Related
Code implements the dynamic programming solution for global pairwise alignment of two sequences. Trying to perform a semi-global alignment between the SARS-CoV-2 reference genome and the first read in the Nanopore sample. The length of the reference genome is 29903 base pairs and the length of the first Nanopore read is 1246 base pairs. When I run the following code, I get this message in my terminal:
import sys
import numpy as np
GAP = -2
MATCH = 5
MISMATCH = -3
MAXLENGTH_A = 29904
MAXLENGTH_B = 1247
# insert sequence files
A = open("SARS-CoV-2 reference genome.txt", "r")
B = open("Nanopore.txt", "r")
def max(A, B, C):
if (A >= B and A >= C):
return A
elif (B >= A and B >= C):
return B
else:
return C
def Tmax(A, B, C):
if (A > B and A > C):
return 'D'
elif (B > A and B > C):
return 'L'
else:
return 'U'
def m(p, q):
if (p == q):
return MATCH
else:
return MISMATCH
def append(st, c):
return c + "".join(i for i in st)
if __name__ == "__main__":
if (len(sys.argv) != 2):
print("Usage: align <input file>")
sys.exit()
if (not os.path.isfile(sys.argv[1])):
print("input file not found.")
sys.exit()
S = np.empty([MAXLENGTH_A, MAXLENGTH_B], dtype = int)
T = np.empty([MAXLENGTH_A, MAXLENGTH_B], dtype = str)
with open(sys.argv[1], "r") as file:
A = str(A.readline())[:-1]
B = str(B.readline())[:-1]
print("Sequence A:",A)
print("Sequence B:",B)
N = len(A)
M = len(B)
S[0][0] = 0
T[0][0] = 'D'
for i in range(0, N + 1):
S[i][0] = GAP * i
T[i][0] = 'U'
for i in range(0, M + 1):
S[0][i] = GAP * i
T[0][i] = 'L'
for i in range(1, N + 1):
for j in range(1, M + 1):
S[i][j] = max(S[i-1][j-1]+m(A[i-1],B[j-1]),S[i][j-1]+GAP,S[i-1][j]+GAP)
T[i][j] = Tmax(S[i-1][j-1]+m(A[i-1],B[j-1]),S[i][j-1]+GAP,S[i-1][j]+GAP)
print("The score of the alignment is :",S[N][M])
i, j = N, M
RA = RB = RM = ""
while (i != 0 or j != 0):
if (T[i][j]=='D'):
RA = append(RA,A[i-1])
RB = append(RB,B[j-1])
if (A[i-1] == B[j-1]):
RM = append(RM,'|')
else:
RM = append(RM,'*')
i -= 1
j -= 1
elif (T[i][j]=='L'):
RA = append(RA,'-')
RB = append(RB,B[j-1])
RM = append(RM,' ')
j -= 1
elif (T[i][j]=='U'):
RA = append(RA,A[i-1])
RB = append(RB,'-')
RM = append(RM,' ')
i -= 1
print(RA)
print(RM)
print(RB)
This has nothing to do with python. The error message comes this line:
if (len(sys.argv) != 2):
print("Usage: align <input file>")
The code expects to be called with exactly one argument, the input file:
align path/to/input/file
You provided a different number of arguments, probably zero.
just a small labyrinth solver. try it to on python but dont even understand why it doesnt print anything. Im just started with python and trying to actually translate my teachers code from cpp just for interest.
