We Keep Coding

Genetic Algorithm Elitism Python

I'm trying to do the elitism method to get the best fitness value of each of the generations I generate, keeping beyond the fitness the values ​​of X and Y to be an individual of the next generation, however, I can't apply a logic using dict that Solve the problem. It remains to get this detail right to be able to finalize the complete implementation and carry out the general revisions.
import random
def generate_population(size, x_boundaries, y_boundaries):
lower_x_boundary, upper_x_boundary = x_boundaries
lower_y_boundary, upper_y_boundary = y_boundaries
population = []
for i in range(size):
individual = {
'x': random.uniform(lower_x_boundary, upper_x_boundary),
'y': random.uniform(lower_y_boundary, upper_y_boundary),
}
population.append(individual)
return population
def fitness(individual):
x = individual['x']
y = individual['y']
return abs((-(100*(x*x - y)*(x*x - y) + (1 - x)*(1-x))))
def sort_population_by_fitness(population):
return sorted(population, key=fitness)
def choice_by_roulette(sorted_population, fitness_sum):
drawn = random.uniform(0, 1)
accumulated = 0
for individual in sorted_population:
fitnessX = fitness(individual)
probability = fitnessX / fitness_sum
accumulated += probability
if drawn <= accumulated:
return individual
def crossover(choice_a, choice_b):
xa = choice_a['x']
ya = choice_a['y']
xb = choice_b['x']
yb = choice_b['y']
#xa = xa*xb
#xa = xa**0.5
#ya = ya*yb
#ya = ya**0.5
return {'x': xa+0.01, 'y': ya+0.01}
def mutate(new_individual):
x = new_individual['x']
y = new_individual['y']
flagx = 0
flagy = 0
new_x = x*(1+random.uniform(-0.01/2, 0.01/2))
new_y = y*(1+random.uniform(-0.01/2, 0.01/2))
while flagx == 1:
if (new_x > 2) or (new_x < -2):
new_x = x*(1+random.uniform(-0.01/2, 0.01/2))
flagx = 1
else:
flagx = 0
while flagy == 1:
if (new_y > 2) or (new_y < -2):
new_y = y*(1+random.uniform(-0.01/2, 0.01/2))
flagy = 1
else:
flagy = 0
return {'x': new_x, 'y': new_y}
def eletism(x_gen, milior):
pior = sort_population_by_fitness(x_gen)
fitness(pior)
print(pior)
#for i in x_gen:
#print(teste['x'])
#x = teste['x']
#y = teste['y']
#print(milior)
return pior
def make_next_gen(population):
next_gen = []
sorted_population = sort_population_by_fitness(population)
soma_fitness = sum(fitness(individual)for individual in population)
for i in range(9):
first_choice = choice_by_roulette(sorted_population, soma_fitness)
second_choice = choice_by_roulette(sorted_population, soma_fitness)
new_individual = crossover(first_choice, second_choice)
drawn = random.randint(1,5)
if drawn == 1:
new_individual = mutate(new_individual)
next_gen.append(new_individual)
return next_gen
generations = 100
population = generate_population(size=10, x_boundaries=(-2, 2), y_boundaries=(-2, 2))
i = 0
while i!= generations:
for individual in population:
print(individual, fitness(individual))
population = make_next_gen(population)
i += 1
best_individual = sort_population_by_fitness(population)[-1]
print(best_individual, fitness(best_individual))

