def port_mean(self):
'''
组合的收益率期望
'''
series = pd.Series({'port mean': self.port_rate().mean()})
if self.path:
makedir(self.path, 'rate')
series.to_csv(f'{self.path}\\rate\\port_mean.csv')
return self.port_rate().mean()
def cov(self):
'''
各风险资产协方差矩阵
'''
df = self.calculate()['cov']
if self.path:
makedir(self.path, 'rate')
df.to_csv(f'{self.path}\\rate\\cov.csv')
return df
def __init__(self,
names=['比亚迪', '阳光电源', '璞泰来', '紫光国微', '盛新锂能'],
start_date='2021-05-01',
end_date='2021-11-01',
frequency='d',
rfr=0.023467,
funds=10000000,
path='.\\Markovitz cache\\'):
self.names = names
self.lens = len(names)
self.start_date = start_date
self.end_date = end_date
self.frequency = frequency
self.rfr = (rfr*100) / \
{'d': 365, 'w': 52, 'm': 30}[frequency]
self.funds = funds
self.path = path
if self.path:
makedir(self.path, '')
sprint('Initializing...')
if not self.path:
sd = StockData(names=self.names,
start_date=self.start_date,
end_date=self.end_date,
frequency=self.frequency)
self.datas = sd.stocks_data()
else:
try:
self.datas = pd.read_csv(
f'{self.path}\\stock data\\stocks_data.csv')
except:
sd = StockData(names=self.names,
start_date=self.start_date,
end_date=self.end_date,
frequency=self.frequency,
path=self.path)
self.datas = sd.stocks_data()
self.datas.index = self.datas['name']
self.data = self.datas.reset_index(drop=True)
self.date = list(map(lambda x: str(x)[:10], self.data.date.unique()))
self.first_date = self.date[0]
self.last_date = self.date[-1]
# 第一天开盘价
self.first_price = self.data[self.data.date ==
self.data.date.unique()[0]][[
'open', 'name'
]].set_index('name').to_dict()['open']
# 最后一天收盘价
self.last_price = self.data[self.data.date ==
self.data.date.unique()[-1]][[
'close', 'name'
]].set_index('name').to_dict()['close']
# 每只股票最大手数
self.max_shares_dict = {
name: math.floor(self.funds / (shares * 100))
for name, shares in self.last_price.items()
}
def __init__(self, names=['贵州茅台', '隆基股份'],
start_date='2019-12-01', end_date='2020-12-31',
frequency='d',
adjustflag='3',
path='.\\StockData Cache\\'):
self.names = names
self.start_date = start_date
self.end_date = end_date
self.frequency = frequency
self.adjustflag = adjustflag # 默认不复权
self.path = path
if self.path:
makedir(self.path, '')
login()
def boundary_scatter_data(self, number=500):
'''
边界散点数据，默认生成500个
'''
if self.path:
try:
df_scatter = pd.read_csv(
f'{self.path}\\scatter data\\scatter_data.csv',
index=False)
except:
df_scatter = self.scatter_data()
else:
df_scatter = self.scatter_data()
data_dict = self.calculate()
data_mean = data_dict['mean']
data_cov = data_dict['cov']
scatter_list = []
sprint('Searching for boundary scatter...')
