first genetic algo bot

Pipfile

@@ -8,6 +8,7 @@ name = "pypi"
 [packages]
 
 matplotlib = "*"
+numpy = "*"
 
 
 [dev-packages]

Pipfile.lock

@@ -1,7 +1,7 @@
 {
     "_meta": {
         "hash": {
-            "sha256": "aed9c28be63899aa45429206673c5a773fc0eca0acea8ec8909e1f1fcd6b4e7c"
+            "sha256": "1a39e45c62576713be6123d9287975b50115164b6bad65cf1b5c879588893f83"
         },
         "host-environment-markers": {
             "implementation_name": "cpython",

genetic.py

@@ -0,0 +1,88 @@
+import supply
+import random
+import matrixbot
+import numpy as np
+from operator import itemgetter
+
+SOLD_BENEFIT = 2
+
+def run_generation(pop, i):
+    print("Generation %d" % i)
+    ranking = []
+    for x in pop:
+        score = evaluate(x)
+        ranking.append((score, x))
+    ranking.sort(key=itemgetter(0))
+    print("Best of generation: ", ranking[0])
+    newpop = [x[1] for x in ranking[:len(ranking)//2]]
+    newpop = breed(newpop, len(pop), i)
+    return newpop
+
+def evaluate(mem):
+    g = supply.variableRequestGenerator(supply.TURNS, 8, 14)
+    #chain = [StupidAI(12), PlayerChain("Manufacturer", 12), Base()]
+    chain = [matrixbot.MatrixBot(mem[:25], mem[25:], 12), supply.Base()]
+    total_sold = 0
+    history = []
+    for topreq in g:
+        requests = [x.request() for x in chain]
+        requests = requests[:-1]
+        requests.insert(0, topreq)
+        got = 0
+        for i, c in reversed(list(enumerate(chain))):
+            got = c.reconcile(requests[i], got)
+        #print("Sold ", got, " units.")
+        total_sold += got
+        history.append([x.cost() for x in chain])
+    total_cost = [sum([x[0] * supply.SUPPLY_COST + x[1] * supply.BACKLOG_COST for x in y]) for y in history]
+    cost = supply.integrate(total_cost)[-1] - (total_sold * SOLD_BENEFIT)
+    return cost
+
+
+def mate(a, b):
+    out = []
+    for x in range(len(a)):
+        if random.random() < 0.5:
+            out.append(a[x])
+        else:
+            out.append(b[x])
+    return np.array(out)
+
+def mutate(a):
+    for i in range(5):
+        x = random.randint(0, len(a) - 1)
+        amt = random.uniform(-0.5, 0.5)
+        a[x] = a[x] + amt
+
+WEIGHT = 0.9
+LATE_WEIGHT = 0.2
+GENS = 500
+
+def breed(pop, n, i):
+    global WEIGHT
+    mut_chance = (WEIGHT - LATE_WEIGHT) * (GENS - i / GENS) + LATE_WEIGHT
+    total = n - len(pop)
+    newbies = []
+    while total != 0:
+        a = random.choice(pop)
+        b = random.choice(pop)
+        c = mate(a, b)
+        if random.random() < mut_chance:
+            mutate(c)
+        newbies.append(c)
+        total -= 1
+    c = pop[:]
+    c.extend(newbies)
+    return c
+
+def main():
+    starting_pop = []
+    for i in range(300):
+        x = np.random.uniform(low=-2, high=2, size=30)
+        starting_pop.append(x)
+    pop = starting_pop
+    for gen in range(GENS):
+        pop = run_generation(pop, gen+1)
+
+if __name__ == "__main__":
+    main()

matrixbot.py

@@ -0,0 +1,22 @@
+import supply
+import numpy as np
+
+class MatrixBot(supply.Chain):
+    def __init__(self, hidden1, hidden2, initial):
+        a = np.matrix(hidden1).reshape(5,5)
+        b = np.matrix(hidden2).reshape(1,5)
+        self.mat = np.matmul(b, a)
+        super().__init__(initial)
+    def request(self):
+        x = [self.backlog, self.last_got, self.last_req, self.last_ship, self.supply]
+        out = np.matmul(self.mat, np.matrix(x).transpose())
+        n = out.tolist()[0][0]
+        if n < 0:
+            return 0
+        if n > 200:
+            return 200
+        return int(n)
+
+if __name__ == "__main__":
+    m = MatrixBot(np.random.uniform(low=-3, high=3, size=25), np.random.uniform(low=-3, high=3, size=5), 12)
+    print(m.request())

supply.py

@@ -1,6 +1,7 @@
 import math
 import random
 import matplotlib.pyplot as plt
+import matrixbot
 
 BACKLOG_COST = 25
 SUPPLY_COST = 5
@@ -100,8 +101,22 @@ def main():
     global SUPPLY_COST
     global BACKLOG_COST
     g = variableRequestGenerator(TURNS, 8, 14)
-    #chain = [StupidAI(12), PlayerChain("Manufacturer", 12), Base()]
-    chain = [PlayerChain("me", 12), LessStupidAI(12), LessStupidAI(12), LessStupidAI(12), Base()]
+    #chain = [PlayerChain("Manufacturer", 12), Base()]
+    #chain = [PlayerChain("me", 12), LessStupidAI(12), LessStupidAI(12), LessStupidAI(12), Base()]
+    mb1 = matrixbot.MatrixBot([ 0.29963248,  0.08142691, -0.86641011,  0.23675042,  0.7086182 ,
+       -0.06441882,  0.03062067, -1.18299915,  0.68115478,  0.16068485,
+       -1.7178326 , -0.29003603, -0.83202861,  1.73222139, -1.98878473,
+       -0.96036021,  0.65793096,  1.50552035, -1.18544224,  0.03207729,
+        0.78074126, -0.91446605,  2.92469872,  0.48680479, -0.34067442],
+                              [-0.07150818, -0.10019835, -0.02610447, -0.02049193,  0.42415006], 12)
+    mb2 = matrixbot.MatrixBot([ 0.29963248,  0.08142691, -0.86641011,  0.23675042,  0.7086182 ,
+       -0.06441882,  0.03062067, -1.18299915,  0.68115478,  0.16068485,
+       -1.7178326 , -0.29003603, -0.83202861,  1.73222139, -1.98878473,
+       -0.96036021,  0.65793096,  1.50552035, -1.18544224,  0.03207729,
+        0.78074126, -0.91446605,  2.92469872,  0.48680479, -0.34067442],
+                              [-0.07150818, -0.10019835, -0.02610447, -0.02049193,  0.42415006], 12)
+    chain = [mb1, PlayerChain("me", 12), mb2, Base()]
+    import pdb; pdb.set_trace()
     turn = 0
     total_sold = 0
     history = []