SavePearlHarbor

Извлечение «знаний» или классификация длинной в один if

—

от автора

admin

В статье мы постараемся классифицировать злокачественную опухоль груди от доброкачественной основываясь на наборе данных взятом отсюда. Как бы странно не звучало, но точность не будет главным приоритетом в этот раз, так как уже есть довольно хорошие решения с упором именно на точность, что и понятно, ведь от данных тестов зависит жизнь человека. Например в 2012 году Бриттани Венгер победила в конкурсе Google Science Fair с проектом cloud4cancer.appspot.com, который был обучен именно по выше указанному набору.

Прежде чем начать советую Вам ознакомится со спецификациями dataset’а и прочесть мой предыдущий пост, так как алгоритм решения взят именно оттуда. Если коротко про данные, то первое число в строке — идентификационный номер случая, следующие 9 описывают опухоль, последнее — тип опухоли(4 — злокачественная, 2 — доброкачественная). Пара примеров:

1017122,8,10,10,8,7,10,9,7,1,4
1018099,1,1,1,1,2,10,3,1,1,2

Для тех кто не прочитал предыдущий пост. резюмирую его в этом абзаце.
Нейрон — сложная адаптивная логическая функция, которая не обладает функциональной полнотой, так как не может генерировать те таблицы истинности, в которых при всех неактивных параметрах(False), результатом становиться True. В частности к таким логическим функциям, которые нейрон не может симулировать, относятся: отрицание, штрих Шеффера, стрелка Пирса, эквивалентность, импликации и т.д. Но есть исключения: нейроны, которые периодически генерируют потенциал действия без стимуляции дендритов. Это лишь личное мнение, которое помогло сделать алгоритм решения.

Класс из предыдущего поста, который будет использован при решении:

import random class LogicReconstructer:     groups=[]     threshold = 0.99     maxmem = 10     numparams = 0      def __init__(self,numparams,threshold = 0.99, totalmem = 10):         self.numparams=numparams         self.threshold=threshold         self.maxmem=totalmem      def getactive(self,params):         if len(params)!=self.numparams:             raise Exception("LogicReconstructer: numparams mismatch")          active=[]         for x in range(self.numparams):             if params[x]:                 active.append(x)         return  active      def extractgroups(self,params,result):         active=self.getactive(params)         exist = False         ignore = False          if result and active:             ind=0             while ind<len(self.groups):                  if len(active)>len(self.groups[ind][0]) and self.issublist(self.groups[ind][0],active):                     ignore=True                     break                  elif len(active)==len(self.groups[ind][0]) and self.issublist(active,self.groups[ind][0]):                     exist=True                     break                  elif len(active)<len(self.groups[ind][0]) and self.issublist(active,self.groups[ind][0]):                     del self.groups[ind]                     ind-=1                  ind+=1              if not exist and not ignore:                 self.groups.append([active,[0]*self.numparams,False])      def extractinhibitors(self,params,result):         active=self.getactive(params)          if result:             count=0             for _,grp in enumerate(self.groups):                 if self.issublist(grp[0],active):                     count+=1                     if count>1:                         return          for _,grp in enumerate(self.groups):             if not grp[2] and self.issublist(grp[0],active):                  neg=[]                 negvalue=False                 for y in range(self.numparams):                     if grp[1][y]<=-self.threshold:                         neg.append(y)                         negvalue|=params[y]                     elif grp[1][y]>=self.threshold:                         grp[2]=True                  for y in range(self.numparams):                     if params[y]:                         if y in neg or not negvalue:                             grp[1][y] = self.counting(grp[1][y],self.maxmem,result)       def counting(self,prc,total,item):         result=prc-prc/total         if not item:             result-=1/total         else:             result+=1/total         return result      def issublist(self,a,b):         for ind,item in enumerate(a):             if item not in b:                 return False         return True      def getsublist(self,a,b):         result=[]         for ind,item in enumerate(a):             if item in b:                 result.append(item)         return result      def simulate(self,params):         result=False         for ind,item in enumerate(self.groups):             if item[2]:                 locres=True                 for x in range(len(item[0])):                     locres&=params[item[0][x]]                 for x in range(len(item[1])):                     if item[1][x]<=-self.threshold:                         locres=locres&~params[x]                 result|=locres         return result      def getlogicfunc(self,guess=False):         result=""         for ind,item in enumerate(self.groups):             if item[2] or guess:                 locres=""                 for x in range(len(item[0])):                     if x!=0:                         locres+=" and "                     locres+=str(item[0][x])                 for x in range(len(item[1])):                     if item[1][x]<=-self.threshold:                         locres+=" and not "+str(x)                 if ind!=0:                     result+=" or "                 result+=locres         return result      def randparams(self):         result = []         for x in range(self.numparams):             result.append(random.choice([True, False]))         return result      def isready(self):         result=bool(self.groups)         for ind,item in enumerate(self.groups):             result&=item[2]         return result      def getlogicstuct(self):         result = []         for _,item in enumerate(self.groups):             grp=[]             if item[2]:                 for x in range(len(item[0])):                     grp.append([item[0][x],True])                 for x in range(len(item[1])):                     if item[1][x]<=-self.threshold:                         grp.append([x,False])             if grp:                 result.append(grp)         return result      def simulatebystruct(self,params,grps):         for _,item in enumerate(grps):             locres=True             for _,param in enumerate(item):                 if param[1]:                     locres&=params[param[0]]                 else:                     locres&=~params[param[0]]                 if not locres:                     break             if locres:                 return True          return  False

Итак, к делу. Для начала нужно классифицировать хоть как-нибудь с удовлетворительной точностью.