N Puzzle with Depth First Search

I'm trying solve N Puzzle with Depth First Search using python 3.
With 3 x 3 puzzle it run good and fast but with 4 x 4 puzzle, it runs too slow and can't find solution with error: "MemoryError".
I also use "h(n) = depth + number of wrong tiles" to evaluate priority of each node.
I'm a newbie to python so hope you can help me with this
Here is my code:
import sys
import getopt
import random
import time
class State:
def __init__(self, parent, board, move, depth):
self.parent = parent
self.previousMove = move
self.board = board
self.map = ''.join(str(e) for e in board)
self.depth = depth
self.cost = self.calculateCost()
def calculateCost(self):
pos = 1
count = 0
for tile in self.board:
if tile == pos:
count += 1
pos += 1
return self.depth + 8 - count
class Puzzle:
def __init__(self, k, customBoard = None):
self.k = k
self.n = k*k - 1
self.sizeOfBoard = k*k
self.timeOfSolving = 0
self.timeOfGenerateSuccessors = 0
self.maxDeepSearch = 0
self.inititalState = State(None, self.createInitialBoard(customBoard), 'Start', 0)
self.goalBoard = self.createGoalBoard()
self.finalState = None
self.stateStorage = set() # Store states that have visited
self.path = [] # Store states that lead to goalstate
self.stack = []
def isSolvable(self, board):
# count invertion in puzzle's board
invCount = 0
for i in range(0, self.sizeOfBoard - 1):
if board[i] == 0:
continue
for j in range(i+1, self.sizeOfBoard):
if board[j] == 0:
continue
if board[i] > board[j]:
invCount += 1
# print(invCount)
if (invCount % 2 == 0):
return True
return False
def createInitialBoard(self, customBoard):
print("Creating initial state")
if customBoard is None:
board = []
lstAddSuccess = []
while 1:
board.clear()
lstAddSuccess.clear()
for count in range(0, self.k*self.k):
newTile = random.randint(0, self.n)
while newTile in lstAddSuccess:
newTile = random.randint(0, self.n)
lstAddSuccess += [newTile]
board += [newTile]
if self.isSolvable(board):
break
else:
board = [int(e) for e in customBoard]
if not self.isSolvable(board):
print("Cant find solution with this puzzle! Exiting...")
exit(-1)
return board
def createGoalBoard(self):
board = []
for count in range(1, self.n + 1):
board += [count]
board += [0]
return board
def printBoard(self, board):
for row in range(0, self.sizeOfBoard, self.k):
# for col in range(row, row + self.k):
print(board[row:row + self.k])
def generateSuccessors(self, currentState):
indexOfZero = currentState.board.index(0)
rowIndexOfZero = indexOfZero % self.k
colIndexOfZero = indexOfZero // self.k
lstSuccessors = []
# Slide to zero to up
if colIndexOfZero != 0:
newState = currentState.board.copy()
newState[indexOfZero] = newState[indexOfZero - self.k]
newState[indexOfZero - self.k] = 0
lstSuccessors.append(
State(currentState, newState, 'up', currentState.depth + 1))
# Slide zero to down
if colIndexOfZero != self.k - 1:
newState = currentState.board.copy()
newState[indexOfZero] = newState[indexOfZero + self.k]
newState[indexOfZero + self.k] = 0
lstSuccessors.append(
State(currentState, newState, 'down', currentState.depth + 1))
# slide zero to left
if rowIndexOfZero != 0:
newState = currentState.board.copy()
newState[indexOfZero] = newState[indexOfZero - 1]
newState[indexOfZero - 1] = 0
lstSuccessors.append(
State(currentState, newState, 'left', currentState.depth + 1))
# Slide zero to right
if rowIndexOfZero != self.k - 1:
newState = currentState.board.copy()
newState[indexOfZero] = newState[indexOfZero + 1]
newState[indexOfZero + 1] = 0
lstSuccessors.append(
State(currentState, newState, 'right', currentState.depth + 1))
lstSuccessorsCost = [ele.cost for ele in lstSuccessors]
lstSuccessorsInOrderOfCost = []
for i in range(0, len(lstSuccessorsCost)):
lstSuccessorsInOrderOfCost.append(lstSuccessors[lstSuccessorsCost.index(min(lstSuccessorsCost))])
lstSuccessorsCost[lstSuccessorsCost.index(min(lstSuccessorsCost))] = 100
return lstSuccessorsInOrderOfCost
def solvePuzzle(self, currentState):
self.stack.append(currentState)
self.stateStorage.add(currentState.map)
while len(self.stack) > 0:
currentState = self.stack.pop()
if currentState.board == self.goalBoard:
# find path
# self.printBoard(currentState.board)
self.finalState = currentState
print("Solving " + str(self.n) + " puzzle done!")
return
start_time_gen = time.time()
lstSuccessor = self.generateSuccessors(currentState)
end_time_gen = time.time()
timeOfGen = end_time_gen - start_time_gen
self.timeOfGenerateSuccessors += timeOfGen
for successor in lstSuccessor[::-1]:
if successor.map not in self.stateStorage:
self.stack.append(successor)
self.stateStorage.add(successor.map)
if successor.depth > self.maxDeepSearch:
self.maxDeepSearch += 1
print("Cant solve puzzle! Exiting...")
exit(-1)
def solve(self):
start_time = time.time()
self.solvePuzzle(self.inititalState)
end_time = time.time()
self.timeOfSolving = end_time - start_time
print("Running time: " + str(self.timeOfSolving))
print("Max Search Dept: " + str(self.maxDeepSearch))
print("Final State Dept: " + str(self.finalState.depth))
def printInitialBoard(self):
self.printBoard(self.inititalState.board)
def printPath(self):
if self.finalState is None:
print("No solution found!")
return
path = []
state = self.finalState
while (state is not None):
if state.previousMove is not None:
path.append(state.previousMove)
state = state.parent
print("path: "),
print(path[::-1])
def main(argv):
# if (len(argv) != 1 or int(argv[0]) not in range(1, 10000)):
# print("Input must be k of integer, which is k*k matrix of puzzle")
# exit()
# eight_puzzle = Puzzle(int(argv[0]))
k = int(input("Enter size of k * k puzzle, k = "))
while k not in range(2, 100):
print("k must be in range 2 - 100")
k = int(input("Enter size of k * k puzzle, k = "))
print("""
Choose:
1. Randome puzzle
2. Custome puzzle
""")
file = input()
if int(file) == 1:
puzzle = Puzzle(k)
elif int(file) == 2:
board = input("Enter puzzle: ")
puzzle = Puzzle(k ,list(board.split(" ")))
puzzle.printInitialBoard()
puzzle.solve()
puzzle.printPath()
if __name__ == "__main__":
main(sys.argv[1:])