need to reach to the destination after visiting each cell
m = [
[2,0,0,0,0,0],
[0,0,0,0,0,0],
[0,0,0,0,0,0],
[0,0,0,0,0,0],
[0,0,0,2,0,0],
[0,0,0,0,0,0]
]
STOP = 34
r = 0
c = 0
def init( r_: int = 0, c_: int = 0) -> None:
r = 0
c = 0
def step(r,c,level):
if level==STOP-1:
if r == 3 and c == 5:
for i in range(0,level):
print("("+init(int(r),int(c))+"," + init(int(r),int(c)) + ") - ")
print("(3,5)\n")
return True
else:
return False
m[r][c]=1
if c > 0 and m[r][c - 1] == 0:
if step(r, c - 1, level + 1):
return True
if c < 5 and m[r][c + 1] == 0:
if (step(r, c + 1, level + 1)):
return True
if r > 0 and m[r - 1][c] == 0:
if (step(r - 1, c, level + 1)):
return True
if r < 5 and m[r + 1][c] == 0:
if (step(r + 1, c, level + 1)):
return True
m[r][c] = 0
return False
def main(argc, argv):
step(0, 1, 0)
Python doesn't automatically call main like c does, nor does it require a main function. Your code can just live in the top level (e.g. print('hello world') is a valid, complete program)
Change this line:
def main(argc, argv):
to this:
if __name__ == '__main__':
got it
import matplotlib.pyplot as plt
S, F, W, X = 1, 2, 0, None
FIELD = [[X,S,W,W,W,W],
[W,W,W,W,W,W],
[W,W,W,W,W,W],
[W,W,W,W,W,F],
[W,W,W,X,W,W],
[W,W,W,W,W,W]]
ROWS = len(FIELD)
COLS = len(FIELD[0])
START_POS = [(i, line.index(S)) for i, line in enumerate(FIELD) if S in line][0]
FINISH_POS = [(i, line.index(F)) for i, line in enumerate(FIELD) if F in line][0]
STEPS = sum(line.count(W) for line in FIELD) + 1
print("Start:", START_POS, "\nFinish:", FINISH_POS, "\nTotal steps:", STEPS)
def do_step(level, path, points):
global FIELD
r, c = points[-1]
if r<0 or c<0 or r>=ROWS or c>=COLS or FIELD[r][c] == X:
return
if level == STEPS and (r, c) == FINISH_POS:
print("Found path:", path)
yy, xx = zip(*points)
plt.plot(xx, yy, "-ok")
plt.gca().invert_yaxis()
plt.show()
exit()
current = FIELD[r][c]
FIELD[r][c] = X
for dr, dc, dir in ((-1,0,'^'), (0,1,'>'), (1,0,'v'), (0,-1,'<')):
do_step(level+1, path+dir, points+[(r+dr,c+dc)])
FIELD[r][c] = current
do_step(0, "", [START_POS])
print("No path's found.")
I'm currently trying to code a non linear SVM for handwritten digits recognition using the MNIST data base.
I chose to use the SMO algorithm (based on Platt's paper and other books), but I have some trouble implementing it.
When I run the code over the training set, the bias goes higher and higher, sometimes until "Inf" value, leading the SVM to "classify" every example in the same class.
Here is my code:
import numpy
import gzip
import struct
import matplotlib
from sklearn import datasets
from copy import copy
class SVM:
def __init__(self, constant, data_set, label_set):
self._N = len(data_set)
if self._N != len(label_set):
raise Exception("Data size and label size don't match.")
self._C = constant
self._epsilon = 0.001
self._tol = 0.001
self._data = [numpy.ndarray.flatten((1/255)*elt) for elt in data_set]
self._dimension = len(self._data[0])
self._label = label_set
self._alphas = numpy.zeros((1, self._N))
self._b = 0
self._errors = numpy.ndarray((2, 0))
def kernel(self, x1, x2):
x1 = x1.reshape(1,self._dimension)
result = numpy.power(numpy.dot(x1, x2), 3)
return result
def evaluate(self, x):
result = 0
i = 0
while i < self._N:
result += self._alphas[0, i]*self._label[i]*self.kernel(x, self._data[i])
i += 1
result += self._b
return result
def update(self, i1, i2, E2):
i1 = int(i1)
i2 = int(i2)
if i1 == i2:
return 0
y1 = self._label[i1]
y2 = self._label[i2]
alpha1 = self._alphas[0, i1]
alpha2 = self._alphas[0, i2]
#If alpha1 is non-bound, its error is in the cache.
#So we check its position to extract its error.
#Else, we compute it.
if alpha1 > 0 and alpha1 < self._C :
position = 0
for i, elt in enumerate(self._errors[0, :]):
if elt == i1:
position = i
E1 = self._errors[1, position]
else:
E1 = self.evaluate(self._data[i1]) - y1
s = y1*y2
H = L = 0
if y1 != y2:
L = max(0, alpha2 - alpha1)
H = min(self._C, self._C + alpha2 - alpha1)
else:
L = max(0, alpha2 + alpha1 - self._C)
H = min(self._C, alpha2 + alpha1)
if H == L:
return 0
K11 = self.kernel(self._data[i1], self._data[i1])
K12 = self.kernel(self._data[i1], self._data[i2])
K22 = self.kernel(self._data[i2], self._data[i2])
eta = K11 + K22 - 2*K12
if eta > 0:
alpha2_new = alpha2 + (y2*(E1 - E2)/eta)
if alpha2_new < L:
alpha2_new = L
elif alpha2_new > H:
alpha2_new = H
else:
f1 = y1*(E1 + self._b) - alpha1*K11 - s*alpha2*K12
f2 = y2*(E2 + self._b) - alpha2*K22 - s*alpha1*K12
L1 = alpha1 + s*(alpha2 - L)
H1 = alpha1 + s*(alpha2 - H)
FuncL = L1*f1 + L*f2 + (1/2)*numpy.square(L1)*K11 + (1/2)*numpy.square(L)*K22 + s*L1*L*K12
FuncH = H1*f1 + H*f2 + (1/2)*numpy.square(H1)*K11 + (1/2)*numpy.square(H)*K22 + s*H1*H*K12
if FuncL < FuncH - self._epsilon:
alpha2_new = L
elif FuncL > FuncH + self._epsilon:
alpha2_new = H
else:
alpha2_new = alpha2
if numpy.abs(alpha2_new - alpha2) < self._epsilon*(alpha2_new+alpha2+ self._epsilon):
return 0
alpha1_new = alpha1 + s*(alpha2 - alpha2_new)
#Update of the threshold.
