def get_index_members_akshare(exchange: str, index_code: str, pname: str):
cur_index_members_df = ak.index_stock_cons(index=index_code)
cimd = cur_index_members_df[['品种代码', '纳入日期']]
cimd.columns = ['stock_code', 'in_date']
cimd['out_date'] = 'nan'
index_member_hist_df = ak.index_stock_hist(index=exchange + index_code)
index_members = pd.concat([cimd, index_member_hist_df], axis=0)
index_members = index_members.reset_index(drop=True)
all_data = []
for _, row in index_members.iterrows():
if row['stock_code'][0] == '6':
cur_symbol = row['stock_code'] + '.SH'
else:
cur_symbol = row['stock_code'] + '.SZ'
in_date = pd.to_datetime(row['in_date'])
cur_in_date = int(in_date.strftime('%Y%m%d'))
if row['out_date'] == 'nan':
cur_out_date = 0
else:
out_date = pd.to_datetime(row['out_date'])
cur_out_date = int(out_date.strftime('%Y%m%d'))
all_data.append([cur_symbol, cur_in_date, cur_out_date])
index_members2 = pd.DataFrame(all_data, columns=index_members.columns)
index_members2 = index_members2.drop_duplicates(
['stock_code', 'in_date',
'out_date']).sort_values(['stock_code', 'in_date',
'out_date']).reset_index(drop=True)
index_members2.to_pickle(pname)
def BenchmarkComponentWeightLimit(lower_limit, hard=True, benchmark='000300'):
"""
成分股权重约束，即要求优化结果中，基准成分股的权重之和的下限。基准成分股权重限制。基准为优化时指定的基准。
:param benchmark: 格式参照‘000300’
:param lower_limit: 基准成分股权重之和下界
:param hard: 软约束/硬约束
"""
# start = '2019-01-09'
try:
index_df = ak.index_stock_cons(index=benchmark)
except ValueError:
print('The symbol is invalid.')
exit(1)
else:
lst = index_df['品种代码']
judge = []
for k in range(len(returns.columns)):
if returns.columns[k][:6] in lst:
judge.append(1)
else:
judge.append(0)
def fun(omega):
return omega.dot(judge) - lower_limit
constraints.append({'type': 'eq', 'fun': fun})
constraints_hard.append(hard)
def get_hs300_list1():
index_stock_cons_df = ak.index_stock_cons(index="000300")
print(index_stock_cons_df)
print(index_stock_cons_df.shape[0])
#print(index_stock_cons_df['品种代码'].values.tolist()[0:-1])
hslist = sorted(index_stock_cons_df['品种代码'].values.tolist())
#[print(index) for index in hslist]
hsdict = Counter(hslist)
[print(k, hsdict[k]) for k in hsdict.keys()]
def indexStocksCN(idx):
print(idx)
index_stock_cons_df = ak.index_stock_cons(index=idx[2:])
# print(index_stock_cons_df)
index_stock_cons_df.drop_duplicates(subset='品种代码',
keep='first',
inplace=True)
index_stock_cons_df.set_index('品种代码', inplace=True)
# 今日全场股票概况（价格、市值等）
df = ak.stock_zh_a_spot()
df.set_index('symbol', inplace=True)
# 按总市值排顺序，只保留指数成份股
df = df.loc[df.index.isin(
[dealSymbol(s) for s in index_stock_cons_df.index])].copy()
df.sort_values(by='mktcap', ascending=True, inplace=True)
df = df.iloc[:int(len(df) / 2) - 1]
# 计算因子值
days = 30
sortedDf = pd.DataFrame()
tqdmRange = tqdm(range(len(df)))
tqdmRange = tqdm([-3, -2, -1])
for i in tqdmRange:
symbol = dealSymbol(df.index[i])
tqdmRange.set_description("cauculating factor value for %s" % symbol)
factorVaule_1 = []
factorVaule_2 = []
stockK = ak.stock_zh_index_daily_tx(symbol=symbol)
stockK['symbol'] = symbol
for j in range(0, len(stockK)):
if j < days:
factorVaule_1.append(None)
factorVaule_2.append(None)
continue
factorVaule_1.append(factor_1(stockK.iloc[j - days:j]))
factorVaule_2.append(factor_1(stockK.iloc[j - days:j]))
stockK['factor_1'] = factorVaule_1
stockK['factor_2'] = factorVaule_2
stockK.to_csv('Quotation/' + symbol + '.csv')
stockK = stockK[['symbol', 'factor_1', 'factor_2']].copy()
stockK.reset_index(inplace=True)
sortedDf = sortedDf.append(stockK)
sortedDf.sort_values(by=['date', 'factor_1'], ascending=True, inplace=True)
sortedDf.dropna(subset=['factor_1'], inplace=True)
sortedDf.to_csv(idx + 'factor.csv')
sortedDf['date'] = pd.to_datetime(sortedDf['date']).date
return sortedDf
def get_laststock_set(hs300, datadir):
allset = set()
if os.path.exists(hs300):
input = open(hs300, 'r')
allset = set([stock.rstrip() for stock in input.readlines()])
else:
index_stock_cons_df = ak.index_stock_cons(index="000300") #沪深300
allset = set(index_stock_cons_df['品种代码'].values.tolist()[0::])
print('沪深300个数', len(allset))
existset = set()
if os.path.exists(datadir):
filelist = os.listdir(datadir)
existset = set([stock.split('_')[0] for stock in filelist])
lastset = allset - existset
if len(lastset) > 0:
for stock in lastset:
bget, mises_stock_df, latestmv = calc_stock_finmv_df(stock)
if bget is False: print("get empty DataFrame:%s" % stock)
return allset, lastset
fund_etf_hist_df.iloc[0, 4] = 0 # 第一行的处理为0
fund_etf_hist_df['Additional'] = fund_etf_hist_df['Daily_Increase'].map(
addinput)
fund_etf_hist_df['share'] = (
fund_etf_hist_df['Fixed_Input'] +
fund_etf_hist_df['Additional']) / fund_etf_hist_df['close'].shift(-1)
fund_etf_hist_df.iloc[-1, 6] = 0 # 最后一天份数设为0
fund_etf_hist_df.iloc[-1, 3] = 0 # 最后一天定投金额设为0
return fund_etf_hist_df
index_stock_cons_df = ak.index_stock_cons(index=TARGET_INDEX)
index_stock_cons_df.to_csv(
'/data/jupyter/root/TARGET_INDEX_STOCK_LIST_GBK.csv', encoding="gbk")
index_stock_cons_df.to_csv(
'/data/jupyter/root/TARGET_INDEX_STOCK_LIST_UTF8.csv')
temp1 = ak.stock_financial_abstract(stock=300782).head(5)
temp1['股票编码'] = 300782
temp2 = ak.stock_financial_abstract(stock=300661).head(5)
temp2['股票编码'] = 300661
temp1 = temp1.append(temp2).reindex()
temp1
temp1.append(temp2).to_csv('/data//jupyter/root/temp.csv')
def get_index_cons_list(index: str):
index_stock_cons_df = ak.index_stock_cons(index)
stk_id_list = index_stock_cons_df['品种代码'].tolist()
return stk_id_list
def query_index_content(code='sh000001'):
code = code[2:]
print(code)
index_stock_cons_df = ak.index_stock_cons(index=code)
index_stock_cons_df.rename(columns={'品种代码': 'code'}, inplace=True)
return index_stock_cons_df