def test_tot(self): """Histogram total retrieval""" a = [1,3,5,2,4,0,7,7.01] hist = stats.Histogram(a, n_bins=8) #print hist.total self.assertTrue(hist.total==len(a)) hist.add([3,-1]) self.assertTrue(hist.total==len(a)+2)
def test(self): """Histogram""" a = [1,3,5,2,4,0,7,7.01] hist = stats.Histogram() hist.init(min(a), max(a), 10) hist.add(a) self.assertTrue(len(hist.extras) == 0) hist.add(12.0) self.assertTrue(len(hist.extras) == 1)
def test_neardist(self): """Nearest distances""" comp = protprop.Composition() pp = protprop.ProteinProperties() aa_classes = ['FY','P','NQ'] for xi in range(5): seq = genMotif(aa_classes, [(0,2),(1,1),(2,2),(0,2),(1,1),(2,2)]) #print seq dists = pp.nearestDistances(seq, aa_classes) #print dists hist = stats.Histogram(vals=dists['FY'], n_bins=7, min_val=-0.5,max_val=6.5) #print hist self.assertTrue(hist[1].count==2) self.assertTrue(hist[4].count==1) self.assertTrue(hist[2].count==0)
def test_alldist(self): """All distances""" comp = protprop.Composition() pp = protprop.ProteinProperties() aa_classes = ['FY','P','NQ'] for xi in range(5): seq = genMotif(aa_classes, [(0,2),(1,1),(2,2),(0,2),(1,1),(2,2)]) #print seq dists = pp.allDistances(seq, aa_classes) #print dists hist = stats.Histogram(vals=dists['FY'], n_bins=7, min_val=-0.5,max_val=6.5) #print hist self.assertTrue(hist[1].count==2) self.assertTrue(hist[4].count==1) self.assertTrue(hist[2].count==0) answer = [1, 5, 6, 4, 5, 1] for (a,b) in zip(dists['FY'], answer): self.assertTrue(a==b)
subseq = seq[startpos:(startpos + window_size)]
if not '*' in subseq:
score = quant.quant(subseq, base=options.logarithm_base)
if score < min_ent:
min_ent = score
min_seq = subseq
if score > max_ent:
max_ent = score
max_seq = subseq
scores.append(score)
n_samples += 1
data_outs.write("# Minimum-entropy sequence = {}\n".format(min_seq))
data_outs.write("# Maximum-entropy sequence = {}\n".format(max_seq))
hist = stats.Histogram([20**s for s in scores], options.num_bins)
data_outs.write(
"ent.lower\tent.mid\tent.upper\tcount\tdensity\tcum.count\tcum.density\n"
)
n_written = 0
for b in hist.bins:
line = "{me.lower:1.4f}\t{me.mid:1.4f}\t{me.upper:1.4f}\t{me.count:d}\t{me.density:1.3E}\t{me.cum:d}\t{me.cumdensity:1.3E}\n".format(
me=b)
data_outs.write(line)
n_written += 1
# Write out stopping time
data_outs.write("# Run finished {}\n".format(util.timestamp()))
# Shut down output
if not options.out_fname is None:
def test_bin(self): """Histogram bin value retrieval""" a = [1,3,5,2,4,0,7,7.01] hist = stats.Histogram(a, n_bins=8) self.assertTrue(hist[7].count == 2) self.assertTrue(hist[-1].count == 0)
#! /usr/local/bin/python
import sys, os, math, string, random, pickle
import stats
if __name__ == "__main__":
h = stats.Histogram()
bin_min = -1.3
bin_max = 10
h.init(bin_min, bin_max, 10)
for i in range(10000):
x = random.random() * (bin_max - bin_min - 2) + bin_min
h.add(x)
print h
h = stats.Histogram()
h.init(bin_min, bin_max, 10)
try:
h.add("waah")
except TypeError, te:
print te
print h
h = stats.Histogram()
print h