def ts_rank_m(x, period):
# res = np.zeros(x.shape) * np.nan
# for ix in range(0, x.shape[0] - period + 1):
# res[ix + period - 1] = (np.argsort(np.argsort(x[ix:ix + period], axis=0), axis=0)[-1] + 1) * 1. / period
# res[np.isnan(x)] = np.nan
res = bn.move_rank(x, period, min_count=1, axis=0)
return res
def getStatsTS(X, Y, quantile=10, window=500, minCnt=250):
"""
X: Input factor, shape should be 40320*1082
Y: Existing factor, price
Calculate the return of 10, 20 ,30 by
Standardized Return_i = (Price_t+i-Price_t)/Price_t/i
"""
def calcFwdRet(price, window=30):
"""
"""
fwd = np.roll(price, -window, axis=0)
fwd[-window:, :] = np.nan
return fwd / price - 1
print('Now Calculating IC and IR matrix, start counting...')
t0 = time.time()
X = np.asarray(X)
Y = np.asarray(Y)
Y_ = np.zeros(Y.shape)
for i in range(len(Y) - 30):
for j in range(Y.shape[1]):
Y_[i, j] = (Y[i + 30, j] - Y[i, j]) / Y[i, j] / 30
Y = Y_
if X.shape != Y.shape:
print(X.shape)
print(Y.shape)
raise
N = len(X)
IC = np.zeros((N, ))
bottom = 1.0 / quantile
top = 1 - bottom
# ts rank
X = bn.move_rank(X, window=window, min_count=minCnt, axis=0)
print(np.isnan(X).sum())
# norm to [0, 1]
X = 0.5 * (X + 1)
# get common data
X = np.where((~np.isnan(X) & (~np.isnan(Y))), X, np.nan)
Y = np.where((~np.isnan(X) & (~np.isnan(Y))), Y, np.nan)
# cross-rank Y
Y_rk = bn.nanrankdata(Y, axis=1)
Y_rk /= bn.nanmax(Y_rk, axis=1)[:, np.newaxis]
# ls
LS = np.nanmean(np.where(X > top, Y, np.nan), axis=1) \
- np.nanmean(np.where(X < bottom, Y, np.nan), axis=1)
# Loop
for ii in range(N):
IC[ii] = np.corrcoef(X[ii][~np.isnan(X[ii])],
Y_rk[ii][~np.isnan(Y_rk[ii])])[0, 1]
t1 = time.time()
print("total time used for IC and LS matrix calculation is:", (t1 - t0))
return IC, LS
def init(self):
self.windows = self.param['window']
self.cols = self.param['col']
self.types = self.param['type']
self.translation_cols = self.param.get('translation')
self.scale_cols = self.param.get('scale')
self.move_window_mapping = {
"mean":
lambda c, s, t, w: bn.move_mean(c, w) * s + t,
"std":
lambda c, s, t, w: bn.move_std(c, w) * s,
"var":
lambda c, s, t, w: bn.move_var(c, w) * s * s,
"min":
lambda c, s, t, w: bn.move_min(c, w) * s + t,
"max":
lambda c, s, t, w: bn.move_max(c, w) * s + t,
"rank":
lambda c, s, t, w: bn.move_rank(c, w),
"sum":
lambda c, s, t, w: bn.move_sum(c, w) * s + t * w,
"ema":
lambda c, s, t, w: F.
ema(c, 2.0 /
(w + 1), start_indices=self.base.start_indices) * s + t,
"rsi":
lambda c, s, t, w: F.rsi(
c, w, start_indices=self.base.start_indices),
"psy":
lambda c, s, t, w: F.psy(
c, w, start_indices=self.base.start_indices),
"bias":
lambda c, s, t, w: F.bias(
c, w, start_indices=self.base.start_indices)
}
def Ts_rank(A, n):
if n < 2:
#print ("计算周期的排序，n不得小于2，返回输入")
return A
result = bk.move_rank(A, n, axis=0, min_count=1)
result[np.isnan(A)] = np.nan
result = result + 2 # 不希望值中出现0
return result
def ts_rank(data,period):
result = bk.move_rank(data,window=period, min_count=1,axis = 0)
return (result+1)/2
def main():
lines = getLines()
hdr = getHdr(lines) # array
if sys.argv[1] == 'hdrs':
hdrList = '\n'.join(hdr)
print(hdrList)
sys.exit(0)
colRefs = getColRefs(hdr)
#print('colRefs: {}'.format(colRefs))
windowPeriod = int(sys.argv[1])
workingColumns = []
for column in sys.argv[2:]:
workingColumns.append(column)
validateWorkingColumns(hdr, workingColumns)
#print('working columns: {}'.format(' - '.join(workingColumns)))
#print('first line: {}'.format(lines[0]))
# get the position in the data array for each column to check
colNums = [colRefs[i] for i in workingColumns]
#print('colNums: {}'.format(colNums))
#sys.exit(0)
# this is a dict of lists, where each list is all values for the column
#colValues = getDataSet(colRefs[workingColumns[0]],lines)
colValues = getDataSet(colRefs, workingColumns, lines)
#print('{}'.format(colValues))
ratesRising = False
for colName in workingColumns:
colNum = colRefs[colName]
ma = bn.move_rank(colValues[colNum], window=windowPeriod)
#print('len(ma): {}'.format(len(ma)))
#for i in range(0,len(ma)):
#if math.isnan(ma[i]):
#continue
#if i%72 == 0:
#print('{:0.2f}'.format(ma[i]))
# skip the first windowPeriod of values, as they are 'nan'
avgFirstPeriod = average(ma[windowPeriod:windowPeriod * 2])
midStart = int(len(ma) - (windowPeriod / 2))
avgMiddlePeriod = average(ma[midStart:midStart + windowPeriod])
avgLastPeriod = average(ma[len(ma) - windowPeriod:])
if (avgMiddlePeriod > avgFirstPeriod > 0) and (avgLastPeriod >
avgMiddlePeriod > 0):
#if True:
ratesRising = True
#print('{} is rising: {} {} {}'.format(colName,avgFirstPeriod,avgMiddlePeriod,avgLastPeriod))
print('{} is rising'.format(colName))
print(' avgFirstPeriod: {:0.6f}'.format(avgFirstPeriod))
print('avgMiddlePeriod: {:0.6f}'.format(avgMiddlePeriod))
print(' avgLastPeriod: {:0.6f}'.format(avgLastPeriod))
print(' %increased: {:5.0f}'.format(
((avgLastPeriod / avgFirstPeriod) - 1) * 100))
#print('{}'.format(ma))
if ratesRising:
sys.exit(1)
def time_move_rank(self, dtype, shape, order, axis, window):
bn.move_rank(self.arr, window, axis=axis)
def time_move_rank(self, dtype, shape, window):
bn.move_rank(self.arr, window)