b1 = E1 + y1*(alpha1_new - alpha1)*K11 + y2*(alpha2_new - alpha2)*K12 + self._b
b2 = E2 + y1*(alpha1_new - alpha1)*K12 + y2*(alpha2_new - alpha2)*K22 + self._b
if L < alpha1_new < H:
b_new = b1
elif L < alpha2_new < H:
b_new = b2
else:
b_new = (b1+b2)/2
#Update the cache error
#If alpha2 was bound and its new value is non-bound, we add its index and its error to the cache.
#If alpha2 was unbound and its new value is bound, we delete it from the cache.
if (alpha2 == 0 or alpha2 == self._C) and (alpha2_new > 0 and alpha2_new < self._C):
vector_alpha2_new = numpy.array([i2, E2])
vector_alpha2_new = vector_alpha2_new.reshape((2, 1))
self._errors = numpy.concatenate((self._errors, vector_alpha2_new), 1)
if (alpha2 > 0 and alpha2 < self._C) and (alpha2_new == 0 or alpha2_new == self._C):
l = 0
position = 0
while l < len(self._errors[0, :]):
if self._errors[0, l] == i2:
position = l
l += 1
self._errors = numpy.delete(self._errors, position, 1)
#We do the exact same thing with alpha1.
if (alpha1 == 0 or alpha1 == self._C) and (alpha1_new > 0 and alpha1_new < self._C):
vector_alpha1_new = numpy.array([i1, E1])
vector_alpha1_new = vector_alpha1_new.reshape((2, 1))
self._errors = numpy.concatenate((self._errors, vector_alpha1_new), 1)
if (alpha1 > 0 and alpha1 < self._C) and (alpha1_new == 0 or alpha1_new == self._C):
l = 0
position = 0
while l < len(self._errors[0, :]):
if self._errors[0, l] == i1:
position = l
l += 1
self._errors = numpy.delete(self._errors, position, 1)
#Then we update the error for each non bound point using the new values for alpha1 and alpha2.
for i,error in enumerate(self._errors[1, :]):
self._errors[1, i] = error + (alpha2_new - alpha2)*y2*self.kernel(self._data[i2], self._data[int(self._errors[0, i])]) + (alpha1_new - alpha1)*y1*self.kernel(self._data[i1], self._data[int(self._errors[0, i])]) - self._b + b_new
#Storing the new values of alpha1 and alpha2:
self._alphas[0, i1] = alpha1_new
self._alphas[0, i2] = alpha2_new
self._b = b_new
print(self._errors)
return 1
def examineExample(self, i2):
i2 = int(i2)
y2 = self._label[i2]
alpha2 = self._alphas[0, i2]
if alpha2 > 0 and alpha2 < self._C:
position = 0
for i, elt in enumerate(self._errors[0, :]):
if elt == i2:
position = i
E2 = self._errors[1, position]
else:
E2 = self.evaluate(self._data[i2]) - y2
r2 = E2*y2
if (r2< -self._tol and alpha2 < self._C) or (r2 > self._tol and alpha2 > 0):
n = numpy.shape(self._errors)[1]
if n > 1:
i1 = 0
if E2 > 0:
min = self._errors[1, 0]
position = 0
for l, elt in enumerate(self._errors[1, :]):
if elt < min:
min = elt
position = l
i1 = self._errors[0, position]
else:
max = self._errors[1, 0]
position = 0
for l, elt in enumerate(self._errors[1, :]):
if elt > max:
max = elt
position = l
i1 = self._errors[0, position]
if self.update(i1, i2, E2):
return 1
#loop over all non bound examples starting at a random point.
list_index = [i for i in range(n)]
numpy.random.shuffle(list_index)
for i in list_index:
i1 = self._errors[0, i]
if self.update(i1, i2, E2):
return 1
#Loop over all the training examples, starting at a random point.
