def __init__(self, SCORE_ID, errprob, err_funcs, aggcols, epsilon, **kwargs):
self.global_std = StdFunc()
self.global_mean = AvgFunc()
self.global_bounds = [1e10000, -1e10000]
self.SCORE_ID = SCORE_ID
self.err_funcs = err_funcs
self.aggcols = aggcols
self.epsilon = epsilon
self.errprob = errprob
self.min_points = kwargs.get('min_points', 2)
self.sampler = Sampler(self.errprob, self.SCORE_ID)
def __init__(self, *args, **kwargs):
QuadScoreSample4.__init__(self, *args, **kwargs)
self.global_std = StdFunc()
self.global_mean = AvgFunc()
self.global_bounds = [1e10000, -1e10000]
self.epsilon = kwargs.get('epsilon', 0.005)
class QuadScoreSample5(QuadScoreSample4):
"""
uses global std and mean
"""
def __init__(self, *args, **kwargs):
QuadScoreSample4.__init__(self, *args, **kwargs)
self.global_std = StdFunc()
self.global_mean = AvgFunc()
self.global_bounds = [1e10000, -1e10000]
self.epsilon = kwargs.get('epsilon', 0.005)
def evaluate_split(self, stats_list):
probs = []
for stat in stats_list:
if not stat:
continue
est, std = stat.est, stat.std
if not len(stat.vals):
prob = 0.
elif std == 0:
prob = 1.
else:
weight = self.weight(max(stat.vals))
if weight == 0:
prob = 1.
else:
bound = max(stat.vals) - min(stat.vals)
prob = (std * (2.58 + 2.58)) / weight
prob = 1 - prob / (self.global_bounds[1] - self.global_bounds[0])
#prob = est + 2.58 * std
# if std == 0:
# prob = 1.
# else:
# # Prob( (X-mean)^2 < epsilon ) >= 0.95
# w = self.weight(est + 2.58 * std)
# alpha = self.epsilon * abs(est) / w
# prob = math.erf(alpha / (std * math.sqrt(2.)))
probs.append(prob)
return np.mean(probs) if probs else 0.
def evaluate(self, table):
if not len(table):
return PartitionStats(self.global_mean.value(),
std=self.global_std.value(),
vals=[])
vals = []
newvals = []
for row in table:
if row[self.SCORE_ID].value == -inf:
est = self.err_func([row])
row[self.SCORE_ID] = est
newvals.append(est)
vals.append(row[self.SCORE_ID].value)
samp_size = len(vals)
newvals = np.array(newvals)
self.global_std.delta(add=[newvals], update=True)
self.global_mean.delta(add=[newvals], update=True)
self.global_bounds[0] = min(self.global_bounds[0], min(vals))
self.global_bounds[1] = max(self.global_bounds[1], max(vals))
if samp_size == 1:
est, std = vals[0], 0.
else:
# slightly biased std estimator
est = np.mean(vals)
S2 = 1. / (samp_size - 1) * sum([(v-est)**2 for v in vals])
S = math.sqrt(S2)
std = self.kn(samp_size) * S
if samp_size > 2:
_logger.debug('\tsampsize(%d)\t%.4f+-%.4f\t%.4f - %.4f',
samp_size,
est,
std,
self.global_bounds[0],
self.global_bounds[1]
)
return PartitionStats(est, std=std, vals=vals)
def weight(self, val):
u = self.global_mean.value()
std = self.global_std.value()
if std == 0:
return 1.
max_std = 2.58
#max_std = 1.6
# weight increases quadratically.
nstds = (val - u) / std
nstds = min(max(0, nstds), max_std)
y = (nstds / max_std) ** 2
return y
# linear scale, hits maximum at 2.58-0.5 i think
r = 2.58 + 2.58 + 0.5 # why is a 0.5 here?
v = min(r, max(0., (val - u) / std - 0.5))
return 0.0001 + (v / r) * (1 - 0.0001)
# using ERF
w = .5 * (1 + math.erf( (val-u) / math.sqrt(2*std**2) ))
# rescale to be between 0.2 - 1
return 0.001 + w * (1 - 0.001)
def should_stop(self, table, stats):
if len(table) <= self.min_points:
return True
std, est = stats.std, stats.est
val, allsame = None, True
for i, row in enumerate(table):
if i == 0:
val = tuple([row[aggcol].value for aggcol in self.aggcols])
else:
if val != tuple([row[aggcol].value for aggcol in self.aggcols]):
allsame = False
break
if allsame:
return True
# Prob( (X-mean)^2 < epsilon ) >= 0.95
w = self.weight(est + 2.58 * std)
if w == 0 or std == 0:
prob = 1.
else:
alpha = math.sqrt( self.epsilon * abs(est) / w )
#alpha = self.epsilon * 2.58 * self.global_std.value() / w
#alpha = math.sqrt( self.epsilon * 2 * 2.58 * self.global_std.value() / w )
prob = math.erf(alpha / (std * math.sqrt(2.)))