Обучаем

def getbin(num,max,min=0):     result=[]     for i in range(min,max+1):         if i<=num:             result.append(True)         else:             result.append(False)     return result  def med():     file = open('C:/meddata.txt', 'r')     lines = file.readlines()     file.close()      data = []      for i in range(len(lines)):         data.append(lines[i].strip().split(","))     lines.clear()      bindata = []     numdata =[]     for i in range(len(data)):         tmp=[]         tmp2=[]         for x in range(len(data[i])):             if x!=0 and x!=10:                 tmp.extend(getbin(int(data[i][x]),10,1))                 tmp2.extend([int(data[i][x])])             elif x==10:                 if int(data[i][x])==4:                     tmp.extend([True])                 else:                     tmp.extend([False])         bindata.append(tmp)         numdata.append(tmp2)     data.clear()      neuron = LogicReconstructer(len(bindata[0])-1,totalmem=7, threshold=0.98)      for _,item in enumerate(bindata):         neuron.extractgroups(item[:-1],item[-1:][0])          ready=False     while not neuron.isready():         rnd=random.randint(0,len(bindata)-1)         neuron.extractinhibitors(bindata[rnd][:-1],bindata[rnd][-1:][0])          logicstruct=neuron.getlogicstuct()     print(logicstruct) 	     falsepositive = 0     falsenegative = 0     for _,item in enumerate(bindata):        res = neuron.simulatebystruct(item[:-1],logicstruct)        if res!=item[-1:][0]:            if res:                falsepositive+=1            else:                falsenegative+=1     print(falsenegative/len(bindata),falsepositive/len(bindata))

В данных встречались знаки вопроса, которые я заменил в блокноте на десятки, посчитав, что пусть уж лучше классификатор ложно сработает чем пропустит. Так же преобразовал числа в бинарную форму функцией getbin, пропустив при этом первое, так как оно особой роли не играет. В итоге у меня, после обучения, получилась структура которая даёт 1.4% ложно негативных и 1.1% ложно положительных ответов, обобщив 241 положительный пример 49-ю логическими группами. Это не лучший результат, но в дальнейшем будем использовать именно его(я получал 0 ложно негативных и 1.2% ложно положительных ответов).