list_bound = [i for i in range(self._N) if not numpy.any(self._errors[0, :] == i)]
numpy.random.shuffle(list_bound)
for i in list_bound:
i1 = i
if self.update(i1, i2, E2):
return 1
return 0
def SMO(self):
numChanged = 0
examineAll = 1
cpt = 1
while(numChanged > 0 or examineAll):
numChanged = 0
if examineAll == 1:
for i in range(self._N):
numChanged += self.examineExample(i)
else:
for i in self._errors[0, :]:
numChanged += self.examineExample(i)
if examineAll == 1:
examineAll = 0
elif numChanged == 0:
examineAll = 1
cpt += 1
def load_training_data(a, b):
train = gzip.open("train-images-idx3-ubyte.gz", "rb")
labels = gzip.open("train-labels-idx1-ubyte.gz", "rb")
train.read(4)
labels.read(4)
number_images = train.read(4)
number_images = struct.unpack(">I", number_images)[0]
rows = train.read(4)
rows = struct.unpack(">I", rows)[0]
cols = train.read(4)
cols = struct.unpack(">I", cols)[0]
number_labels = labels.read(4)
number_labels = struct.unpack(">I", number_labels)[0]
image_list = []
label_list = []
if number_images != number_labels:
raise Exception("The number of labels doesn't match with the number of images")
else:
for l in range(number_labels):
if l % 1000 == 0:
print("l:{}".format(l))
mat = numpy.zeros((rows, cols), dtype = numpy.uint8)
for i in range(rows):
for j in range(cols):
pixel = train.read(1)
pixel = struct.unpack(">B", pixel)[0]
mat[i][j] = pixel
image_list += [mat]
lab = labels.read(1)
lab = struct.unpack(">B", lab)[0]
label_list += [lab]
train.close()
labels.close()
i = 0
index_a = []
index_b = []
while i < number_labels:
if label_list[i] == a:
index_a += [i]
elif label_list[i] == b:
index_b += [i]
i += 1
image_list = [m for i,m in enumerate(image_list) if (i in index_a) | (i in index_b)]
mean = (a+b)/2
label_list = [ numpy.sign(m - mean) for l,m in enumerate(label_list) if l in index_a+index_b]
return ([image_list, label_list])
def load_test_data():
test = gzip.open("t10k-images-idx3-ubyte.gz", "rb")
labels = gzip.open("t10k-labels-idx1-ubyte.gz", "rb")
test.read(4)
labels.read(4)
number_images = test.read(4)
number_images = struct.unpack(">I", number_images)[0]
rows = test.read(4)
rows = struct.unpack(">I", rows)[0]
cols = test.read(4)
cols = struct.unpack(">I", cols)[0]
number_labels = labels.read(4)
number_labels = struct.unpack(">I", number_labels)[0]
image_list = []
label_list = []
if number_images != number_labels:
raise Exception("The number of labels doesn't match with the number of images")
else:
for l in range(number_labels):
if l % 1000 == 0:
print("l:{}".format(l))
mat = numpy.zeros((rows, cols), dtype = numpy.uint8)
for i in range(rows):
for j in range(cols):
pixel = test.read(1)
pixel = struct.unpack(">B", pixel)[0]
mat[i][j] = pixel
image_list += [mat]
lab = labels.read(1)
lab = struct.unpack(">B", lab)[0]
label_list += [lab]
test.close()
labels.close()
return ([image_list, label_list])
data = load_training_data(0, 7)
images_training = data[0]
labels_training = data[1]
svm = SVM(0.1, images_training[0:200], labels_training[0:200])
svm.SMO()
def view(image, label=""):
print("Number : {}".format(label))
pylab.imshow(image, cmap = pylab.cm.gray)
pylab.show()
First, SMO is a fairly complicated algorithm - it is not one easy to debug in this kind of format.
Second, you are starting too high up in your testing. Some advice to help you debug your problems.
1) First, switch to using the linear kernel. Its much easier for you to compute the exact linear solution with another algorithm and compare what you are getting with the exact solution. This way its only the weight vectors and bias term. If you stay in the dual space, you'll have to compare all the coefficients and make sure things stay in the same order.
2) Start with a much simpler 2D problem where you know what the general solution should look like. You can then visualize the solution, and watch as it changes at each step - this can be a visual tool to help you find where something goes wrong.
