def probabilityDensity(): print '## Estimating the Probability Density 估计概率密度' reload(numpredict) print '40 80 ',numpredict.probguess(data,[99,20],40,80) print '80 120 ',numpredict.probguess(data,[99,20],80,120) print '120 1000',numpredict.probguess(data,[99,20],120,1000) print '30 120 ',numpredict.probguess(data,[99,20],30,120)
def av_probs(data, vec1, highnum, k, weightf, width_a):
dicus = {}
for a in range(0, highnum + 1):
b = numpredict.probguess(data, vec1, a, a + width_a, k, weightf)
for c in range(a, a + width_a):
if c not in dicus: dicus[c] = []
dicus[c].append(b)
high2 = 0
for prob in dicus:
if len(dicus[prob]) > high2:
high2 = len(dicus[prob])
for x in dicus:
a = sum(dicus[x])
if a == 0:
dicus[x] = 0.0
else:
b = a / high2
dicus[x] = b
list1 = []
for a in dicus:
b = (a, int(dicus[a] * 500))
list1.append(b)
del dicus
return list1
def cumulativegraph(data,
vec1,
high,
k=5,
weightfun=numpredict.gaussianweight):
t1 = arange(0.0, high, S)
cprob = array(
[numpredict.probguess(data, vec1, 0, v, k, weightfun) for v in t1])
plot(t1, cprob)
def probabilitygraph(data, vec1, high, k=5, weightfun=numpredict.gaussianweight,
ss=5.0/10):
t1 = arange(0.0, high, S)
probs = [numpredict.probguess(data, vec1, v, v+S, k, weightfun) for v in t1]
# gaussian smooth with nearby points
smoothed = []
for i in range(len(probs)): # O(n^2)
sv = 0.0
for j in range(0, len(probs)):
dist = abs(i - j)*0.1
weight = numpredict.gaussianweight(dist, sigma=ss)
sv += weight*probs[j]
smoothed.append(sv)
plot(t1, array(probs))
plot(t1, array(smoothed))
def probabilitygraph(data,
vec1,
high,
k=5,
weightfun=numpredict.gaussianweight,
ss=5.0 / 10):
t1 = arange(0.0, high, S)
probs = [
numpredict.probguess(data, vec1, v, v + S, k, weightfun) for v in t1
]
# gaussian smooth with nearby points
smoothed = []
for i in range(len(probs)): # O(n^2)
sv = 0.0
for j in range(0, len(probs)):
dist = abs(i - j) * 0.1
weight = numpredict.gaussianweight(dist, sigma=ss)
sv += weight * probs[j]
smoothed.append(sv)
plot(t1, array(probs))
plot(t1, array(smoothed))
def cumulativegraph(data, vec1, high, k=5, weightfun=numpredict.gaussianweight):
t1 = arange(0.0, high, S)
cprob = array([numpredict.probguess(data, vec1, 0, v, k, weightfun)
for v in t1])
plot(t1, cprob)
