def get_daily_data(self, code, expire=60 * 6):
"""
获取一支股票所有历史数据保存到本地
"""
UT.check_dir(CT.DAILY_DIR)
file_path = CT.DAILY_DIR + code
expired = UT.check_file_expired(file_path, expire)
if expired or not os.path.exists(file_path):
symbol = self._code_to_symbol(code)
start_date = CT.START
end_date = date_time.get_today_str()
adjust = 'qfq'
if is_index(code):
d = ak.stock_zh_index_daily(symbol)
else:
d = ak.stock_zh_a_daily(symbol, start_date, end_date, adjust)
if d is None:
return d
d.to_csv(file_path, sep='\t')
if not os.path.exists(file_path):
return None
#d = pd.read_csv(file_path, sep='\t', index_col=0)
d = pd.read_csv(file_path,
sep='\t',
skiprows=0,
parse_dates=True,
header=0,
index_col=0)
return d
def perchase_plan(self):
for i in range(len(self.stock_list)):
stock = self.stock_list[i]
df = ak.stock_zh_index_daily(symbol=stock)
money = self.PortWts[i] * self.assets_amount
amount = math.floor(money / (df['close'][len(df) - 1] * 100)) * 100
if amount > 0:
print('股票%s(%s)购买%s股' % (stock, code_to_name(stock), amount))
def save_index(code: str, mongo=None):
if not mongo:
mongo = Mongo()
if code == 'sh000985':
df = AkData.index_price_daily(code, 'em')
else:
df = ak.stock_zh_index_daily(code)
if mongo.has_collection(code):
mongo.drop(code)
mongo.save(code, df)
def get_daily_data(self, start_date, end_date):
df = ak.stock_zh_index_daily(symbol="sh510050")
df1 = df.loc[start_date:end_date]
print('')
print(df1)
#dates = df['date']
open1 = df1['open'][start_date]
print('open1: {0};'.format(open1))
print('df1[2020-06-01]: {0};'.format(df1.loc[start_date]))
'''
def index_price_daily(code: str, source: str = None) -> dict:
if source == 'tx':
df = ak.stock_zh_index_daily_tx(symbol=code)
elif source == 'em':
df = ak.stock_zh_index_daily_em(symbol=code)
else:
df = ak.stock_zh_index_daily(symbol=code)
df['date'] = pd.to_datetime(df['date'])
df = df.rename({'date': '_id'}, axis=1)
print(df)
return json.loads(df.T.to_json()) # use default date_format='epoch' instead of 'iso'
def index_price_daily(code: str, source: str = None) -> pd.DataFrame:
if source == 'tx':
df = ak.stock_zh_index_daily_tx(symbol=code)
elif source == 'em':
df = ak.stock_zh_index_daily_em(symbol=code)
else:
df = ak.stock_zh_index_daily(symbol=code)
df['date'] = pd.to_datetime(df['date'])
df = df.rename({'date': '_id'}, axis=1)
print(df)
return df
def download(self):
for type in ['trade','favourite']:
tickers = pd.read_csv(self.BASIC + type +'.csv', encoding='gb18030')['tag'].values.tolist()
alltickers = tickers.copy()
removed_tickers = []
# tickers = list(set(tickers).difference(set([i[:-4] for i in os.listdir(self.AKSHARE + type + '/') ])))
for ticker in tickers:
if ticker[:2]=='E_':
try:
data = ak.fund_etf_hist_sina(symbol=ticker[2:])
data = data.drop_duplicates()
data.to_csv(self.AKSHARE + type + '/' + ticker + '.csv', encoding='gb18030', index=False)
except :
print('Can not download ETF:',ticker)
removed_tickers.append(ticker)
elif ticker[:2]=='S_':
try:
data = ak.stock_zh_a_daily(symbol=ticker[2:], adjust="qfq")
data.drop(['outstanding_share','turnover'],axis=1,inplace=True)