One important thing is you said this:
b1 = E1 + y1*(alpha1_new - alpha1)*K11 + y2*(alpha2_new - alpha2)*K12 + self._b
b2 = E2 + y1*(alpha1_new - alpha1)*K12 + y2*(alpha2_new - alpha2)*K22 + self._b
Basically you're just adding to b every time with this code. Your b's should look more like this:
b1 = smo.b - E1 - y1 * (a1 - alpha1) * smo.K[i1, i1] - y2 * (a2 - alpha2) * smo.K[i1, i2]
b2 = smo.b - E2 - y1 * (a1 - alpha1) * smo.K[i1, i2] - y2 * (a2 - alpha2) * smo.K[i2, i2]
This version is not perfect, but I recommend checking apex51's version on Github for pointers:
SVM-and-sequential-minimal-optimization
The mathematical basis in the notes are very strong (despite some minor discrepancies with Platt's paper) and the code is not perfect, but a good direction for you. I would also suggest looking at other, completed SMOs and trying to tweak that code to math your needs instead of writing from scratch.
If I have 2 numbers in binary form as a string, and I want to add them I will do it digit by digit, from the right most end. So 001 + 010 = 011
But suppose I have to do 001+001, how should I create a code to figure out how to take carry over responses?
bin and int are very useful here:
a = '001'
b = '011'
c = bin(int(a,2) + int(b,2))
# 0b100
int allows you to specify what base the first argument is in when converting from a string (in this case two), and bin converts a number back to a binary string.
This accepts an arbitrary number or arguments:
>>> def bin_add(*bin_nums: str) -> str:
... return bin(sum(int(x, 2) for x in bin_nums))[2:]
...
>>> x = bin_add('1', '10', '100')
>>> x
'111'
>>> int(x, base = 2)
7
Here's an easy to understand version
def binAdd(s1, s2):
if not s1 or not s2:
return ''
maxlen = max(len(s1), len(s2))
s1 = s1.zfill(maxlen)
s2 = s2.zfill(maxlen)
result = ''
carry = 0
i = maxlen - 1
while(i >= 0):
s = int(s1[i]) + int(s2[i])
if s == 2: #1+1
if carry == 0:
carry = 1
result = "%s%s" % (result, '0')
else:
result = "%s%s" % (result, '1')
elif s == 1: # 1+0
if carry == 1:
result = "%s%s" % (result, '0')
else:
result = "%s%s" % (result, '1')
else: # 0+0
if carry == 1:
result = "%s%s" % (result, '1')
carry = 0
else:
result = "%s%s" % (result, '0')
i = i - 1;
if carry>0:
result = "%s%s" % (result, '1')
return result[::-1]
Can be simple if you parse the strings by int (shown in the other answer). Here is a kindergarten-school-math way:
>>> def add(x,y):
maxlen = max(len(x), len(y))
#Normalize lengths
x = x.zfill(maxlen)
y = y.zfill(maxlen)
result = ''
carry = 0
for i in range(maxlen-1, -1, -1):
r = carry
r += 1 if x[i] == '1' else 0
r += 1 if y[i] == '1' else 0
# r can be 0,1,2,3 (carry + x[i] + y[i])
# and among these, for r==1 and r==3 you will have result bit = 1
# for r==2 and r==3 you will have carry = 1
result = ('1' if r % 2 == 1 else '0') + result
carry = 0 if r < 2 else 1
if carry !=0 : result = '1' + result
return result.zfill(maxlen)
>>> add('1','111')
'1000'
>>> add('111','111')
'1110'
>>> add('111','1000')
'1111'
It works both ways
# as strings
a = "0b001"
b = "0b010"
c = bin(int(a, 2) + int(b, 2))
# as binary numbers
a = 0b001
b = 0b010
c = bin(a + b)
you can use this function I did:
def addBinary(self, a, b):
"""
:type a: str
:type b: str
:rtype: str
"""
#a = int('10110', 2) #(0*2** 0)+(1*2**1)+(1*2**2)+(0*2**3)+(1*2**4) = 22
#b = int('1011', 2) #(1*2** 0)+(1*2**1)+(0*2**2)+(1*2**3) = 11
sum = int(a, 2) + int(b, 2)
if sum == 0: return "0"
out = []
while sum > 0:
res = int(sum) % 2
out.insert(0, str(res))
sum = sum/2
return ''.join(out)
def addBinary(self, A, B):
min_len, res, carry, i, j = min(len(A), len(B)), '', 0, len(A) - 1, len(B) - 1
while i>=0 and j>=0:
r = carry
r += 1 if A[i] == '1' else 0
r += 1 if B[j] == '1' else 0
res = ('1' if r % 2 == 1 else '0') + res
carry = 0 if r < 2 else 1
i -= 1
j -= 1
while i>=0:
r = carry
r += 1 if A[i] == '1' else 0
res = ('1' if r % 2 == 1 else '0') + res
carry = 0 if r < 2 else 1
i -= 1
while j>=0:
r = carry
r += 1 if B[j] == '1' else 0
res = ('1' if r % 2 == 1 else '0') + res
carry = 0 if r < 2 else 1
j -= 1
if carry == 1:
return '1' + res
return res
#addition of two binary string without using 'bin' inbuilt function
numb1 = input('enter the 1st binary number')
numb2 = input("enter the 2nd binary number")
list1 = []
carry = '0'
maxlen = max(len(numb1), len(numb2))
x = numb1.zfill(maxlen)
y = numb2.zfill(maxlen)
for j in range(maxlen-1,-1,-1):
d1 = x[j]
d2 = y[j]
if d1 == '0' and d2 =='0' and carry =='0':
list1.append('0')
carry = '0'
elif d1 == '1' and d2 =='1' and carry =='1':
list1.append('1')
carry = '1'
elif (d1 == '1' and d2 =='0' and carry =='0') or (d1 == '0' and d2 =='1' and
carry =='0') or (d1 == '0' and d2 =='0' and carry =='1'):
list1.append('1')
carry = '0'
elif d1 == '1' and d2 =='1' and carry =='0':
list1.append('0')
carry = '1'
else:
list1.append('0')
if carry == '1':
list1.append('1')
addition = ''.join(list1[::-1])
print(addition)
Not an optimal solution but a working one without use of any inbuilt functions.