for i in trange(number):
random_rate = random.uniform(df_scatter.rate.min(),
df_scatter.rate.max())
constraints = ({
'type': 'eq',
'fun': lambda weights: weights.sum() - 1
}, {
'type':
'eq',
'fun':
lambda weights: data_mean.dot(weights.T)['pctChg'] -
random_rate
})
opts = sco.minimize(
fun=lambda weights: weights.dot(data_cov).dot(weights.T),
x0=np.ones(self.lens) / self.lens,
bounds=tuple((0, 1) for x in range(self.lens)),
constraints=constraints)
scatter_list.append([opts.x, np.sqrt(opts.fun), random_rate])
df_boundary_scatter = pd.DataFrame(scatter_list,
columns=['weights', 'risk', 'rate'])
df_boundary_scatter['sharpe'] = (df_boundary_scatter.rate -
self.rfr) / df_boundary_scatter.risk
df_boundary_scatter = df_boundary_scatter.sort_values(by='sharpe',
ascending=False)
if self.path:
makedir(self.path, 'scatter data')
df_boundary_scatter.to_csv(
f'{self.path}\\scatter data\\boundary_scatter_data.csv')
return df_boundary_scatter
def max_loss(self, level=0.05):
'''
在5%显著性水平下，组合中每种风险资产的最大跌幅
'''
df_pctChg = self.data[['name', 'date', 'pctChg']]
loss_dict = dict(
zip(self.names, [
abs(
np.percentile(df_pctChg[df_pctChg.name == name]['pctChg'],
level * 100)) for name in self.names
]))
loss_series = pd.Series(loss_dict)
if self.path:
makedir(self.path, 'ask')
loss_series.to_csv(
f'{self.path}\\ask\\max_loss(level={level}).csv')
return loss_series
def port_rate(self):
'''
按照各资产权重计算的组合收益率序列 --> 返回一个Series
'''
df_pctChg = self.data[['name', 'date', 'pctChg']]
df_pctChg['weights'] = df_pctChg.name.map(self.weights_dict)
df_pctChg[
'weighted_pctChg'] = df_pctChg['weights'] * df_pctChg['pctChg']
df = pd.DataFrame()
for name in self.names:
df[name] = list(
df_pctChg[df_pctChg.name == name]['weighted_pctChg'])
df.index = self.date
if self.path:
makedir(self.path, 'rate')
df.sum(axis=1).to_csv(f'{self.path}\\rate\\port_rate_series.csv')
return df.sum(axis=1)
def calculate(self):
'''
计算收益率均值、协方差矩阵、相关系数矩阵
'''
data = self.data[['date', 'name', 'pctChg']]
# 收益率均值
data_mean = data.groupby('name').mean().T[self.names]
# 协方差矩阵 & 相关系数矩阵
df = pd.DataFrame()
for name in self.names:
df[name] = list(data[data['name'] == name]['pctChg'])
data_cov = df.cov()
data_corr = df.corr()
if self.path:
makedir(self.path, 'mean,cov,corr')
data_mean.T.to_csv(f'{self.path}\\mean,cov,corr\\data_mean.csv')
data_cov.to_csv(f'{self.path}\\mean,cov,corr\\data_cov.csv')
data_corr.to_csv(f'{self.path}\\mean,cov,corr\\data_corr.csv')
return {'mean': data_mean, 'cov': data_cov, 'correlation': data_corr}
def __init__(self,
names=['比亚迪', '阳光电源', '璞泰来', '紫光国微', '盛新锂能'],
start_date='2021-05-01',
end_date='2021-11-01',
frequency='w',
rfr=0.023467,
market_index='沪深300指数',
path='.\\CAPM cache\\'):
self.names = names
self.lens = len(names)
self.start_date = start_date
self.end_date = end_date
self.frequency = frequency
self.rfr = (rfr*100) / \
{'d': 365, 'w': 52, 'm': 30}[frequency]
self.market_index = market_index
self.path = path
if self.path:
makedir(self.path, '')
sprint('Initializing...')
