def dataType2Sigal(dt):
price_seps = [50.0,200.0]
volume_seps = [10,100,400]
key_transform = {'price' : numberic2SignalFn(float, price_seps),
'volume' : numberic2SignalFn(int, volume_seps)}
signals = {}
for key in key_transform:
if hasattr(dt, key):
v = getattr(dt, key)
signal = "%s%s" % (key, key_transform[key](v))
signals[signal] = 1
return signals
def dataType2Sigal(dt):
price_seps = [50.0, 200.0]
volume_seps = [10, 100, 400]
key_transform = {
'price': numberic2SignalFn(float, price_seps),
'volume': numberic2SignalFn(int, volume_seps)
}
signals = {}
for key in key_transform:
if hasattr(dt, key):
v = getattr(dt, key)
signal = "%s%s" % (key, key_transform[key](v))
signals[signal] = 1
return signals
def stats_items(iter, fn_conv, name):
logger.info("Stating %s", name)
#n2s = numberic2SignalFn(int, [0, 1, 10, 100, 400])
n2s = numberic2SignalFn(
int,
range(21) + range(30, 110, 10) + range(150, 350, 50) +
range(400, 1200, 200))
volumes = []
for i in iter:
iv = fn_conv(i)
s = n2s(iv)
volumes.append(s)
cs = Series(volumes)
g = cs.groupby(cs.values).agg(len)
total = len(volumes)
sig2prob = {}
for sig, count in g.iteritems():
if sig == 0:
logger.warn("%s sig %s -- %s %s %s", name, sig,
count * 1.0 / total, count, total)
total -= count
else:
logger.info("%s sig %s -- %s %s %s", name, sig,
count * 1.0 / total, count, total)
sig2prob[sig] = count * 1.0 / total
return sig2prob
def __init__(self):
self.total = 0
self.matched = 0
self.shop_matched = 0
self.item_matched = 0
self.notmatched_item_exists = 0
dbs = get_db_engines(**{'dbconnstrs' : FLAGS.xdbconnstrs})
self.guangdb = dbs[0]
self.statdb = dbs[1]
self.timediffs = []
self.pricediffs = []
self.volumediffs = []
self.volumesignal_diffs = []
self.volume2signal = numberic2SignalFn(int, [1, 10, 100, 400])
def stats_items_dist(iter, fn_conv, name, splitter):
logger.info("Stating %s", name)
n2s = numberic2SignalFn(int, splitter.range_sum)
volumes = []
for i in iter:
iv = fn_conv(i)
s = n2s(iv)
volumes.append(s)
cs = Series(volumes)
g = cs.groupby(cs.values).agg(len)
total = len(volumes)
sig2prob = {}
for sig, count in g.iteritems():
if sig == 0:
logger.warn("%s sig %s -- %s %s %s", name, sig, count*1.0/total, count, total)
total -= count
else:
logger.info("%s sig %s -- %s %s %s", name, sig, count*1.0/total, count, total)
sig2prob[sig] = count*1.0/total
return sig2prob
def stats_items(iter, fn_conv, name):
logger.info("Stating %s", name)
#n2s = numberic2SignalFn(int, [0, 1, 10, 100, 400])
n2s = numberic2SignalFn(int, range(21) + range(30, 110, 10) + range(150,350,50) + range(400,1200,200))
volumes = []
for i in iter:
iv = fn_conv(i)
s = n2s(iv)
volumes.append(s)
cs = Series(volumes)
g = cs.groupby(cs.values).agg(len)
total = len(volumes)
sig2prob = {}
for sig, count in g.iteritems():
if sig == 0:
logger.warn("%s sig %s -- %s %s %s", name, sig, count*1.0/total, count, total)
total -= count
else:
logger.info("%s sig %s -- %s %s %s", name, sig, count*1.0/total, count, total)
sig2prob[sig] = count*1.0/total
return sig2prob
def stats_items_dist(iter, fn_conv, name, splitter):
logger.info("Stating %s", name)
n2s = numberic2SignalFn(int, splitter.range_sum)
volumes = []
for i in iter:
iv = fn_conv(i)
s = n2s(iv)
volumes.append(s)
cs = Series(volumes)
g = cs.groupby(cs.values).agg(len)
total = len(volumes)
sig2prob = {}
for sig, count in g.iteritems():
if sig == 0:
logger.warn("%s sig %s -- %s %s %s", name, sig,
count * 1.0 / total, count, total)
total -= count
else:
logger.info("%s sig %s -- %s %s %s", name, sig,
count * 1.0 / total, count, total)
sig2prob[sig] = count * 1.0 / total
return sig2prob