# two approaches
# first - binary to decimal conversion, add and then decimal to binary conversion
# second - binary addition normally
# binary addition - optimal approach
# rules
# 1 + 0 = 1
# 1 + 1 = 0 (carry - 1)
# 1 + 1 + 1(carry) = 1 (carry -1)
aa = a
bb = b
len_a = len(aa)
len_b = len(bb)
min_len = min(len_a, len_b)
carry = 0
arr = []
while min_len > 0:
last_digit_aa = int(aa[len(aa)-1])
last_digit_bb = int(bb[len(bb)-1])
add_digits = last_digit_aa + last_digit_bb + carry
carry = 0
if add_digits == 2:
add_digits = 0
carry = 1
if add_digits == 3:
add_digits = 1
carry = 1
arr.append(add_digits) # will rev this at the very end for output
aa = aa[:-1]
bb = bb[:-1]
min_len -= 1
a_len_after = len(aa)
b_len_after = len(bb)
if a_len_after > 0:
while a_len_after > 0:
while carry == 1:
if len(aa) > 0:
sum_digit = int(aa[len(aa) - 1]) + carry
if sum_digit == 2:
sum_digit = 0
carry = 1
arr.append(sum_digit)
aa = aa[:-1]
else:
carry = 0
arr.append(sum_digit)
aa = aa[:-1]
else:
arr.append(carry)
carry = 0
if carry == 0 and len(aa) > 0:
arr.append(aa[len(aa) - 1])
aa = aa[:-1]
a_len_after -= 1
if b_len_after > 0:
while b_len_after > 0:
while carry == 1:
if len(bb) > 0:
sum_digit = int(bb[len(bb) - 1]) + carry
if sum_digit == 2:
sum_digit = 0
carry = 1
arr.append(sum_digit)
bb = bb[:-1]
else:
carry = 0
arr.append(sum_digit)
bb = bb[:-1]
else:
arr.append(carry)
carry = 0
if carry == 0 and len(bb) > 0:
arr.append(bb[len(bb) - 1])
bb = bb[:-1]
b_len_after -= 1
if carry == 1:
arr.append(carry)
out_arr = reversed(arr)
out_str = "".join(str(x) for x in out_arr)
return out_str
I have a little problem with Python.
I'm try to write an application for DCM standard who some slice and draw the final model.
This is my code:
from lar import *
from scipy import *
import scipy
import numpy as np
from time import time
from pngstack2array3d import pngstack2array3d
colors = 2
theColors = []