if not self.path:
sd = StockData(names=self.names + [market_index],
start_date=self.start_date,
end_date=self.end_date,
frequency=self.frequency)
self.datas = sd.stocks_data()
else:
try:
self.datas = pd.read_csv(
f'{self.path}\\stock data\\stocks_data.csv')
except:
sd = StockData(names=self.names + [market_index],
start_date=self.start_date,
end_date=self.end_date,
frequency=self.frequency,
path=self.path)
self.datas = sd.stocks_data()
self.datas.index = self.datas['name']
self.data = self.datas.loc[self.names].reset_index(drop=True)
self.Rm_data = self.datas.loc[self.market_index].reset_index(drop=True)
def init_scatter_data(self):
'''
初始临近整数组合散点
'''
# 初始临近整数组合权重
df_init_shares = self.init_port()
for name in self.names:
df_init_shares[name] = df_init_shares[name] * self.last_price[name]
df_init_shares['sum'] = df_init_shares.sum(axis=1)
for name in self.names:
df_init_shares[name] = df_init_shares[name] / df_init_shares['sum']
df_init_shares = df_init_shares[df_init_shares['sum'] <= self.funds /
100]
weights = np.array([
list(i.values())
for i in list(df_init_shares[self.names].T.to_dict().values())
])
# 收益率、风险和夏普比率
data_dict = self.calculate()
data_mean = data_dict['mean']
data_cov = data_dict['cov']
# 散点DataFrame
df_init_scatter = pd.DataFrame()
# 随机权重
df_init_scatter['weights'] = pd.Series(map(lambda x: str(x), weights))
# 风险
df_init_scatter['risk'] = np.sqrt(
np.diagonal(weights.dot(data_cov).dot(weights.T)))
# 收益率
df_init_scatter['rate'] = data_mean.dot(weights.T).T['pctChg']
# 夏普比率
df_init_scatter['sharpe'] = (df_init_scatter.rate -
self.rfr) / df_init_scatter.risk
df_init_scatter = df_init_scatter.sort_values(by='sharpe',
ascending=False)
if self.path:
makedir(self.path, 'scatter data')
df_init_scatter.to_csv(
f'{self.path}\\scatter data\\df_init_scatter.csv')
return df_init_scatter
def stocks_info(self):
'''
Return a dict containing stock names, codes and ipoDate
{
'贵州茅台': {'code': 'sh.600519', 'ipoDate': '2001-08-27'},
'隆基股份': {'code': 'sh.601012', 'ipoDate': '2012-04-11'},
...
}
'''
info = {}
sprint('Loading stocks information...')
for name in tqdm(self.names):
rs = bs.query_stock_basic(code_name=name)
stock_info = get_data(rs)
info[name] = {'code': stock_info['code'][0],
'ipoDate': stock_info['ipoDate'][0]}
if self.path:
makedir(self.path, 'stock data')
df_info = pd.DataFrame(info).T
df_info['name'] = df_info.index
df_info.to_csv(
f'{self.path}\\stock data\\stocks_info.csv', index=False)
return info
def scl(self, name='', show=True):
'''
给定资产的证券特征线
'''
if name not in self.names:
sprint(f'name参数值未给定，或参数值{name}不在给定风险资产范围内！已重新随机选择一种给定风险资产！',
color='red')
name = random.choice(self.names)
Ri = self.data[self.data.name == name]['pctChg']
Rm = self.Rm_data['pctChg']
ls_dict = self.ls_beta(Ri)
plt.cla()
plt.axline(xy1=(0, ls_dict['alpha_ols']),
slope=ls_dict['beta_ols'],
c='m')
plt.scatter(Ri, Rm, s=10, marker=".", c='b')
plt.xlabel(f'{name}收益率（%）')
plt.ylabel(f'{self.market_index}收益率（%）')
if show:
plt.show()
else:
makedir(self.path, 'scl')
plt.savefig(f'{self.path}\\scl\\{name}.svg', format='svg')
def drawdown(self, show=True):
'''
组合和各风险资产的最大回撤
'''
df_rate = pd.DataFrame()
df_rate['port'] = self.port_rate()
df_rate[self.market_index] = list(self.Rm_data['pctChg'])
data = self.data[['name', 'date', 'pctChg']]
for name in self.names:
