def form_table(self):
# 將共整合係數標準化，此權重為資金權重，因此必須依股價高低轉為張數權重。
for i in range(len(self.name)):
total = abs(self.weight.w1[i]) + abs(self.weight.w2[i])
self.weight.w2[i] = (self.weight.w2[i] / total)
self.weight.w1[i] = (self.weight.w1[i] / total)
table = pd.concat([self.name, self.select_model, self.weight], axis=1)
#print("共整合係數標準化 done in " + str(end - start))
#------------------------------------------------------------------------------
#計算spread序列，做單根檢定，並刪除非定態spread序列
spread = np.zeros((len(self.data), len(table)))
for i in range(len(table)):
spread[:, i] = table.w1[i] * self.data[
table.stock1[i]] + table.w2[i] * self.data[table.stock2[i]]
self.spread = pd.DataFrame(spread)
#print("刪除非定態spread序列 done in " + str(end - start))
#------------------------------------------------------------------------------
# 計算信噪比 ( spread )------------------------------
for i in range(len(self.spread.T)):
y = self.spread.iloc[:, i]
self.s_n_r.append(snr(y, 100))
self.s_n_r = pd.DataFrame(self.s_n_r)
self.s_n_r.columns = ["snr"]
#print("計算信噪比 done in " + str(end - start))
#------------------------------------------------------------------------------
# 計算過零率 ( spread )------------------------------
#pool = Pool(processes=16)
Boot = 500
for j in range(len(self.spread.T)):
y = self.spread.iloc[:, j]
#t = pool.apply_async(zcr, (y,Boot,con.stock1[j],con.stock2[j],),callback=self.append_zcr_result)
self.z_c_r.append(zcr(y, Boot))
#pool.close()
#pool.join()
#self.stock1_name = pd.DataFrame(self.stock1_name) ; self.stock1_name.columns = ["stock1"]
#self.stock2_name = pd.DataFrame(self.stock2_name) ; self.stock2_name.columns = ["stock2"]
self.z_c_r = pd.DataFrame(self.z_c_r)
self.z_c_r.columns = ["zcr"]
#mix = pd.concat([self.stock1_name,self.stock2_name,self.z_c_r],axis=1)
#print("計算過零率 done in " + str(end - start))
#------------------------------------------------------------------------------
# 開倉門檻and平倉門檻and偏度--------------------------------------
for i in range(len(self.spread.T)):
y = self.spread.iloc[:, i]
# 有時間趨勢項的模型必須分開計算
if table.model_type[i] == 'model4':
x = np.arange(0, len(y))
b1, b0 = np.polyfit(x, y, 1)
trend_line = x * b1 + b0
y = y - trend_line
self.ave.append(np.mean(y))
self.std.append(np.std(y))
self.ske.append(skew(y))
self.ave = pd.DataFrame(self.ave)
self.ave.columns = ["mu"]
self.std = pd.DataFrame(self.std)
self.std.columns = ["stdev"]
self.ske = pd.DataFrame(self.ske)
self.ske.columns = ["skewness"]
#print("開倉門檻and平倉門檻 done in " + str(end - start))
#------------------------------------------------------------------------------
# 整理表格
#start = datetime.now()
#con = pd.concat([con,self.s_n_r],axis=1)
#con = pd.merge( con , mix , on=["stock1","stock2"] , how="outer" )
table = pd.concat(
[table, self.s_n_r, self.z_c_r, self.ave, self.std, self.ske],
axis=1)
print(table)
#end = datetime.now()
del self.s_n_r
del self.z_c_r
del self.ave
del self.std
del self.ske
del self.select_model
del self.weight
del self.name
stock1_name = table.stock1.astype('str', copy=False)
stock2_name = table.stock2.astype('str', copy=False)
test_stock1 = np.array(self.data[stock1_name].T)
test_stock2 = np.array(self.data[stock2_name].T)
mean = np.zeros(len(table))
std = np.zeros(len(table))
for i in range(len(table)):
spread_m, spread = spread_mean(test_stock1, test_stock2, i, table)
mean[i] = np.mean(spread_m[-1:])
#std[i] = np.sqrt(np.mean(np.square(spread_m-spread)))
std[i] = get_Estd(test_stock1, test_stock2, i, table)
table['e_mu'] = mean
table['e_stdev'] = std
return table
def formation_period_single(day1):
# 合併二日資料
#min_price = np.log(pd.concat([day1,day2]))
min_price = day1
min_price = min_price.dropna(axis=1)
min_price.index = np.arange(0, len(min_price), 1)
unit_stock = np.where(
min_price.apply(lambda x: adfuller(x)[1] > 0.05,
axis=0) == True) # 找出單跟的股票
min_price.drop(min_price.columns[unit_stock], axis=1,
inplace=True) # 刪除單跟股票，剩餘為定態序列。
spread = min_price
#------------------------------------------------------------------------------
# 無母數開倉門檻--------------------------------------
ave = []
std = []
for i in range(len(spread.T)):
y = spread.iloc[:, i]
