def fj(realizations, n, p, k, s):
local_log = np.zeros((realizations, 11))
#Realizations
for r in range(realizations):
orig_data = gen_structure_data(n, p).flatten()
variance = np.var(orig_data)
data = orig_data.copy()
#np.save('data.npy', data)
t1 = time.time()
pivots = vFisher(data, classes=k)
t2 = time.time()
fj_tss = get_tss(k, data, pivots)
#Cleanup
del data
data = orig_data.copy()
#data = np.load('data.npy')
####Ordered Sample####
t3 = time.time()
sample = fj_generate_sample(data, pct=s, random=False)
#Returns pivots in the sample, not pivots in the total - hence C-TSS is way off.
fj_ordered = vFisher(sample, classes=k)
t4 = time.time()
data.sort()
pivots = []
for cl in range(0, k - 1):
pivots.append(np.where(data == sample[fj_ordered[cl]])[0][-1])
fj_ordered_tss = get_tss(k, data, pivots)
#Cleanup
del data
data = orig_data.copy()
#data = np.load('data.npy')
####Random Sample####
t5 = time.time()
sample = fj_generate_sample(data, pct=s)
fj_random = vFisher(sample, classes=k)
t6 = time.time()
data.sort()
pivots = []
for cl in range(0, k - 1):
pivots.append(np.where(data == sample[fj_random[cl]])[0][-1])
fj_random_tss = get_tss(k, data, pivots)
log = [
n, k, p, s, variance, fj_tss, fj_random_tss, fj_ordered_tss,
t2 - t1, t4 - t3, t6 - t5
]
log = map(str, log)
local_log[r] = np.array(log)
return local_log
def fj(realizations, n, p, k, s):
local_log = np.zeros((realizations, 11))
#Realizations
for r in range(realizations):
orig_data = gen_structure_data(n,p).flatten()
variance = np.var(orig_data)
data = orig_data.copy()
#np.save('data.npy', data)
t1 = time.time()
pivots = vFisher(data, classes=k)
t2 = time.time()
fj_tss = get_tss(k, data, pivots)
#Cleanup
del data
data = orig_data.copy()
#data = np.load('data.npy')
####Ordered Sample####
t3 = time.time()
sample = fj_generate_sample(data, pct=s, random=False)
#Returns pivots in the sample, not pivots in the total - hence C-TSS is way off.
fj_ordered = vFisher(sample, classes=k)
t4 = time.time()
data.sort()
pivots = []
for cl in range(0,k-1):
pivots.append(np.where(data==sample[fj_ordered[cl]])[0][-1])
fj_ordered_tss = get_tss(k, data, pivots)
#Cleanup
del data
data = orig_data.copy()
#data = np.load('data.npy')
####Random Sample####
t5 = time.time()
sample = fj_generate_sample(data, pct=s)
fj_random = vFisher(sample, classes=k)
t6 = time.time()
data.sort()
pivots = []
for cl in range(0,k-1):
pivots.append(np.where(data==sample[fj_random[cl]])[0][-1])
fj_random_tss = get_tss(k, data, pivots)
log = [n,k,p, s,variance, fj_tss, fj_random_tss, fj_ordered_tss, t2-t1, t4-t3, t6-t5]
log = map(str, log)
local_log[r] = np.array(log)
return local_log
def fj(realizations, n, k, p):
local_log = np.zeros((realizations, 28))
#Realizations
for r in range(realizations):
#Fully computed
orig_data, variance = gen_structure_data(n, p)
data = np.copy(orig_data).ravel()
t1 = time.time()
pivots = vFisher(data, classes=k)
t2 = time.time()
fj_time = t2 - t1
fj_tss = get_tss(k, data, pivots)
del data
#Quantiles
data = np.copy(orig_data).ravel()
t1 = time.time()
quantiles = ps.esda.mapclassify.Quantiles(data, k=k)
t2 = time.time()
q_time = t2-t1
q_tss = quantiles.get_tss()
ordered_time = np.empty(5)
ordered_tss = np.empty(5)
random_time = np.empty(5)
random_tss = np.empty(5)
#Since each sample size is a different method, compute those in a loop
for i, s in enumerate([0.05, 0.1, 0.15, 0.2, 0.25]):
del data
data = np.copy(orig_data).ravel()
####Ordered Sample####
t3 = time.time()
sample = fj_generate_sample(data, pct=s, random=False)
#Returns pivots in the sample, not pivots in the total - hence C-TSS is way off.
fj_ordered = vFisher(sample, classes=k)
t4 = time.time()
data.sort()
pivots = []
for cl in range(0,k-1):
pivots.append(np.where(data==sample[fj_ordered[cl]])[0][-1])
ordered_tss[i] = get_tss(k, data, pivots)
ordered_time[i] = t4-t3
#Cleanup
del data
data = np.copy(orig_data).ravel()
####Random Sample####
t5 = time.time()
sample = fj_generate_sample(data, pct=s)
fj_random = vFisher(sample, classes=k)
t6 = time.time()
data.sort()
pivots = []
for cl in range(0,k-1):
pivots.append(np.where(data==sample[fj_random[cl]])[0][-1])
random_tss[i] = get_tss(k, data, pivots)
random_time[i] = t6 - t5
sampled = np.hstack((ordered_tss,ordered_time, random_tss, random_time))
log = [n,k,p,variance, fj_tss, fj_time, q_tss, q_time]
log = map(str, log)
local_log[r] = np.hstack((np.array(log),sampled))
return local_log