df_rate[name] = list(data[data.name == name]['pctChg'])
del data
# 构建财富指数
wealth = (1 + df_rate / 100).cumprod()
# 找出上一个最高点
previous_max = wealth.cummax()
# 回撤率
draw_down = (wealth - previous_max) / previous_max
# 折线图
if show:
wealth.plot()
previous_max.plot()
draw_down.plot()
plt.show()
else:
makedir(self.path, 'drawdown')
wealth.plot()
plt.savefig(f'{self.path}\\drawdown\\wealth.svg', format='svg')
previous_max.plot()
plt.savefig(f'{self.path}\\drawdown\\previous_max.svg',
format='svg')
draw_down.plot()
plt.savefig(f'{self.path}\\drawdown\\draw_down.svg', format='svg')
if self.path:
makedir(self.path, 'drawdown')
draw_down.min().to_csv(f'{self.path}\\drawdown\\max drawdown.csv')
return draw_down.min()
def scatter_data(self, number=5000):
'''
散点数据，默认生成5000个
'''
data_dict = self.calculate()
data_mean = data_dict['mean']
data_cov = data_dict['cov']
weights = self.weights(number=number)
# 散点DataFrame
df_scatter = pd.DataFrame()
# 随机权重
df_scatter['weights'] = pd.Series(map(lambda x: str(x), weights))
# 风险
df_scatter['risk'] = np.sqrt(
np.diagonal(weights.dot(data_cov).dot(weights.T)))
# 收益率
df_scatter['rate'] = data_mean.dot(weights.T).T['pctChg']
# 夏普比率
df_scatter['sharpe'] = (df_scatter.rate - self.rfr) / df_scatter.risk
df_scatter = df_scatter.sort_values(by='sharpe', ascending=False)
if self.path:
makedir(self.path, 'scatter data')
df_scatter.to_csv(f'{self.path}\\scatter data\\scatter_data.csv')
return df_scatter
def kline(self):
data = self.calculate().to_dict('list')
kline = (
Kline().add_xaxis(xaxis_data=data["date"]).add_yaxis(
series_name="portfolio index",
y_axis=data["datas"],
itemstyle_opts=opts.ItemStyleOpts(
color="#ef232a",
color0="#14b143",
border_color="#ef232a",
border_color0="#14b143",
),
).set_global_opts(
xaxis_opts=opts.AxisOpts(
type_="category",
is_scale=True,
boundary_gap=False,
axisline_opts=opts.AxisLineOpts(is_on_zero=False),
splitline_opts=opts.SplitLineOpts(is_show=False),
split_number=20,
min_="dataMin",
max_="dataMax",
),
yaxis_opts=opts.AxisOpts(
is_scale=True,
splitline_opts=opts.SplitLineOpts(is_show=True)),
datazoom_opts=[
opts.DataZoomOpts(is_show=False,
type_="inside",
xaxis_index=[0, 0],
range_end=100),
opts.DataZoomOpts(is_show=True,
xaxis_index=[0, 1],
pos_top="97%",
range_end=100),
opts.DataZoomOpts(is_show=False,
xaxis_index=[0, 2],
range_end=100),
],
tooltip_opts=opts.TooltipOpts(
trigger="axis",
axis_pointer_type="cross",
background_color="rgba(245, 245, 245, 0.8)",
border_width=1,
border_color="#ccc",
textstyle_opts=opts.TextStyleOpts(color="#000"),
),
brush_opts=opts.BrushOpts(
x_axis_index="all",
brush_link="all",
out_of_brush={"colorAlpha": 0.1},
brush_type="lineX",
),
# 三个图的 axis 连在一块
axispointer_opts=opts.AxisPointerOpts(
is_show=True,
link=[{
"xAxisIndex": "all"
}],
label=opts.LabelOpts(background_color="#777"),
),
))
kline_line = (Line().add_xaxis(xaxis_data=data["date"]).add_yaxis(
series_name="MA5",
y_axis=self.calculate_ma(day_count=5, data=data),
is_smooth=True,
linestyle_opts=opts.LineStyleOpts(opacity=0.5),
label_opts=opts.LabelOpts(is_show=False),
).add_yaxis(
series_name="MA10",
y_axis=self.calculate_ma(day_count=10, data=data),
is_smooth=True,
linestyle_opts=opts.LineStyleOpts(opacity=0.5),
label_opts=opts.LabelOpts(is_show=False),
).add_yaxis(
series_name="MA20",
y_axis=self.calculate_ma(day_count=20, data=data),
is_smooth=True,