Структура logicstruct

    logicstr = "[[[0, True], [1, True], [2, True], [3, True], [4, True], [10, True], [11, True], [12, True], [20, True], [21, True], [22, True], [30, True], [31, True], [32, True], [40, True], [41, True], [50, True], [51, True], [52, True], [60, True], [61, True], [62, True], [63, True], [70, True], [71, True], [72, True], [73, True], [80, True], [53, False], [54, False]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [10, True], [11, True], [12, True], [13, True], [20, True], [21, True], [22, True], [23, True], [24, True], [25, True], [30, True], [31, True], [32, True], [33, True], [40, True], [41, True], [42, True], [43, True], [44, True], [45, True], [50, True], [60, True], [61, True], [62, True], [63, True], [70, True], [71, True], [72, True], [80, True]], [[0, True], [1, True], [10, True], [11, True], [12, True], [13, True], [14, True], [20, True], [21, True], [22, True], [30, True], [31, True], [32, True], [40, True], [41, True], [42, True], [43, True], [44, True], [45, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [56, True], [60, True], [61, True], [62, True], [63, True], [64, True], [65, True], [66, True], [70, True], [71, True], [72, True], [73, True], [74, True], [80, True], [2, False], [3, False], [4, False], [5, False], [15, False], [23, False], [24, False], [25, False], [33, False], [34, False], [35, False], [36, False], [37, False], [38, False], [57, False], [58, False], [59, False], [75, False], [76, False], [77, False]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [8, True], [9, True], [10, True], [11, True], [12, True], [13, True], [20, True], [21, True], [22, True], [30, True], [40, True], [41, True], [42, True], [50, True], [51, True], [52, True], [60, True], [61, True], [62, True], [63, True], [64, True], [65, True], [70, True], [71, True], [72, True], [73, True], [74, True], [80, True], [81, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [10, True], [11, True], [12, True], [13, True], [14, True], [15, True], [20, True], [21, True], [22, True], [23, True], [24, True], [30, True], [31, True], [32, True], [33, True], [34, True], [35, True], [40, True], [41, True], [42, True], [43, True], [44, True], [45, True], [46, True], [47, True], [48, True], [49, True], [50, True], [60, True], [61, True], [62, True], [70, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [8, True], [10, True], [11, True], [12, True], [13, True], [14, True], [20, True], [21, True], [22, True], [23, True], [24, True], [25, True], [26, True], [27, True], [30, True], [40, True], [41, True], [50, True], [51, True], [52, True], [60, True], [61, True], [70, True], [80, True], [81, True], [82, True], [83, True], [84, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [10, True], [11, True], [12, True], [20, True], [21, True], [22, True], [30, True], [31, True], [32, True], [33, True], [40, True], [41, True], [50, True], [51, True], [52, True], [53, True], [60, True], [61, True], [62, True], [70, True], [71, True], [72, True], [73, True], [80, True], [5, False], [34, False], [42, False], [54, False], [55, False], [56, False], [74, False]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [10, True], [11, True], [20, True], [21, True], [22, True], [23, True], [30, True], [40, True], [41, True], [42, True], [43, True], [44, True], [50, True], [60, True], [61, True], [62, True], [63, True], [64, True], [70, True], [71, True], [72, True], [73, True], [80, True], [81, True], [82, True], [83, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [10, True], [11, True], [20, True], [21, True], [22, True], [30, True], [40, True], [41, True], [42, True], [43, True], [44, True], [45, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [56, True], [57, True], [58, True], [59, True], [60, True], [61, True], [62, True], [63, True], [64, True], [70, True], [80, True], [5, False], [13, False], [14, False], [15, False], [25, False], [31, False], [32, False], [33, False], [34, False], [35, False], [36, False], [37, False], [38, False], [65, False], [66, False], [73, False], [74, False], [75, False], [76, False], [77, False]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [8, True], [10, True], [11, True], [12, True], [13, True], [14, True], [20, True], [21, True], [22, True], [23, True], [24, True], [30, True], [31, True], [40, True], [41, True], [50, True], [51, True], [60, True], [61, True], [62, True], [63, True], [64, True], [70, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [10, True], [11, True], [12, True], [20, True], [21, True], [22, True], [23, True], [30, True], [40, True], [41, True], [42, True], [43, True], [44, True], [50, True], [51, True], [60, True], [61, True], [62, True], [70, True], [71, True], [72, True], [73, True], [74, True], [75, True], [76, True], [77, True], [78, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [8, True], [9, True], [10, True], [11, True], [12, True], [13, True], [20, True], [21, True], [30, True], [40, True], [41, True], [42, True], [50, True], [51, True], [60, True], [61, True], [62, True], [63, True], [70, True], [71, True], [72, True], [80, True], [81, True], [82, True], [83, True], [84, True], [85, True], [86, True], [87, True], [88, True], [89, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [10, True], [11, True], [12, True], [20, True], [21, True], [22, True], [23, True], [30, True], [40, True], [41, True], [42, True], [43, True], [44, True], [45, True], [46, True], [47, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [56, True], [57, True], [58, True], [59, True], [60, True], [61, True], [62, True], [63, True], [70, True], [71, True], [72, True], [73, True], [74, True], [75, True], [76, True], [77, True], [78, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [10, True], [11, True], [12, True], [13, True], [14, True], [15, True], [16, True], [17, True], [18, True], [19, True], [20, True], [21, True], [30, True], [31, True], [32, True], [33, True], [34, True], [35, True], [36, True], [37, True], [40, True], [41, True], [42, True], [43, True], [44, True], [45, True], [46, True], [47, True], [48, True], [49, True], [50, True], [51, True], [60, True], [61, True], [62, True], [63, True], [64, True], [65, True], [66, True], [70, True], [71, True], [72, True], [73, True], [74, True], [75, True], [76, True], [77, True], [80, True], [81, True], [82, True], [83, True], [84, True], [85, True], [86, True], [87, True], [88, True], [89, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [8, True], [9, True], [10, True], [11, True], [12, True], [13, True], [14, True], [15, True], [20, True], [21, True], [22, True], [23, True], [30, True], [40, True], [41, True], [42, True], [50, True], [51, True], [52, True], [53, True], [60, True], [61, True], [62, True], [70, True], [71, True], [80, True], [81, True], [82, True]], [[0, True], [1, True], [2, True], [10, True], [11, True], [12, True], [20, True], [21, True], [22, True], [23, True], [24, True], [25, True], [30, True], [31, True], [32, True], [33, True], [40, True], [41, True], [42, True], [43, True], [44, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [56, True], [57, True], [60, True], [61, True], [62, True], [63, True], [70, True], [71, True], [72, True], [73, True], [80, True]], [[0, True], [1, True], [10, True], [11, True], [12, True], [20, True], [21, True], [22, True], [23, True], [30, True], [31, True], [32, True], [33, True], [40, True], [41, True], [50, True], [51, True], [52, True], [53, True], [54, True], [60, True], [61, True], [70, True], [71, True], [72, True], [73, True], [74, True], [80, True], [3, False]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [10, True], [11, True], [20, True], [21, True], [22, True], [30, True], [40, True], [41, True], [42, True], [43, True], [44, True], [45, True], [50, True], [51, True], [52, True], [60, True], [61, True], [62, True], [63, True], [64, True], [65, True], [66, True], [70, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [10, True], [11, True], [12, True], [20, True], [21, True], [22, True], [23, True], [30, True], [31, True], [32, True], [33, True], [40, True], [41, True], [42, True], [50, True], [51, True], [52, True], [60, True], [61, True], [62, True], [70, True], [71, True], [80, True], [81, True], [82, True], [83, True], [84, True], [85, True], [86, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [10, True], [11, True], [12, True], [20, True], [21, True], [22, True], [23, True], [24, True], [30, True], [31, True], [32, True], [33, True], [40, True], [41, True], [42, True], [43, True], [44, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [56, True], [57, True], [58, True], [59, True], [60, True], [70, True], [71, True], [72, True], [73, True], [74, True], [75, True], [80, True], [81, True]], [[0, True], [1, True], [2, True], [10, True], [11, True], [12, True], [13, True], [20, True], [21, True], [22, True], [23, True], [24, True], [30, True], [31, True], [40, True], [41, True], [42, True], [43, True], [44, True], [45, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [56, True], [57, True], [60, True], [61, True], [62, True], [63, True], [70, True], [80, True], [3, False], [59, False], [73, False], [74, False], [75, False], [76, False], [77, False]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [8, True], [9, True], [10, True], [11, True], [12, True], [13, True], [14, True], [15, True], [16, True], [17, True], [20, True], [21, True], [22, True], [23, True], [24, True], [25, True], [26, True], [27, True], [28, True], [29, True], [30, True], [31, True], [32, True], [33, True], [34, True], [35, True], [36, True], [37, True], [38, True], [39, True], [40, True], [41, True], [42, True], [43, True], [44, True], [45, True], [50, True], [60, True], [61, True], [62, True], [70, True], [80, True], [81, True], [82, True], [83, True], [84, True], [85, True], [86, True], [87, True], [88, True], [89, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [10, True], [11, True], [12, True], [13, True], [14, True], [15, True], [16, True], [17, True], [18, True], [19, True], [20, True], [21, True], [22, True], [23, True], [24, True], [25, True], [26, True], [27, True], [28, True], [29, True], [30, True], [31, True], [32, True], [40, True], [41, True], [42, True], [43, True], [44, True], [45, True], [46, True], [47, True], [50, True], [60, True], [61, True], [62, True], [63, True], [64, True], [70, True], [71, True], [72, True], [73, True], [74, True], [75, True], [76, True], [77, True], [78, True], [79, True], [80, True], [81, True], [82, True]], [[0, True], [10, True], [11, True], [12, True], [13, True], [14, True], [20, True], [21, True], [22, True], [23, True], [24, True], [25, True], [26, True], [27, True], [30, True], [31, True], [32, True], [33, True], [34, True], [35, True], [40, True], [41, True], [42, True], [43, True], [44, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [56, True], [57, True], [60, True], [61, True], [62, True], [63, True], [64, True], [65, True], [66, True], [70, True], [71, True], [72, True], [73, True], [74, True], [75, True], [76, True], [77, True], [78, True], [79, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [10, True], [20, True], [30, True], [31, True], [32, True], [40, True], [50, True], [51, True], [52, True], [53, True], [54, True], [60, True], [61, True], [70, True], [80, True], [77, False]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [10, True], [11, True], [12, True], [13, True], [20, True], [21, True], [22, True], [23, True], [30, True], [40, True], [41, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [56, True], [57, True], [58, True], [60, True], [61, True], [62, True], [70, True], [71, True], [72, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [10, True], [11, True], [12, True], [13, True], [14, True], [15, True], [20, True], [21, True], [22, True], [23, True], [24, True], [25, True], [30, True], [31, True], [40, True], [41, True], [42, True], [43, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [56, True], [57, True], [58, True], [59, True], [60, True], [61, True], [62, True], [70, True], [71, True], [72, True], [73, True], [74, True], [75, True], [80, True], [5, False], [32, False], [33, False], [34, False], [35, False], [36, False], [37, False], [38, False], [44, False], [45, False], [63, False], [64, False], [65, False], [66, False], [76, False], [77, False]], [[0, True], [1, True], [2, True], [10, True], [11, True], [12, True], [20, True], [21, True], [22, True], [23, True], [24, True], [30, True], [31, True], [40, True], [41, True], [42, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [56, True], [57, True], [58, True], [59, True], [60, True], [61, True], [62, True], [63, True], [64, True], [65, True], [66, True], [70, True], [80, True], [3, False], [4, False], [5, False], [13, False], [14, False], [15, False], [25, False], [32, False], [33, False], [34, False], [35, False], [36, False], [37, False], [38, False], [43, False], [44, False], [45, False], [71, False], [72, False], [73, False], [74, False], [75, False], [76, False], [77, False]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [10, True], [11, True], [20, True], [21, True], [22, True], [23, True], [30, True], [40, True], [41, True], [42, True], [50, True], [51, True], [52, True], [53, True], [60, True], [61, True], [62, True], [70, True], [71, True], [72, True], [80, True]], [[0, True], [10, True], [11, True], [12, True], [13, True], [20, True], [21, True], [22, True], [30, True], [31, True], [32, True], [33, True], [34, True], [35, True], [36, True], [37, True], [38, True], [39, True], [40, True], [41, True], [42, True], [43, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [56, True], [57, True], [58, True], [59, True], [60, True], [61, True], [62, True], [63, True], [64, True], [70, True], [71, True], [72, True], [73, True], [74, True], [75, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [10, True], [20, True], [21, True], [22, True], [30, True], [40, True], [41, True], [42, True], [43, True], [50, True], [51, True], [52, True], [53, True], [54, True], [60, True], [61, True], [62, True], [63, True], [64, True], [70, True], [71, True], [72, True], [73, True], [74, True], [75, True], [76, True], [77, True], [78, True], [79, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [10, True], [11, True], [12, True], [13, True], [14, True], [20, True], [21, True], [22, True], [23, True], [24, True], [30, True], [31, True], [40, True], [41, True], [42, True], [43, True], [44, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [56, True], [57, True], [58, True], [59, True], [60, True], [61, True], [62, True], [63, True], [70, True], [71, True], [72, True], [80, True], [5, False], [15, False], [25, False], [32, False], [33, False], [34, False], [35, False], [36, False], [37, False], [38, False], [45, False], [64, False], [65, False], [66, False], [73, False], [74, False], [75, False], [76, False], [77, False]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [8, True], [9, True], [10, True], [20, True], [30, True], [40, True], [41, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [56, True], [57, True], [58, True], [59, True], [60, True], [61, True], [62, True], [63, True], [64, True], [70, True], [71, True], [72, True], [73, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [10, True], [11, True], [12, True], [13, True], [14, True], [15, True], [16, True], [17, True], [18, True], [19, True], [20, True], [21, True], [22, True], [30, True], [31, True], [40, True], [41, True], [42, True], [43, True], [44, True], [45, True], [50, True], [51, True], [52, True], [53, True], [60, True], [61, True], [62, True], [70, True], [71, True], [72, True], [73, True], [74, True], [75, True], [76, True], [77, True], [78, True], [79, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [8, True], [9, True], [10, True], [11, True], [12, True], [13, True], [20, True], [21, True], [22, True], [23, True], [24, True], [25, True], [26, True], [30, True], [31, True], [40, True], [41, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [56, True], [57, True], [60, True], [61, True], [62, True], [63, True], [64, True], [65, True], [70, True], [80, True]], [[0, True], [1, True], [2, True], [10, True], [11, True], [12, True], [13, True], [20, True], [21, True], [22, True], [23, True], [30, True], [31, True], [32, True], [33, True], [34, True], [35, True], [36, True], [37, True], [38, True], [39, True], [40, True], [41, True], [42, True], [43, True], [44, True], [50, True], [60, True], [61, True], [62, True], [70, True], [71, True], [72, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [10, True], [11, True], [12, True], [20, True], [21, True], [22, True], [30, True], [40, True], [41, True], [42, True], [50, True], [51, True], [52, True], [60, True], [61, True], [62, True], [70, True], [71, True], [72, True], [80, True], [81, True], [82, True], [5, False], [31, False], [32, False], [33, False], [34, False], [54, False], [55, False], [56, False], [57, False], [58, False], [59, False]], [[0, True], [1, True], [2, True], [10, True], [11, True], [12, True], [13, True], [14, True], [15, True], [16, True], [17, True], [18, True], [19, True], [20, True], [21, True], [22, True], [30, True], [31, True], [32, True], [33, True], [34, True], [35, True], [36, True], [37, True], [38, True], [39, True], [40, True], [41, True], [42, True], [43, True], [44, True], [45, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [56, True], [57, True], [58, True], [59, True], [60, True], [61, True], [62, True], [63, True], [64, True], [70, True], [80, True], [81, True], [82, True], [83, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [10, True], [11, True], [12, True], [13, True], [14, True], [15, True], [16, True], [20, True], [21, True], [22, True], [23, True], [24, True], [25, True], [26, True], [27, True], [30, True], [31, True], [40, True], [41, True], [42, True], [43, True], [50, True], [51, True], [60, True], [61, True], [62, True], [63, True], [64, True], [70, True], [71, True], [72, True], [73, True], [74, True], [75, True], [76, True], [77, True], [78, True], [79, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [8, True], [9, True], [10, True], [11, True], [12, True], [13, True], [14, True], [15, True], [16, True], [17, True], [18, True], [19, True], [20, True], [21, True], [22, True], [23, True], [24, True], [25, True], [26, True], [27, True], [28, True], [29, True], [30, True], [40, True], [41, True], [42, True], [43, True], [44, True], [45, True], [50, True], [60, True], [61, True], [70, True], [71, True], [72, True], [73, True], [74, True], [75, True], [76, True], [77, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [8, True], [9, True], [10, True], [11, True], [20, True], [21, True], [30, True], [40, True], [41, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [60, True], [70, True], [80, True], [81, True]], [[0, True], [1, True], [2, True], [10, True], [11, True], [12, True], [13, True], [14, True], [15, True], [20, True], [21, True], [22, True], [23, True], [30, True], [31, True], [32, True], [33, True], [34, True], [35, True], [36, True], [37, True], [38, True], [39, True], [40, True], [41, True], [42, True], [50, True], [51, True], [52, True], [60, True], [61, True], [62, True], [70, True], [71, True], [72, True], [73, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [10, True], [11, True], [12, True], [20, True], [21, True], [30, True], [40, True], [41, True], [42, True], [50, True], [51, True], [52, True], [53, True], [60, True], [61, True], [62, True], [63, True], [70, True], [80, True], [31, False], [32, False], [33, False], [34, False], [43, False], [71, False]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [10, True], [11, True], [12, True], [13, True], [20, True], [21, True], [22, True], [23, True], [30, True], [40, True], [41, True], [42, True], [43, True], [44, True], [45, True], [50, True], [51, True], [52, True], [53, True], [54, True], [55, True], [56, True], [57, True], [58, True], [59, True], [60, True], [61, True], [70, True], [71, True], [72, True], [73, True], [74, True], [80, True], [81, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [5, True], [6, True], [7, True], [8, True], [10, True], [11, True], [12, True], [13, True], [14, True], [15, True], [16, True], [17, True], [20, True], [21, True], [22, True], [23, True], [24, True], [25, True], [26, True], [27, True], [30, True], [31, True], [32, True], [33, True], [34, True], [35, True], [36, True], [37, True], [38, True], [40, True], [41, True], [42, True], [43, True], [44, True], [45, True], [50, True], [51, True], [52, True], [60, True], [61, True], [62, True], [63, True], [70, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [10, True], [11, True], [12, True], [13, True], [14, True], [15, True], [16, True], [17, True], [18, True], [19, True], [20, True], [21, True], [22, True], [23, True], [24, True], [25, True], [26, True], [27, True], [30, True], [31, True], [32, True], [33, True], [34, True], [40, True], [41, True], [42, True], [43, True], [50, True], [60, True], [61, True], [62, True], [63, True], [64, True], [65, True], [66, True], [67, True], [68, True], [69, True], [70, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [10, True], [11, True], [12, True], [13, True], [20, True], [21, True], [22, True], [23, True], [24, True], [25, True], [30, True], [31, True], [32, True], [33, True], [34, True], [35, True], [36, True], [37, True], [40, True], [41, True], [42, True], [43, True], [50, True], [60, True], [61, True], [62, True], [63, True], [64, True], [65, True], [66, True], [67, True], [70, True], [71, True], [72, True], [73, True], [74, True], [75, True], [76, True], [77, True], [78, True], [79, True], [80, True]], [[0, True], [1, True], [2, True], [3, True], [4, True], [10, True], [11, True], [12, True], [13, True], [14, True], [15, True], [16, True], [20, True], [21, True], [22, True], [23, True], [30, True], [40, True], [41, True], [42, True], [43, True], [44, True], [45, True], [50, True], [60, True], [61, True], [62, True], [63, True], [64, True], [65, True], [66, True], [70, True], [71, True], [72, True], [73, True], [74, True], [75, True], [76, True], [77, True], [78, True], [79, True], [80, True], [81, True], [82, True]], [[0, True], [1, True], [2, True], [3, True], [10, True], [11, True], [12, True], [13, True], [14, True], [15, True], [16, True], [17, True], [20, True], [21, True], [22, True], [23, True], [24, True], [25, True], [30, True], [31, True], [32, True], [33, True], [40, True], [41, True], [42, True], [50, True], [51, True], [52, True], [53, True], [60, True], [61, True], [62, True], [63, True], [64, True], [65, True], [66, True], [67, True], [68, True], [69, True], [70, True], [71, True], [72, True], [73, True], [74, True], [75, True], [80, True]]]"     logicstruct=literal_eval(logicstr)

