tmp = get_wei(pool_tmp)
pool_wei_tmp = append_df(pool_wei_tmp, target_feq='D')
# 简单回测
daily_return, net_cpd_31_69, cum_excess_df = easy_bt(pool_wei_tmp, basic_return_path=None)
para_dict = {'因子名称': factor_name,
'max_para': 100,
'min_para': 70,
}
pool_tmp = test_mode(pool, para_dict)
pool_tmp = append_df(pool_tmp, target_feq='D')
pool_wei_tmp = get_wei(pool_tmp)
pool_wei_tmp = append_df(pool_wei_tmp, target_feq='D')
# 简单回测
daily_return_top, net_cpd_70_100, cum_excess_df = easy_bt(pool_wei_tmp, basic_return_path=None)
res_df = pd.DataFrame({'top': net_cpd_70_100['net_value'], 'middle': net_cpd_31_69['net_value'],
'bottom': net_cpd_1_30['net_value']})
fig = plt.figure()
plt.plot(res_df)
plt.legend(list(res_df.columns))
plt.show()
top_sub_bottom = daily_return_top['daily_return'] - daily_return_bottom['daily_return']
top_sub_bottom_cum = (top_sub_bottom + 1).cumprod()
top_sub_bottom_df = pd.DataFrame({"top减bottom累计收益": top_sub_bottom_cum})
top_sub_bottom_df.index.name = '日期'
fig = plt.figure()
plt.plot(top_sub_bottom_df)
plt.show()
save_path = r'D:\pythoncode\IndexEnhancement\股票池\计算机'
res_df.to_csv(os.path.join(save_path, factor_name+'_3.csv'))
top_sub_bottom_df.to_csv(os.path.join(save_path, factor_name+'_top减bottom_3.csv'))
def financial_condition_pool(selection_dict, start_date, end_date):
data = Data()
stock_basic = data.stock_basic_inform
firstindustry = stock_basic[['中信一级行业']]
all_stocks_code = stock_basic[['sec_name'.upper(), 'ipo_date'.upper()]]
# roe
roettm = data.roettm
# 净利润同比增速
netprofitgrowrate = data.netprofitgrowrate
# 基本每股收益同比增长率
basicepsyoy = data.basicepsyoy
# 销售毛利率
grossincome = data.grossincomeratiottm
# 资产负债率
debtassetsratio = data.debtassetsratio
# 估值
pe = data.pe
cond_total = pd.DataFrame()
for plate_name, conditions_dict in selection_dict.items():
pe_con = None
con_plate = None
if plate_name == 'all':
codes_in_industry = list(firstindustry.index)
else:
codes_in_industry = [ind for ind in firstindustry.index if firstindustry[ind] == plate_name]
for conditions_type, tuples in conditions_dict.items():
if conditions_type.split('_')[0] == 'scope':
myfun = 'scopy_condition'
for t in tuples:
if t == 'pe':
has_pe = 1
pe_con = copy.deepcopy(t)
continue
res = eval('select_stocks(' + tuples[0] + ', codes_in_industry, start_date, end_date)')
res_con = eval(myfun + '(res, minV=' + str(tuples[1]) + ', maxV= ' + str(tuples[2]) + ')')
if isinstance(con_plate, pd.DataFrame):
con_plate = con_plate & res_con
else:
con_plate = res_con
elif conditions_type.split('_')[0] == 'rise':
myfun = 'rise_condition'
# for t in tuples:
res = eval('select_stocks(' + tuples[0] + ', codes_in_industry, start_date, end_date)')
res_con = eval(myfun + '(res,' + str(tuples[1]) + ')')
if isinstance(con_plate, pd.DataFrame):
con_plate = con_plate & res_con
else:
con_plate = res_con
# 不同行业之间合并
cond_total = pd.concat([cond_total, con_plate], axis=1)
# 剔除上市未满N年得股票，N = 1
# N = 1
# for col, items in cond_total.iteritems():
# for i in items.index:
# if items[i]:
# if i in all_stocks_code.index:
# de = col - all_stocks_code.loc[i, 'ipo_date']
# if de.days < N * 365:
# items[i] = False
# else:
# # i 不在all_stocks_code里面，是因为all_stocks_code没有更新，说明该股票是最近上市的股票，
# # 直接全部复制为False
# items[i] = False
# 剔除st
for col, items in cond_total.iteritems():
for i in items.index:
if i in all_stocks_code.index and 'ST' in all_stocks_code.loc[i, 'sec_name'.upper()]:
items[i] = False
# 调整为公告日期
cond_total = adjust_months(cond_total)
# 用来扩展月度数据
cond_total = append_df(cond_total)
return cond_total
def ROA_ttm(self):
roa_ttm = self.roattm
roa_ttm = adjust_months(roa_ttm)
roa_ttm = append_df(roa_ttm)
roa_ttm = CALFUNC.del_dat_early_than(roa_ttm, START_YEAR)
return roa_ttm