DEBUG = False
MAX_CHAINS = colors
# It is VERY important that the below parameter values
# correspond exactly to each other !!
# ------------------------------------------------------------
MAX_CHUNKS = 75
imageHeight, imageWidth = 250,250 # Dx, Dy
# configuration parameters
# ------------------------------------------------------------
beginImageStack = 430
endImage = beginImageStack
nx = ny = 50
imageDx = imageDy = 50
count = 0
# ------------------------------------------------------------
# Utility toolbox
# ------------------------------------------------------------
def ind(x,y): return x + (nx+1) * (y + (ny+1) )
def invertIndex(nx,ny):
nx,ny = nx+1,ny+1
def invertIndex0(offset):
a0, b0 = offset / nx, offset % nx
a1, b1 = a0 / ny, a0 % ny
return b0,b1
return invertIndex0
def invertPiece(nx,ny):
def invertIndex0(offset):
a0, b0 = offset / nx, offset % nx
a1, b1 = a0 / ny, a0 % ny
return b0,b1
return invertIndex0
# ------------------------------------------------------------
# computation of d-chain generators (d-cells)
# ------------------------------------------------------------
# cubic cell complex
# ------------------------------------------------------------
def the3Dcell(coords):
x,y= coords
return [ind(x,y),ind(x+1,y),ind(x,y+1),ind(x+1,y+1)]
# construction of vertex coordinates (nx * ny )
# ------------------------------------------------------------
V = [[x,y] for y in range(ny+1) for x in range(nx+1) ]
if __name__=="__main__" and DEBUG == True:
print "\nV =", V
# construction of CV relation (nx * ny)
# ------------------------------------------------------------
CV = [the3Dcell([x,y]) for y in range(ny) for x in range(nx)]
if __name__=="__main__" and DEBUG == True:
print "\nCV =", CV
#hpc = EXPLODE(1.2,1.2,1.2)(MKPOLS((V,CV[:500]+CV[-500:])))
#box = SKELETON(1)(BOX([1,2,3])(hpc))
#VIEW(STRUCT([box,hpc]))
# construction of FV relation (nx * ny )
# ------------------------------------------------------------
FV = []
v2coords = invertIndex(nx,ny)
for h in range(len(V)):
x,y= v2coords(h)
if (x < nx) and (y < ny): FV.append([h,ind(x+1,y),ind(x,y+1),ind(x+1,y+1)])
if __name__=="__main__" and DEBUG == True:
print "\nFV =",FV
#hpc = EXPLODE(1.2,1.2,1.2)(MKPOLS((V,FV[:500]+FV[-500:])))
#box = SKELETON(1)(BOX([1,2,3])(hpc))
#VIEW(STRUCT([box,hpc]))
# construction of EV relation (nx * ny )
# ------------------------------------------------------------
EV = []
v2coords = invertIndex(nx,ny)
for h in range(len(V)):
x,y = v2coords(h)
if x < nx: EV.append([h,ind(x+1,y)])
if y < ny: EV.append([h,ind(x,y+1)])
if __name__=="__main__" and DEBUG == True:
print "\nEV =",EV
#hpc = EXPLODE(1.2,1.2,1.2)(MKPOLS((V,EV[:500]+EV[-500:])))
#box = SKELETON(1)(BOX([1,2,3])(hpc))
#VIEW(STRUCT([box,hpc]))
# ------------------------------------------------------------
# computation of boundary operators (∂3 and ∂2s)
# ------------------------------------------------------------
"""
# computation of the 2D boundary complex of the image space
# ------------------------------------------------------------
Fx0V, Ex0V = [],[] # x == 0
Fx1V, Ex1V = [],[] # x == nx-1
Fy0V, Ey0V = [],[] # y == 0
Fy1V, Ey1V = [],[] # y == ny-1
v2coords = invertIndex(nx,ny)
for h in range(len(V)):
x,y = v2coords(h)
if (y == 0):
if x < nx: Ey0V.append([h,ind(x+1,y)])
if (x < nx):
Fy0V.append([h,ind(x+1,y),ind(x,y)])
elif (y == ny):
if x < nx: Ey1V.append([h,ind(x+1,y)])
if (x < nx):
Fy1V.append([h,ind(x+1,y),ind(x,y)])
if (x == 0):
if y < ny: Ex0V.append([h,ind(x,y+1)])
if (y < ny):
Fx0V.append([h,ind(x,y+1),ind(x,y)])
elif (x == nx):
if y < ny: Ex1V.append([h,ind(x,y+1)])
if (y < ny):
Fx1V.append([h,ind(x,y+1),ind(x,y)])
FbV = Fy0V+Fy1V+Fx0V+Fx1V
EbV = Ey0V+Ey1V+Ex0V+Ex1V
"""
"""
if __name__=="__main__" and DEBUG == True:
hpc = EXPLODE(1.2,1.2,1.2)(MKPOLS((V,FbV)))
VIEW(hpc)
hpc = EXPLODE(1.2,1.2,1.2)(MKPOLS((V,EbV)))
VIEW(hpc)
"""
# computation of the ∂2 operator on the boundary space
# ------------------------------------------------------------
print "start partial_2_b computation"
#partial_2_b = larBoundary(EbV,FbV)
print "end partial_2_b computation"
# computation of ∂3 operator on the image space
# ------------------------------------------------------------
print "start partial_3 computation"
partial_3 = larBoundary(FV,CV)
print "end partial_3 computation"
