def gmmEM(data, K, it,show=False,usekmeans=True):
#data += finfo(float128).eps*100
centroid = kmeans2(data, K)[0] if usekmeans else ((max(data) - min(data))*random_sample((K,data.shape[1])) + min(data))
N = data.shape[0]
gmm = GaussianMM(centroid)
if show: gmm.draw(data)
while it > 0:
print it," iterations remaining"
it = it - 1
# e-step
gausses = zeros((K, N), dtype = data.dtype)
for k in range(0, K):
gausses[k] = gmm.c[k]*mulnormpdf(data, gmm.mean[k], gmm.covm[k])
sums = sum(gausses, axis=0)
if count_nonzero(sums) != sums.size:
raise "Divide by Zero"
gausses /= sums
# m step
sg = sum(gausses, axis=1)
if count_nonzero(sg) != sg.size:
raise "Divide by Zero"
gmm.c = ones(sg.shape) / N * sg
for k in range(0, K):
gmm.mean[k] = sum(data * gausses[k].reshape((-1,1)), axis=0) / sg[k]
d = data - gmm.mean[k]
d1 = d.transpose()*gausses[k]
gmm.covm[k]=dot(d1,d)/sg[k]
if show: gmm.draw(data)
return gmm
def simulate_buy_and_hold(df_day_gain, df_analyzed):
df_buy_and_hold = df_day_gain.copy()
for row_index, row in df_buy_and_hold.iterrows():
analyzed_row = df_analyzed.loc[row_index]
number_of_invested = count_nonzero(analyzed_row)
money_invested = previous_row.sum(
) if row_index != df_buy_and_hold.index[0] else 1
for key, value in row.iteritems():
if row_index == df_buy_and_hold.index[0]:
row[key] = money_invested / \
number_of_invested if analyzed_row[key] else 0
else:
if previous_row_invested == number_of_invested:
row[key] = (1 + value) * \
previous_row[key] if analyzed_row[key] else 0
else:
row[key] = (1 + value) * (
money_invested /
number_of_invested) if analyzed_row[key] else 0
previous_row = row
previous_row_invested = number_of_invested
return df_buy_and_hold
def calculateMisclassificationRate(ours, real):
return 1.0 - count_nonzero(ours + real)*1.0 / ours.size
def checkClassification(self,binary):
fp = count_nonzero(logical_and(self.notMask, binary))
tp = count_nonzero(logical_and(self.mask,binary))
return fp,tp
def __init__(self,fileName):
self.mask = imread(fileName) > 0
self.notMask = logical_not(self.mask)
self.positives = count_nonzero(self.mask)*1.0
self.negatives = (self.mask.size - self.positives)*1.0