knapsack branch and bound wrong result

I have converted the code given at this link into a python version. The code is supposed to calculate the correct value of maximum value to be filled in knapsack of weight W. I have attached the code below:
#http://www.geeksforgeeks.org/branch-and-bound-set-2-implementation-of-01-knapsack/
from queue import Queue
class Node:
def __init__(self):
self.level = None
self.profit = None
self.bound = None
self.weight = None
def __str__(self):
return "Level: %s Profit: %s Bound: %s Weight: %s" % (self.level, self.profit, self.bound, self.weight)
def bound(node, n, W, items):
if(node.weight >= W):
return 0
profit_bound = int(node.profit)
j = node.level + 1
totweight = int(node.weight)
while ((j < n) and (totweight + items[j].weight) <= W):
totweight += items[j].weight
profit_bound += items[j].value
j += 1
if(j < n):
profit_bound += (W - totweight) * items[j].value / float(items[j].weight)
return profit_bound
Q = Queue()
def KnapSackBranchNBound(weight, items, total_items):
items = sorted(items, key=lambda x: x.value/float(x.weight), reverse=True)
u = Node()
v = Node()
u.level = -1
u.profit = 0
u.weight = 0
Q.put(u)
maxProfit = 0;
while not Q.empty():
u = Q.get()
if u.level == -1:
v.level = 0
if u.level == total_items - 1:
continue
v.level = u.level + 1
v.weight = u.weight + items[v.level].weight
v.profit = u.profit + items[v.level].value
if (v.weight <= weight and v.profit > maxProfit):
maxProfit = v.profit;
v.bound = bound(v, total_items, weight, items)
if (v.bound > maxProfit):
Q.put(v)
v.weight = u.weight
v.profit = u.profit
v.bound = bound(v, total_items, weight, items)
if (v.bound > maxProfit):
# print items[v.level]
Q.put(v)
return maxProfit
if __name__ == "__main__":
from collections import namedtuple
Item = namedtuple("Item", ['index', 'value', 'weight'])
input_data = open("test.data").read()
lines = input_data.split('\n')
firstLine = lines[0].split()
item_count = int(firstLine[0])
capacity = int(firstLine[1])
print "running from main"
items = []
for i in range(1, item_count+1):
line = lines[i]
parts = line.split()
items.append(Item(i-1, int(parts[0]), float(parts[1])))
kbb = KnapSackBranchNBound(capacity, items, item_count)
print kbb
The program is supposed to calculate value of 235 for following items inside file test.data:
5 10
40 2
50 3.14
100 1.98
95 5
30 3
The first line shows number of items and knapsack weight. Lines below first line shows the value and weight of those items. Items are made using a namedtuple and sorted according to value/weight. For this problem I am getting 135 instead of 235. What am I doing wrong here?
EDIT:
I have solved the problem of finding correct items based on branch and bound. If needed, one can check it here