data = data.drop_duplicates()
data.to_csv(self.AKSHARE + type + '/' + ticker + '.csv', encoding='gb18030', index=True)
except :
print('Can not download stock:',ticker)
removed_tickers.append(ticker)
elif ticker[:2]=='I_':
try:
data = ak.stock_zh_index_daily(symbol=ticker[2:])
data = data.drop_duplicates()
data.to_csv(self.AKSHARE + type + '/' + ticker + '.csv', encoding='gb18030', index=True)
except :
print('Can not download index:',ticker)
removed_tickers.append(ticker)
for ticker in removed_tickers: # Remove empty record
try:
os.remove(raw_path + ticker + '.csv')
except:
pass
if type == 'favourite':
data = pd.DataFrame(list(set(alltickers).difference(set(removed_tickers))),columns =['tag'])
data.sort_values(by=['tag'],ascending=[True],inplace=True)
data.to_csv(self.BASIC + 'favourite.csv', encoding='gb18030',index=False)
elif type == 'archive':
data = pd.DataFrame(list(set(alltickers).difference(set(removed_tickers))),columns =['tag'])
data.sort_values(by=['tag'],ascending=[True],inplace=True)
data.to_csv(self.BASIC + 'archive.csv', encoding='gb18030',index=False)
return
def download_data(target_stocks):
for target_stock in target_stocks:
print(target_stock)
if target_stock in ex_list:
print('Skip: ' + target_stock)
continue
if os.path.exists('daily_summary/' + target_stock + '.csv'):
os.remove('daily_summary/' + target_stock + '.csv')
else:
print('file not exists: ' + target_stock + '.csv')
stock_zh_ah_daily_df = ak.stock_zh_index_daily(
symbol=str(target_stock))
# print(stock_zh_ah_daily_df)
stock_zh_ah_daily_df.to_csv('daily_summary/' + target_stock + '.csv')
time.sleep(6)
def TrackingErrorLimit(upper_limit, benchmark='sz399552', hard=True):
"""
追踪误差约束。基准为优化时指定的基准。
:param upper_limit: 追踪误差上界
:param benchmark: 基准（代码格式参照‘sz399552’）
:param hard: 软约束/硬约束
"""
start_d, end_d = returns.index[0], returns.index[-1]
# start = '2019-01-09'
try:
index_df = ak.stock_zh_index_daily(symbol=benchmark)['close']
except ValueError:
print('The symbol is invalid.')
exit(1)
else:
try:
start = np.where(index_df.index == datetime.datetime.strptime(
start_d, '%Y-%m-%d'))[0][0]
end = np.where(index_df.index == datetime.datetime.strptime(
end_d, '%Y-%m-%d'))[0][0]
if end < len(index_df):
bm = index_df[start:end + 1]
else:
bm = index_df[start:]
except ValueError:
print(
'The benchmark you choose is invalid with akshare or does not have enough supported data.'
)
def cumulative(lst, t):
prod = 1
for k in range(t):
prod *= lst[t]
return prod
def fun(omega):
TD = []
for i in range(len(returns.columns)):
TD.append(
cumulative(returns.dot(omega), i) - cumulative(bm, i))
exp = np.mean(TD)
TE = np.sqrt(np.sum((TD - exp)**2) / (len(TD) - 1))
return upper_limit - TE
constraints.append({'type': 'eq', 'fun': fun})
constraints_hard.append(hard)
def get_stock_index():
# 沪深300
csi300 = ak.stock_zh_index_daily(symbol="sh000300")
csi300.columns = columns_name
csi300.loc[:, 'gain'] = (csi300['close'] - csi300['open'])/csi300['open']*100
print(csi300.shape)
csi300.to_csv(store_path+r".\csi300.csv", index=False, sep=',')