linestyle_opts=opts.LineStyleOpts(opacity=0.5),
label_opts=opts.LabelOpts(is_show=False),
).add_yaxis(
series_name="MA30",
y_axis=self.calculate_ma(day_count=30, data=data),
is_smooth=True,
linestyle_opts=opts.LineStyleOpts(opacity=0.5),
label_opts=opts.LabelOpts(is_show=False),
).set_global_opts(
xaxis_opts=opts.AxisOpts(
type_="category",
grid_index=1,
axislabel_opts=opts.LabelOpts(is_show=False),
),
yaxis_opts=opts.AxisOpts(
grid_index=1,
split_number=3,
axisline_opts=opts.AxisLineOpts(is_on_zero=False),
axistick_opts=opts.AxisTickOpts(is_show=False),
splitline_opts=opts.SplitLineOpts(is_show=False),
axislabel_opts=opts.LabelOpts(is_show=True),
),
))
# Overlap Kline + Line
overlap_kline_line = kline.overlap(kline_line)
# Bar-1
bar_1 = (Bar().add_xaxis(xaxis_data=data["date"]).add_yaxis(
series_name="Volumn",
y_axis=data["volume"],
xaxis_index=1,
yaxis_index=1,
label_opts=opts.LabelOpts(is_show=False),
itemstyle_opts=opts.ItemStyleOpts(color=JsCode("""
function(params) {
var colorList;
if (barData[params.dataIndex][1] > barData[params.dataIndex][0]) {
colorList = '#ef232a';
} else {
colorList = '#14b143';
}
return colorList;
}
""")),
).set_global_opts(
xaxis_opts=opts.AxisOpts(
type_="category",
grid_index=1,
axislabel_opts=opts.LabelOpts(is_show=False),
),
legend_opts=opts.LegendOpts(is_show=False),
))
# Bar-2 (Overlap Bar + Line)
bar_2 = (Bar().add_xaxis(xaxis_data=data["date"]).add_yaxis(
series_name="MACD",
y_axis=data["MACD"],
xaxis_index=2,
yaxis_index=2,
label_opts=opts.LabelOpts(is_show=False),
itemstyle_opts=opts.ItemStyleOpts(color=JsCode("""
function(params) {
var colorList;
if (params.data >= 0) {
colorList = '#ef232a';
} else {
colorList = '#14b143';
}
return colorList;
}
""")),
).set_global_opts(
xaxis_opts=opts.AxisOpts(
type_="category",
grid_index=2,
axislabel_opts=opts.LabelOpts(is_show=False),
),
yaxis_opts=opts.AxisOpts(
grid_index=2,
split_number=4,
axisline_opts=opts.AxisLineOpts(is_on_zero=False),
axistick_opts=opts.AxisTickOpts(is_show=False),
splitline_opts=opts.SplitLineOpts(is_show=False),
axislabel_opts=opts.LabelOpts(is_show=True),
),
legend_opts=opts.LegendOpts(is_show=False),
))
line_2 = (Line().add_xaxis(xaxis_data=data["date"]).add_yaxis(
series_name="DIFF",
y_axis=data["DIFF"],
xaxis_index=2,
yaxis_index=2,
label_opts=opts.LabelOpts(is_show=False),
).add_yaxis(
series_name="DEA",
y_axis=data["DEA"],
xaxis_index=2,
yaxis_index=2,
label_opts=opts.LabelOpts(is_show=False),
).set_global_opts(legend_opts=opts.LegendOpts(is_show=False)))
# 最下面的柱状图和折线图
overlap_bar_line = bar_2.overlap(line_2)
# 最后的 Grid
grid_chart = Grid(
init_opts=opts.InitOpts(width="1500px", height="750px"))
# 这个是为了把 data.datas 这个数据写入到 html 中,还没想到怎么跨 series 传值
# demo 中的代码也是用全局变量传的
grid_chart.add_js_funcs("var barData = {}".format(data["datas"]))
# K线图和 MA5 的折线图
grid_chart.add(
overlap_kline_line,
grid_opts=opts.GridOpts(pos_left="3%",
pos_right="1%",
height="60%"),
)
# Volumn 柱状图
grid_chart.add(
bar_1,
grid_opts=opts.GridOpts(pos_left="3%",
pos_right="1%",
pos_top="71%",
height="10%"),
)
# MACD DIFS DEAS
grid_chart.add(
overlap_bar_line,
grid_opts=opts.GridOpts(pos_left="3%",
pos_right="1%",
pos_top="82%",
height="14%"),
)
makedir(self.path, 'kline')
grid_chart.render(
f"{self.path}\\kline\\{str(self.names)}_{time.strftime('%Y-%m-%d', time.localtime())}.html"
)