# ------------------------------------------------------------
# input from volume image (test: 250 x 250 x 250)
# ------------------------------------------------------------
out = []
Nx,Ny = imageHeight/imageDx, imageWidth/imageDx
segFaces = set(["Fy0V","Fy1V","Fx0V","Fx1V"])
for inputIteration in range(imageWidth/imageDx):
startImage = endImage
endImage = startImage + imageDy
xEnd, yEnd = 0,0
theImage,colors,theColors = pngstack2array3d('SLICES2/', startImage, endImage, colors)
print "\ntheColors =",theColors
theColors = theColors.reshape(1,2)
background = max(theColors[0])
foreground = min(theColors[0])
print "\n(background,foreground) =",(background,foreground)
if __name__=="__main__" and DEBUG == True:
print "\nstartImage, endImage =", (startImage, endImage)
for i in range(imageHeight/imageDx):
for j in range(imageWidth/imageDy):
xStart, yStart = i * imageDx, j * imageDy
xEnd, yEnd = xStart+imageDx, yStart+imageDy
image = theImage[:, xStart:xEnd, yStart:yEnd]
nx,ny = image.shape
if __name__=="__main__" and DEBUG == True:
print "\n\tsubimage count =",count
print "\txStart, yStart =", (xStart, yStart)
print "\txEnd, yEnd =", (xEnd, yEnd)
print "\timage.shape",image.shape
# ------------------------------------------------------------
# image elaboration (chunck: 50 x 50)
# ------------------------------------------------------------
"""
# Computation of (local) boundary to be removed by pieces
# ------------------------------------------------------------
if pieceCoords[0] == 0: boundaryPlanes += ["Fx0V"]
elif pieceCoords[0] == Nx-1: boundaryPlanes += ["Fx1V"]
if pieceCoords[1] == 0: boundaryPlanes += ["Fy0V"]
elif pieceCoords[1] == Ny-1: boundaryPlanes += ["Fy1V"]
"""
#if __name__=="__main__" and DEBUG == True:
#planesToRemove = list(segFaces.difference(boundaryPlanes))
#FVtoRemove = CAT(map(eval,planesToRemove))
count += 1
# compute a quotient complex of chains with constant field
# ------------------------------------------------------------
chains2D = [[] for k in range(colors)]
def addr(x,y): return x + (nx) * (y + (ny))
for x in range(nx):
for y in range(ny):
if (image[x,y] == background):
chains2D[1].append(addr(x,y))
else:
chains2D[0].append(addr(x,y))
#if __name__=="__main__" and DEBUG == True:
#print "\nchains3D =\n", chains3D
# compute the boundary complex of the quotient cell
# ------------------------------------------------------------
objectBoundaryChain = larBoundaryChain(partial_3,chains2D[1])
b2cells = csrChainToCellList(objectBoundaryChain)
sup_cell_boundary = MKPOLS((V,[FV[f] for f in b2cells]))
# remove the (local) boundary (shared with the piece boundary) from the quotient cell
# ------------------------------------------------------------
"""
cellIntersection = matrixProduct(csrCreate([FV[f] for f in b2cells]),csrCreate(FVtoRemove).T)
#print "\ncellIntersection =", cellIntersection
cooCellInt = cellIntersection.tocoo()
b2cells = [cooCellInt.row[k] for k,val in enumerate(cooCellInt.data) if val >= 4]
"""
# ------------------------------------------------------------
# visualize the generated model
# ------------------------------------------------------------
print "xStart, yStart =", xStart, yStart
if __name__=="__main__":
sup_cell_boundary = MKPOLS((V,[FV[f] for f in b2cells]))
if sup_cell_boundary != []:
out += [T([1,2])([xStart,yStart]) (STRUCT(sup_cell_boundary))]
if count == MAX_CHUNKS:
VIEW(STRUCT(out))
# ------------------------------------------------------------
# interrupt the cycle of image elaboration
# ------------------------------------------------------------
if count == MAX_CHUNKS: break
if count == MAX_CHUNKS: break
if count == MAX_CHUNKS: break
And this is the error take from the terminal :
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-4-2e498c6090a0> in <module>()
213
214 image = theImage[:, xStart:xEnd, yStart:yEnd]
--> 215 nx,ny = image.shape
216
217 if __name__=="__main__" and DEBUG == True:
ValueError: too many values to unpack
Someone can help me to solve this issue????
Based on the line:
image = theImage[:, xStart:xEnd, yStart:yEnd]
image is a 3d array, not a 2d array (it appears to be multiple slices of an image), with the 2nd and 3rd dimensions representing x and y respectively. Thus, if you want to get its dimensions you'll need to unpack it into three dimensions, something like:
nslice, nx, ny = image.shape