# 美国 us500
us500 = ak.index_investing_global_from_url(
url="https://www.investing.com/indices/us-spx-500", period="每日", start_date="20060101",
end_date="20211224")
us500.columns = columns_name
us500.loc[:, 'gain'] = (us500['close'] - us500['open']) / us500['open'] * 100
print(us500.shape)
us500.to_csv(store_path+r".\us500.csv", index=False, sep=',')
# 日本 jp225
jp225 = ak.index_investing_global_from_url(
url="https://www.investing.com/indices/japan-ni225", period="每日", start_date="20060101",
end_date="20211224")
jp225.columns = columns_name
jp225.loc[:, 'gain'] = (jp225['close'] - jp225['open']) / jp225['open'] * 100
print(jp225.shape)
jp225.to_csv(store_path+r".\jp225.csv", index=False, sep=',')
# 英国 uk100
uk100 = ak.index_investing_global_from_url(
url="https://www.investing.com/indices/uk-100", period="每日", start_date="20060101",
end_date="20211224")
uk100.columns = columns_name
uk100.loc[:, 'gain'] = (uk100['close'] - uk100['open']) / uk100['open'] * 100
print(uk100.shape)
uk100.to_csv(store_path+r".\uk100.csv", index=False, sep=',')
# 德国 DAX30
dax30 = ak.index_investing_global_from_url(
url="https://www.investing.com/indices/germany-30", period="每日", start_date="20060101",
end_date="20211224")
dax30.columns = columns_name
dax30.loc[:, 'gain'] = (dax30['close'] - dax30['open']) / dax30['open'] * 100
print(dax30.shape)
dax30.to_csv(store_path+r".\dax30.csv", index=False, sep=',')
# 法国 CAC40
cac40 = ak.index_investing_global_from_url(
url="https://www.investing.com/indices/france-40", period="每日", start_date="20060101",
end_date="20211224")
cac40.columns = columns_name
cac40.loc[:, 'gain'] = (cac40['close'] - cac40['open']) / cac40['open'] * 100
cac40.to_csv(store_path+r".\cac40.csv", index=False, sep=',')
def extract_index_records(code='sh000016', start=None, end=None):
#code should start with 'sh' or 'sz'
result = ak.stock_zh_index_daily(symbol=code)
result.index = result.index.tz_localize(None)
result['date'] = result.index
result = result[['date','open','close','high','low','volume']]
result['total'] = 'NaN'
result['amp'] = 'NaN'
result.columns = ['date','open_price','close_price','high_price','low_price','trancaction','total','amp']
result['rate'] = pd.Series([0]).append(pd.Series((result['close_price'].iloc[1:].values-result['close_price'].iloc[0:-1].values)/result['close_price'].iloc[0:-1].values)).values*100
if start==None and end==None:
data_in_target = result
else:
data_in_target = result[(result['date']<=pd.Timestamp(end)) & (result['date']>=pd.Timestamp(start))]
data_in_target['date'] = data_in_target['date'].apply(lambda x: (x.date()-datetime.date(1, 1, 1)).days)
data_in_target.index = data_in_target.index.rename('')
data_in_target = data_in_target.reset_index()
return data_in_target[['date','open_price','close_price','low_price','high_price','trancaction','total','rate','amp']]
ag[short] += df.loc[20,short]
ag[long_chg] += df.loc[20,long_chg]
ag[short_chg] += df.loc[20,short_chg]
stat = (ag[long]+ag[short])/ag[vol]
ts = (ag[long_chg]-ag[short_chg])/np.abs(ag[long_chg]+ag[short_chg])