Человек это вряд ли поймёт, поэтому хорошо бы преобразовать эту структуру обратно в числа и составить из них логические правила.

Генерация if'а

Функции: 

def numdecoder(binform=[]):     greater=[1]*9     less=[11]*9     for _,item in enumerate(binform):         if item[1]:             greater[item[0]//10]=max(greater[item[0]//10],item[0]%10+1)         else:             less[item[0]//10]=min(less[item[0]//10],item[0]%10+1)     return greater,less  def tologicfunc(numform=[]):     result=""     for _,item in enumerate(numform):         tmp=""         if _!=0:             tmp = " or \\ \n"         first=True         for x in range(len(item[0])):              if item[0][x]>1:                 if not first:                     tmp+=" and "                 tmp+="x["+str(x)+"]>="+str(item[0][x])                 first=False         for x in range(len(item[1])):             if item[1][x]<11:                 tmp+=" and "                 tmp+="x["+str(x)+"]<"+str(item[1][x])         result+=tmp     return result

Пример генерации: 

    numform=[]     for _,item in enumerate(logicstruct):         greater,less=numdecoder(item)         numform.append([greater,less])      print(tologicfunc(numform))

И финальный аккорд, тот самый if… хотя нет, не будет даже if’а.

Классификатор

def medfunc(x):     return x[0]>=5 and x[1]>=3 and x[2]>=3 and x[3]>=3 and x[4]>=2 and x[5]>=3 and x[6]>=4 and x[7]>=4 and x[5]<4 or \            x[0]>=7 and x[1]>=4 and x[2]>=6 and x[3]>=4 and x[4]>=6 and x[6]>=4 and x[7]>=3 or \            x[0]>=2 and x[1]>=5 and x[2]>=3 and x[3]>=3 and x[4]>=6 and x[5]>=7 and x[6]>=7 and x[7]>=5 and x[0]<3 and x[1]<6 and x[2]<4 and x[3]<4 and x[5]<8 and x[7]<6 or \            x[0]>=10 and x[1]>=4 and x[2]>=3 and x[4]>=3 and x[5]>=3 and x[6]>=6 and x[7]>=5 and x[8]>=2 or \            x[0]>=5 and x[1]>=6 and x[2]>=5 and x[3]>=6 and x[4]>=10 and x[6]>=3 or \            x[0]>=9 and x[1]>=5 and x[2]>=8 and x[4]>=2 and x[5]>=3 and x[6]>=2 and x[8]>=5 or \            x[0]>=5 and x[1]>=3 and x[2]>=3 and x[3]>=4 and x[4]>=2 and x[5]>=4 and x[6]>=3 and x[7]>=4 and x[0]<6 and x[3]<5 and x[4]<3 and x[5]<5 and x[7]<5 or \            x[0]>=8 and x[1]>=2 and x[2]>=4 and x[4]>=5 and x[6]>=5 and x[7]>=4 and x[8]>=4 or \            x[0]>=5 and x[1]>=2 and x[2]>=3 and x[4]>=6 and x[5]>=10 and x[6]>=5 and x[0]<6 and x[1]<4 and x[2]<6 and x[3]<2 and x[6]<6 and x[7]<4 or \            x[0]>=9 and x[1]>=5 and x[2]>=5 and x[3]>=2 and x[4]>=2 and x[5]>=2 and x[6]>=5 or \            x[0]>=6 and x[1]>=3 and x[2]>=4 and x[4]>=5 and x[5]>=2 and x[6]>=3 and x[7]>=9 or \            x[0]>=10 and x[1]>=4 and x[2]>=2 and x[4]>=3 and x[5]>=2 and x[6]>=4 and x[7]>=3 and x[8]>=10 or \            x[0]>=5 and x[1]>=3 and x[2]>=4 and x[4]>=8 and x[5]>=10 and x[6]>=4 and x[7]>=9 or \            x[0]>=6 and x[1]>=10 and x[2]>=2 and x[3]>=8 and x[4]>=10 and x[5]>=2 and x[6]>=7 and x[7]>=8 and x[8]>=10 or \            x[0]>=10 and x[1]>=6 and x[2]>=4 and x[4]>=3 and x[5]>=4 and x[6]>=3 and x[7]>=2 and x[8]>=3 or \            x[0]>=3 and x[1]>=3 and x[2]>=6 and x[3]>=4 and x[4]>=5 and x[5]>=8 and x[6]>=4 and x[7]>=4 or \            x[0]>=2 and x[1]>=3 and x[2]>=4 and x[3]>=4 and x[4]>=2 and x[5]>=5 and x[6]>=2 and x[7]>=5 and x[0]<4 or \            x[0]>=8 and x[1]>=2 and x[2]>=3 and x[4]>=6 and x[5]>=3 and x[6]>=7 or \            x[0]>=7 and x[1]>=3 and x[2]>=4 and x[3]>=4 and x[4]>=3 and x[5]>=3 and x[6]>=3 and x[7]>=2 and x[8]>=7 or \            x[0]>=8 and x[1]>=3 and x[2]>=5 and x[3]>=4 and x[4]>=5 and x[5]>=10 and