The problem is that you're inserting multiple references to the same Node() object into your queue. The fix is to initialize two new v objects in each iteration of the while-loop as follows:
while not Q.empty():
u = Q.get()
v = Node() # Added line
if u.level == -1:
v.level = 0
if u.level == total_items - 1:
continue
v.level = u.level + 1
v.weight = u.weight + items[v.level].weight
v.profit = u.profit + items[v.level].value
if (v.weight <= weight and v.profit > maxProfit):
maxProfit = v.profit;
v.bound = bound(v, total_items, weight, items)
if (v.bound > maxProfit):
Q.put(v)
v = Node() # Added line
v.level = u.level + 1 # Added line
v.weight = u.weight
v.profit = u.profit
v.bound = bound(v, total_items, weight, items)
if (v.bound > maxProfit):
# print(items[v.level])
Q.put(v)
Without these reinitializations, you're modifying the v object that you already inserted into the queue.
This is different from C++ where the Node objects are values that are implicitly copied into the queue to avoid aliasing problems such as these.

SVM: problems with SMO algorithm

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.

Genetic algorithm suspends in python?

I have implemented a simple genetic algorithm in python - here is the most of the code:
import random
ings = (('w1', 200, 25, 80),
('su1', 50, 55, 150),
('su2', 400, 100, 203),
('sy1', 10, 150, 355),
('sy2', 123, 88, 101),
('sy3', 225, 5, 30),
('sy4', 1, 44, 99),
('sy5', 500, 220, 300))
mutationRate = 0.2
crossoverRate = 0.9
iterations = 100
file = open('D:\\logfile2.txt', 'a')
class Ingredient:
def __init__(self, n, p, mi, ma):
self.name = n
self.price = p
self.min = mi
self.max = ma
self.perc = random.randrange(self.min, self.max)
class Drink:
def __init__(self):
self.ing = [Ingredient(*x) for x in ings]
self.normalize()
self.fitness = self.evaluate()
def normalize(self):
sum = 0
for x in self.ing:
sum += x.perc
if sum < 1000:
offset = 1000 - sum
while not offset == 0:
index = random.randrange(len(self.ing))
val = self.ing[index].max - self.ing[index].perc
threshold = random.randrange(val) if val > 0 else 0
threshold = threshold if threshold < offset else offset
self.ing[index].perc += threshold
offset -= threshold
if sum > 1000:
offset = sum - 1000
while not offset == 0:
index = random.randrange(len(self.ing))
val = self.ing[index].perc - self.ing[index].min
threshold = random.randrange(val) if val > 0 else 0
threshold = threshold if threshold < offset else offset
self.ing[index].perc -= threshold
offset -= threshold
def evaluate(self):
fitness = 0
for x in self.ing:
fitness += x.perc * x.price
return 300000 - fitness
class GeneticAlgorithm:
def __init__(self):
self.drinkList = [Drink() for x in range(8)]
self.pool = []
def mutate(self, index):
ing1, ing2 = random.randrange(8), random.randrange(8)
while ing1 == ing2:
ing2 = random.randrange(8)
ptr = self.drinkList[index].ing
ing1thr = ptr[ing1].max - ptr[ing1].perc
ing2thr = ptr[ing2].perc - ptr[ing2].min
if ing1thr & ing2thr:
change = random.randrange(ing1thr if ing1thr < ing2thr else ing2thr)
ptr[ing1].perc += change
ptr[ing2].perc -= change
def crossover(self, index1, index2):
ing1, ing2 = random.randrange(8), random.randrange(8)
while ing1 == ing2:
ing2 = random.randrange(8)
ptr1 = self.drinkList[index1].ing[:]
ptr2 = self.drinkList[index2].ing[:]
resultIndex1 = random.randrange(len(self.drinkList))
while True:
resultIndex2 = random.randrange(len(self.drinkList))
if not resultIndex1 == resultIndex2:
break
bias = 1 if ptr1[ing1].perc > ptr2[ing1].perc else -1
if bias == 1:
maxChange = min(ptr1[ing1].perc - ptr1[ing1].min,
ptr1[ing2].max - ptr1[ing2].perc,
ptr2[ing1].max - ptr2[ing1].perc,
ptr2[ing2].perc - ptr2[ing2].min)
if maxChange:
change = random.randrange(maxChange)
ptr1[ing1].perc -= change
ptr1[ing2].perc += change
ptr2[ing1].perc += change
ptr2[ing2].perc -= change
self.drinkList[resultIndex1].ing = ptr1[:]
self.drinkList[resultIndex2].ing = ptr2[:]
if bias == -1:
maxChange = min(ptr1[ing1].max - ptr1[ing1].perc,
ptr1[ing2].perc - ptr1[ing2].min,
ptr2[ing1].perc - ptr2[ing1].min,