return prob >= 0.95
class Evaluator(object):
def __init__(self, SCORE_ID, errprob, err_funcs, aggcols, epsilon, **kwargs):
self.global_std = StdFunc()
self.global_mean = AvgFunc()
self.global_bounds = [1e10000, -1e10000]
self.SCORE_ID = SCORE_ID
self.err_funcs = err_funcs
self.aggcols = aggcols
self.epsilon = epsilon
self.errprob = errprob
self.min_points = kwargs.get('min_points', 2)
self.sampler = Sampler(self.errprob, self.SCORE_ID)
def kn(self, n):
"""
return Kn, where UMVU estimator of std is Kn*S
"""
try:
return math.sqrt(2./(n-1)) * (math.gamma(n/2.) / (math.gamma((n-1.)/2.)))
except:
return 1.
def evaluate(self, tables, sample=True):
if isinstance(tables, list):
self.samples = self.sampler(tables) if sample else tables
if not self.samples:
return None
ests, stds, vals = [], [], []
for table, err_func in zip(self.samples, self.err_funcs):
est, std, vs = self.evaluate_table(table, err_func)
ests.append(est)
stds.append(std)
vals.extend(vs)
est = np.mean(ests)
std = np.mean(stds)
if len(self.err_funcs) and 'Sum' in str(self.err_funcs[0].klass):
est = est / sum(map(len, self.samples)) * sum(map(len, tables))
if len(vals) != sum(map(len, self.samples)):
raise RuntimeError("# vals != # samples")
if sample and len(vals) != sum(map(len, tables)):
raise RuntimeError("# vals != # pts")
return PartitionStats(est, std=std, vals=vals)
else:
return self.evaluate([tables], sample=sample)
def evaluate_table(self, table, err_func):
if not len(table):
return (err_func([]),
0.,
[])
vals = []
newvals = []
for row in table:
if row[self.SCORE_ID].value == -inf:
est = err_func([row])
row[self.SCORE_ID] = est
newvals.append(est)
vals.append(row[self.SCORE_ID].value)
samp_size = len(vals)
newvals = np.array(newvals)
self.global_std.delta(add=[newvals], update=True)
self.global_mean.delta(add=[newvals], update=True)
self.global_bounds[0] = min(self.global_bounds[0], min(vals))
self.global_bounds[1] = max(self.global_bounds[1], max(vals))
if samp_size == 1:
est, std = vals[0], 0.
else:
# slightly biased std estimator
try:
est = np.mean(vals)
except:
pdb.set_trace()
S2 = 1. / (samp_size - 1) * sum([(v-est)**2 for v in vals])
S = math.sqrt(S2)
std = self.kn(samp_size) * S
if samp_size > 2:
_logger.debug('\tsampsize(%d)\t%.4f+-%.4f\t%.4f - %.4f',
samp_size,
est,
std,
self.global_bounds[0],
self.global_bounds[1]
)
return est, std, vals
def weight(self, val):
u = self.global_mean.value()
std = self.global_std.value()
if std == 0:
return 1.
max_std = 2.58
#max_std = 1.6
# weight increases quadratically.
nstds = (val - u) / std
nstds = min(max(0, nstds + 2), max_std)
y = (nstds / max_std) ** 2
return y
# linear scale, hits maximum at 2.58-0.5 i think
r = 2.58 + 2.58 + 0.5 # why is a 0.5 here?
v = min(r, max(0., (val - u) / std - 0.5))
return 0.0001 + (v / r) * (1 - 0.0001)
# using ERF
w = .5 * (1 + math.erf( (val-u) / math.sqrt(2*std**2) ))
# rescale to be between 0.2 - 1
return 0.001 + w * (1 - 0.001)
def should_stop(self, tables, bad_stats, good_stats):
if max(map(len,tables)) <= self.min_points:
return True
# val, allsame = None, True
# for i, row in enumerate(table):
# if i == 0:
# val = tuple([row[aggcol].value for aggcol in self.aggcols])
# else:
# if val != tuple([row[aggcol].value for aggcol in self.aggcols]):
# allsame = False
# break
# if allsame or std == 0:
# return True
if bad_stats.std == 0:
return True
weight = self.weight(max(bad_stats.vals))
if weight == 0:
return True
threshold = (self.global_bounds[1] - self.global_bounds[0]) * self.epsilon / weight
bounds = max(bad_stats.vals) - min(bad_stats.vals)
bounds = max(bounds, bad_stats.std * 2.58 * 2)
return bounds < threshold
#w = self.weight(est + 2.58 * std)
wmse = np.mean([self.weight(v) * (abs(v - bad_stats.est))**2 for v in bad_stats.vals])
return wmse < self.epsilon * (self.global_bounds[1] * 0.8)