x[7]>=6 and x[8]>=2 or \            x[0]>=3 and x[1]>=4 and x[2]>=5 and x[3]>=2 and x[4]>=6 and x[5]>=8 and x[6]>=4 and x[0]<4 and x[5]<10 and x[7]<4 or \            x[0]>=10 and x[1]>=8 and x[2]>=10 and x[3]>=10 and x[4]>=6 and x[6]>=3 and x[8]>=10 or \            x[0]>=5 and x[1]>=10 and x[2]>=10 and x[3]>=3 and x[4]>=8 and x[6]>=5 and x[7]>=10 and x[8]>=3 or \            x[1]>=5 and x[2]>=8 and x[3]>=6 and x[4]>=5 and x[5]>=8 and x[6]>=7 and x[7]>=10 or \            x[0]>=4 and x[3]>=3 and x[5]>=5 and x[6]>=2 and x[7]<8 or \            x[0]>=8 and x[1]>=4 and x[2]>=4 and x[4]>=2 and x[5]>=9 and x[6]>=3 and x[7]>=3 or \            x[0]>=5 and x[1]>=6 and x[2]>=6 and x[3]>=2 and x[4]>=4 and x[5]>=10 and x[6]>=3 and x[7]>=6 and x[0]<6 and x[3]<3 and x[4]<5 and x[6]<4 and x[7]<7 or \            x[0]>=3 and x[1]>=3 and x[2]>=5 and x[3]>=2 and x[4]>=3 and x[5]>=10 and x[6]>=7 and x[0]<4 and x[1]<4 and x[2]<6 and x[3]<3 and x[4]<4 and x[7]<2 or \            x[0]>=7 and x[1]>=2 and x[2]>=4 and x[4]>=3 and x[5]>=4 and x[6]>=3 and x[7]>=3 or \            x[1]>=4 and x[2]>=3 and x[3]>=10 and x[4]>=4 and x[5]>=10 and x[6]>=5 and x[7]>=6 or \            x[0]>=6 and x[2]>=3 and x[4]>=4 and x[5]>=5 and x[6]>=5 and x[7]>=10 or \            x[0]>=5 and x[1]>=5 and x[2]>=5 and x[3]>=2 and x[4]>=5 and x[5]>=10 and x[6]>=4 and x[7]>=3 and x[0]<6 and x[1]<6 and x[2]<6 and x[3]<3 and x[4]<6 and x[6]<5 and x[7]<4 or \            x[0]>=10 and x[4]>=2 and x[5]>=10 and x[6]>=5 and x[7]>=4 or \            x[0]>=8 and x[1]>=10 and x[2]>=3 and x[3]>=2 and x[4]>=6 and x[5]>=4 and x[6]>=3 and x[7]>=10 or \            x[0]>=10 and x[1]>=4 and x[2]>=7 and x[3]>=2 and x[4]>=2 and x[5]>=8 and x[6]>=6 or \            x[0]>=3 and x[1]>=4 and x[2]>=4 and x[3]>=10 and x[4]>=5 and x[6]>=3 and x[7]>=3 or \            x[0]>=5 and x[1]>=3 and x[2]>=3 and x[4]>=3 and x[5]>=3 and x[6]>=3 and x[7]>=3 and x[8]>=3 and x[0]<6 and x[3]<2 and x[5]<5 or \            x[0]>=3 and x[1]>=10 and x[2]>=3 and x[3]>=10 and x[4]>=6 and x[5]>=10 and x[6]>=5 and x[8]>=4 or \            x[0]>=8 and x[1]>=7 and x[2]>=8 and x[3]>=2 and x[4]>=4 and x[5]>=2 and x[6]>=5 and x[7]>=10 or \            x[0]>=10 and x[1]>=10 and x[2]>=10 and x[4]>=6 and x[6]>=2 and x[7]>=8 or \            x[0]>=10 and x[1]>=2 and x[2]>=2 and x[4]>=2 and x[5]>=6 and x[8]>=2 or \            x[0]>=3 and x[1]>=6 and x[2]>=4 and x[3]>=10 and x[4]>=3 and x[5]>=3 and x[6]>=3 and x[7]>=4 or \            x[0]>=6 and x[1]>=3 and x[2]>=2 and x[4]>=3 and x[5]>=4 and x[6]>=4 and x[3]<2 and x[4]<4 and x[7]<2 or \            x[0]>=8 and x[1]>=4 and x[2]>=4 and x[4]>=6 and x[5]>=10 and x[6]>=2 and x[7]>=5 and x[8]>=2 or \            x[0]>=9 and x[1]>=8 and x[2]>=8 and x[3]>=9 and x[4]>=6 and x[5]>=3 and x[6]>=4 or \            x[0]>=4 and x[1]>=10 and x[2]>=8 and x[3]>=5 and x[4]>=4 and x[6]>=10 or \            x[0]>=5 and x[1]>=4 and x[2]>=6 and x[3]>=8 and x[4]>=4 and x[6]>=8 and x[7]>=10 or \            x[0]>=5 and x[1]>=7 and x[2]>=4 and x[4]>=6 and x[6]>=7 and x[7]>=10 and x[8]>=3 or \            x[0]>=4 and x[1]>=8 and x[2]>=6 and x[3]>=4 and x[4]>=3 and x[5]>=4 and x[6]>=10 and x[7]>=6

Входной параметр x — list из девяти чисел в диапазоне от 1 до 10. Точность соответственно такая же как и структуры. Вышло коротко и сердито. Ну и ладно.

P.S. Благодарю Anc за предоставление своих наработок по данной тематике.

ссылка на оригинал статьи http://habrahabr.ru/post/208764/

Комментарии

Добавить комментарий

Ваш адрес email не будет опубликован. Обязательные поля помечены *