ave.append(np.mean(y))
std.append(np.std(y))
ave = pd.DataFrame(ave)
ave.columns = ["mu"]
std = pd.DataFrame(std)
std.columns = ["stdev"]
# 程式防呆
a = np.array(np.where(std < 0.0000001))
if a.size > 1:
a = int(np.delete(a, -1, axis=0))
spread.drop(spread.columns[a], axis=1, inplace=True)
ave.drop(ave.index[a], axis=0, inplace=True)
ave.index = np.arange(0, len(ave), 1)
std.drop(std.index[a], axis=0, inplace=True)
std.index = np.arange(0, len(std), 1)
#------------------------------------------------------------------------------
# 計算過零率 ( spread )------------------------------
Boot = 500
z_c_r = []
for j in range(len(spread.T)):
y = spread.iloc[:, j]
z_c_r.append(zcr(y, Boot))
z_c_r = pd.DataFrame(z_c_r)
z_c_r.columns = ["zcr"]
# -----------------------------------------------------------------------------
stock_name = pd.DataFrame(spread.columns)
stock_name.columns = ["stock"]
con = pd.concat([stock_name, z_c_r, ave, std], axis=1)
return con
def form_table(self):
# 將共整合係數標準化，此權重為資金權重，因此必須依股價高低轉為張數權重。
for i in range(len(self.name)):
total = abs(self.weight.w1[i]) + abs(self.weight.w2[i])
self.weight.w2[i] = (self.weight.w2[i] / total)
self.weight.w1[i] = (self.weight.w1[i] / total)
con = pd.concat([self.name, self.select_model, self.weight, self.pval],
axis=1)
#print("共整合係數標準化 done in " + str(end - start))
#------------------------------------------------------------------------------
#計算spread序列
spread = np.zeros((len(self.data), len(con)))
for i in range(len(con)):
spread[:, i] = con.w1[i] * self.data[
con.stock1[i]] + con.w2[i] * self.data[con.stock2[i]]
self.spread = pd.DataFrame(spread)
#print("刪除非定態spread序列 done in " + str(end - start))
#------------------------------------------------------------------------------
# 計算信噪比 ( spread )------------------------------
for i in range(len(self.spread.T)):
y = self.spread.iloc[:, i]
self.s_n_r.append(snr(y, 100))
self.s_n_r = pd.DataFrame(self.s_n_r)
self.s_n_r.columns = ["snr"]
#print("計算信噪比 done in " + str(end - start))
#------------------------------------------------------------------------------
# 計算過零率 ( spread )------------------------------
#pool = Pool(processes=16)
Boot = 500
for j in range(len(self.spread.T)):
y = self.spread.iloc[:, j]
#t = pool.apply_async(zcr, (y,Boot,con.stock1[j],con.stock2[j],),callback=self.append_zcr_result)
self.z_c_r.append(zcr(y, Boot))
#pool.close()
#pool.join()
#self.stock1_name = pd.DataFrame(self.stock1_name) ; self.stock1_name.columns = ["stock1"]
#self.stock2_name = pd.DataFrame(self.stock2_name) ; self.stock2_name.columns = ["stock2"]
# self.z_c_r = np.zeros(len(self.spread.T))
self.z_c_r = pd.DataFrame(self.z_c_r)
self.z_c_r.columns = ["zcr"]
#mix = pd.concat([self.stock1_name,self.stock2_name,self.z_c_r],axis=1)
#print("計算過零率 done in " + str(end - start))
#------------------------------------------------------------------------------
# 開倉門檻and平倉門檻and偏度--------------------------------------
for i in range(len(self.spread.T)):
y = self.spread.iloc[:, i]
# 有時間趨勢項的模型必須分開計算
if con.model_type[i] == 'model4':
x = np.arange(0, len(y))
b1, b0 = np.polyfit(x, y, 1)
trend_line = x * b1 + b0
y = y - trend_line
# 將spread消除趨勢項後，計算mu與std
self.ave.append(np.mean(y))
self.std.append(np.std(y))
self.ske.append(skew(y))
else:
self.ave.append(np.mean(y))
self.std.append(np.std(y))
self.ske.append(skew(y))
self.ave = pd.DataFrame(self.ave)
self.ave.columns = ["mu"]
self.std = pd.DataFrame(self.std)
self.std.columns = ["stdev"]
self.ske = pd.DataFrame(self.ske)
self.ske.columns = ["skewness"]
#print("開倉門檻and平倉門檻 done in " + str(end - start))
#------------------------------------------------------------------------------
# 整理表格
#start = datetime.now()
#con = pd.concat([con,self.s_n_r],axis=1)
#con = pd.merge( con , mix , on=["stock1","stock2"] , how="outer" )
con = pd.concat(
[con, self.s_n_r, self.z_c_r, self.ave, self.std, self.ske],
axis=1)
#end = datetime.now()
del self.s_n_r
del self.z_c_r
del self.ave
del self.std
del self.ske
del self.select_model
del self.weight
del self.name
#print("整理表格 done in " + str(end - start))
#print(con)
return con