# how to use TS?
print(ag)
print(stat,ts)
return ag
if __name__ == "__main__":
rank = spider(['AG'])
print("------------------------------------------------")
aurank = time.time_ns()
raw_index_df = ak.stock_zh_index_daily(symbol="sz399300")
sma1 = range(20,61,4)
sma2 = range(180,281,10)
results = pd.DataFrame()
for SMA1, SMA2 in product(sma1, sma2):
data: DataFrame = pd.DataFrame(raw_index_df['close'])
data.dropna(inplace=True)
data['returns'] = np.log(data['close'] / data['close'].shift(1))
data['sma1'] = data['close'].rolling(SMA1).mean()
data['sma2'] = data['close'].rolling(SMA2).mean()
data.dropna(inplace=True)
data['position'] = np.where(data['sma1'] > data['sma2'], 1, 0)
data['strategy'] = data['position'].shift(1) * data['returns']
data.dropna(inplace=True)
perf = np.exp(data[['returns', 'strategy']].sum())
results = results.append(
import matplotlib.dates as mdates
df['日期'] = df['日期'].map(mdates.date2num)
# 初始化fig, axes
fig, ax = plt.subplots(figsize=(25, 8))
ax.plot(df['日期'], df['收盘'], label='十年期国债收益率')
ax.xaxis_date()
ax.xaxis.set_major_locator(years)
ax.xaxis.set_minor_locator(months)
ax.xaxis.set_major_formatter(years_fmt)
ax.set_ylabel(ylabel='到期收益率', fontproperties=fontprop)
ax.grid(True)
# 沪深300数据
stock_df = ak.stock_zh_index_daily(symbol="sh000300")
stock_df.reset_index(inplace=True)
stock_df['date'] = stock_df['date'].map(mdates.date2num)
# 初始化fig, axes
ax2 = ax.twinx()
ax2.plot(stock_df['date'],
stock_df['close'],
color='red',
alpha=0.8,
label='沪深300')
ax2.set_ylabel(ylabel='沪深300', fontproperties=fontprop)
from datetime import datetime
updated_at = datetime.now().strftime('%Y-%m-%d')
fig.suptitle('中国十年期国债收益率 v.s. 沪深300\n公众号：结丹记事本儿,更新于{}'.format(updated_at),
fontproperties=fontprop,
def index_a_daily(code, *args, **kwargs):
'''return stock a index daily data for given code symbol to latest datetime
'''
code = _convert_code(ak.stock_zh_index_daily)(code)
return ak.stock_zh_index_daily(code, *args, **kwargs)
def beat_benchmark_ratio(fCode, cPeriod=0, sDate='', eDate=''):
# 排除非法参数： 1) cPeriod与(sDate或eDate)同时出现 2) 有sDate无eDate 3) 有eDate无sDate
if (cPeriod and
(sDate or eDate)) or (sDate and not eDate) or (eDate and not sDate):
raise ValueError("Illegal Argument")
# 用akshare获取：开放式基金-历史数据
fInfo = ak.fund_em_open_fund_info(fund=fCode, indicator="单位净值走势")
# 舍弃无用的数据包
fInfo = fInfo[["净值日期", "单位净值"]]
# 计算收益率为多少
rate = [(fInfo["单位净值"][i] - fInfo["单位净值"][i - 1]) / (fInfo["单位净值"][i - 1])
for i in range(1, len(fInfo))]
fInfo = fInfo[1:]
fInfo["rate"] = rate
# 用cPeriod参数：选出历史数据区间
if cPeriod:
fInfo = fInfo[-cPeriod:].reset_index(drop=True)
# 用sDate和eDate参数：选出历史数据区间
elif sDate and eDate:
f_sDate, f_eDate = datetime.strptime(
sDate, "%Y-%m-%d").date(), datetime.strptime(eDate,
"%Y-%m-%d").date()
fInfo = fInfo.loc[(fInfo["净值日期"] >= f_sDate)
& (fInfo["净值日期"] <= f_eDate)].reset_index(drop=True)
# 舍弃无用的数据包
fInfo = fInfo["rate"]
# 用akshare获取：沪深300-历史数据
benchmark = ak.stock_zh_index_daily(symbol="sh000300")
# 把date转化为column而不是作为index，方便后面的历史数据区间的选中
benchmark = benchmark.reset_index().rename({'index': 'date'},
axis='columns')
benchmark["date"] = benchmark["date"].apply(
lambda x: x.to_pydatetime().date())
# 舍弃无用的数据包
benchmark = benchmark[["date", "close"]]