ptr2[ing2].max - ptr2[ing2].perc)
if maxChange:
change = random.randrange(maxChange)
ptr1[ing1].perc += change
ptr1[ing2].perc -= change
ptr2[ing1].perc -= change
ptr2[ing2].perc += change
self.drinkList[resultIndex1].ing = ptr1[:]
self.drinkList[resultIndex2].ing = ptr2[:]
def roulette(self):
sum = 0
lst = []
for x in self.drinkList:
sum += x.fitness
lst.append(sum)
return lst
def selectOne(self):
selection = random.randrange(self.pool[-1])
index = 0
while selection >= self.pool[index]:
index += 1
return index
def selectCouple(self):
selection1 = random.randrange(self.pool[-1])
index1, index2 = 0, 0
while selection1 >= self.pool[index1]:
index1 += 1
while True:
selection2 = random.randrange(self.pool[-1])
while selection2 >= self.pool[index2]:
index2 += 1
if not index1 == index2: break
return (index1, index2)
def save(self, text):
file.write(text)
for x in self.drinkList:
for y in x.ing:
file.write('min: ' + str(y.min) +
' max: ' + str(y.max) +
' value: ' + str(y.perc) + '\n')
file.write('\n\n')
file.write('\nPopulation fitness: ' +
str(self.calculatePopulationFitness()) +
'\n\n----------------------------------------------\n\n')
def run(self):
file.write("Genetic algorithm\n\nAttributes values:\n" +
"Mutation rate: " + str(mutationRate) +
"\nCrossover rate: " + str(crossoverRate) +
"\nIterations: " + str(iterations) +
"\nIngredients:\n\n" + str(ings))
self.save('\n\n--First population--\n\n')
for cnt in range(iterations):
self.updateFitness()
self.pool = self.roulette()
if random.random() < mutationRate:
index = self.selectOne()
self.showFitness('Mutation in iteration ' + str(cnt))
self.mutate(index)
self.updateFitness()
self.showFitness('Results: ')
if random.random() < crossoverRate:
index1, index2 = self.selectCouple()
self.showFitness('Crossover in iteration ' + str(cnt))
self.crossover(index1, index2)
self.updateFitness()
self.showFitness('Results: ')
self.save('--Final population--\n\n')
def calculatePopulationFitness(self):
sum = 0
for x in self.drinkList:
sum += x.fitness
return sum
def updateFitness(self):
for x in self.drinkList:
x.fitness = x.evaluate()
def showFitness(self, text):
lst = [x.fitness for x in self.drinkList]
all = sum(lst)
file.write(text + '\n' + str(lst) + '||' + str(all) + '\n')
To run it I create an instance of GeneticAlgorithm and launch it through run() method.
The problem is, for low level of iterations the program works more or less fine, but if I set iteration to 50 for example, it seems to fall in infinite loop or suspend at random iteration (the logfile is not updated anymore and the program does not stop - happenes at random iteration). What can be the cause of this?
PS: Can you suggest any changes to the coding style? I'm quite new to python and i don't know all the conventions yet.

I don't completely understand your algorithm but it looks like your code hangs in this loop here:
while True:
selection2 = random.randrange(self.pool[-1])
while selection2 >= self.pool[index2]:
index2 += 1
if not index1 == index2: break
It gets to a point where you never get a value where index1 != index2. This could either indicate you have a mistake somewhere in your code, or that there isn't a situation that meets this condition. You could try putting a cap on the number of iterations of this, for example:
iters = 0
while iters < 5000:
selection2 = random.randrange(self.pool[-1])
while selection2 >= self.pool[index2]:
index2 += 1
iters += 1
if index1 != index2: break
if iters == 5000:
# Deal with not being able to identify a Couple

I know the question is more than a year old. Still I wanted a GA code in python to start with and found the problem.
while True:
selection2 = random.randrange(self.pool[-1])
while selection2 >= self.pool[index2]:
index2 += 1
if not index1 == index2: break
The problem is in this loop. once index2 is found to be equal it is not reset back to zero before trying to find a new value.
while True:
index2 = 0
selection2 = random.randrange(self.pool[-1])
while selection2 >= self.pool[index2]:
index2 += 1
if not index1 == index2: break