# 计算收益率为多少
rate = [(benchmark["close"][i] - benchmark["close"][i - 1]) /
(benchmark["close"][i - 1]) for i in range(1, len(benchmark))]
benchmark = benchmark[1:]
benchmark["rate"] = rate
# 用cPeriod参数：选出历史数据区间
if cPeriod:
benchmark = benchmark[-cPeriod:].reset_index(drop=True)
# 用sDate和eDate参数：选出历史数据区间
elif sDate and eDate:
b_sDate, b_eDate = datetime.strptime(
sDate, "%Y-%m-%d").date(), datetime.strptime(eDate,
"%Y-%m-%d").date()
benchmark = benchmark.loc[(benchmark["date"] >= b_sDate) & (
benchmark["date"] <= b_eDate)].reset_index(drop=True)
# 舍弃无用的数据包
benchmark = benchmark["rate"]
# 计算区间内收益率击败沪深300的比例
benchmark = [
1 if fInfo[i] > benchmark[i] else 0 for i in range(len(fInfo))
]
benchmark_ratio = Counter(benchmark)[1] / len(benchmark)
return "{:.2%}".format(benchmark_ratio)
}
fieldDict_stock = {
'开盘价': 'open',
'收盘价': 'close',
'最高价': 'high',
'最低价': 'low',
'成交量': 'volume',
'换手率': 'turnover'
}
codes = allList[0].split(',')
for code in codes:
if code[:3] == 'zh_':
index_code = code.split('_')[1]
try:
df_temp = ak.stock_zh_index_daily(symbol=index_code).reset_index()
df_target = pd.DataFrame()
df_target['date'] = df_temp['date'].apply(
lambda x: x.strftime('%Y-%m-%d'))
for text in allList[1:]:
if text in fieldDict_index:
col_name = fieldDict_index[text]
df_target[text] = df_temp[col_name]
df_indexes[index_code] = df_target
except:
continue
else:
stock_code = ('sh' if code[0] == '6' else 'sz') + code
try:
if '后复权' in allList[1:]:
df_temp = ak.stock_zh_a_daily(symbol=stock_code,
def get_daily_data(self, start_date, end_date):
df = ak.stock_zh_index_daily(symbol="sh510050")
return df.loc[start_date:end_date]
df = macro_china_gksccz_df[::-1][
macro_china_gksccz_df['operation_from_date'] > last_date]
es_bulk(df, gen_macro_china_gksccz_doc)
# 获取Shibor隔夜利率数据
last_date = getLastRecordDateInEs_pyfy_rate_interbank(es)
page = '100' if last_date == '1970-01-01' else '5'
rate_interbank = ak.rate_interbank(market="上海银行同业拆借市场",
symbol="Shibor人民币",
indicator="隔夜",
need_page=page)
df = rate_interbank[rate_interbank['日期'] > last_date]
es_bulk(df, gen_rate_interbank_doc)
# 获取上证指数
df = ak.stock_zh_index_daily(symbol="sh000001")
last_date = getLastRecordDateInEs(es, "pyfy_stock_zh_index_daily")
es_bulk(df[df.index > last_date], gen_stock_zh_index_daily_doc)
# 美国10年期国债
last_date = getLastRecordDateInEs(es, "pyfy_bond_investing_global_us_10")
df = ak.bond_investing_global(country="美国",
index_name="美国10年期国债",
period="每日",
start_date=last_date,
end_date=time.strftime('%Y-%m-%d',
time.localtime()))
es_bulk(df[df.index > last_date], gen_bond_investing_global_us_10_doc)
# bitcoin
last_date = getLastRecordDateInEs(es, "pyfy_crypto_hist_bitcoin")
#!/usr/bin/python
# -*- coding: UTF-8 -*-
"""
@author:Administrator
@file:20201209.py
@time:2020/12/09
"""
# 示例
import pandas as pd
import akshare as ak
# 列名与数据对其显示
pd.set_option('display.unicode.ambiguous_as_wide', True)
pd.set_option('display.unicode.east_asian_width', True)
# 显示所有列
pd.set_option('display.max_columns', None)
# 显示所有行
pd.set_option('display.max_rows', None)
stock_zh_index_daily_df = ak.stock_zh_index_daily(symbol="sz399552")
with open('stock_zh.txt', 'w') as f:
f.write(str(stock_zh_index_daily_df))