deap实战_2017中国数学建模大赛_B题_第二题

简介

补充:本例子仅仅是之前deap类库的一个实战例子,所以先别问我数学建模的事情,我暂时不想回答(还有为毛踩我文章…..我本来就不是写数学建模的……╮(╯▽╰)╭)(2017/10/31)

原问题是给出一个定价策略,证明其相较于原来定价策略的优点.

那么首先我们第一题第二问得到了一个 价格-完成率 函数,此时我们需要的是给出一个新的定价函数,并利用遗传算法得到最佳参数.

思路

1. 编码–>我们需要编码的是定价函数的参数
2. 评价函数—->将编码输入的定价函数得到价格,然后将价格输入之前得到的 价格-完成率 函数得到完成率
3. 求解的目标应当是最大化完成率
4. 为了控制成本需要对价格进行一定的限制,避免为了提高完成率,而过高定价
5. 阅读提示,建议阅读该部分前,阅读该基础文章http://blog.csdn.net/fontthrone/article/details/78253230

Types

import random

from deap import base
from deap import creator
from deap import tools

import time

ThresholdValue = 28.6670026583

creator.create("FitnessMax", base.Fitness, weights=(1.0,))  # 定义最大化适应度
creator.create("Individual", list, fitness=creator.FitnessMax)  # 这里的list种群的数据类型

toolbox = base.Toolbox()

# Attribute generator: define 'attr_bool' to be an attribute ('gene')
#                      which corresponds to integers sampled uniformly
#                      from the range [0,1] (i.e. 0 or 1 with equal
#                      probability)


toolbox.register("attr_bool", random.random)  # 包含了0,1的随机整数,初始化种群

# Structure initializers: define 'individual' to be an individual
#                         consisting of 100 'attr_bool' elements ('genes')
toolbox.register("individual", tools.initRepeat, creator.Individual,
                 toolbox.attr_bool, 5)

# define the population to be a list of 'individual's
toolbox.register("population", tools.initRepeat, list, toolbox.individual)

ReadData

读取数据,为之后的计算做准备

import pandas as pd

df2 = pd.read_csv('/home/fonttian/Data/MM2017/db.csv')

npones = df2['npones']
level = df2['level']
length = df2['length']
MiDu = df2['MiDu']
npjt = df2['npjt']
listlen = df2['listlen']
price = df2['price']

定义评价函数(适应度函数)

def evalOneMax(individual):
    newPrice = (individual[0] - 0.5) * npones * 20 + (individual[1] - 0.5) * length * 20 + (individual[2] - 0.5) * MiDu * 20 + (individual[3] - 0.5) * level * 20 + (individual[4]) * 100 +listlen * 65.7
    # npones,nplength,npMiDuList3
    w2 = [-0.01633732, 0.83539635, -0.06544261, -0.00280863]
    xjb = length * w2[0] + level * w2[1] + MiDu * w2[2] + npjt * w2[3]
    xjb = xjb * newPrice
    sums = 0
    for i in range(len(xjb)):
        # yuzhi = 28.6670026583
        # if xjb[i] >= yuzhi and newPrice[i] <= price[i] *1.1: # 608
        # if xjb[i] >= yuzhi: # 655
        # yuzhi = 0.474373718686

        if xjb[i] >= ThresholdValue and sum(newPrice) <= 57707.5 * 1.3: # 655
            sums += 1
        else:
            pass

    return sums, # 注意最后的 , 该文件中必须要有,不然会报错

注册其他参数(Operator registration)

# ---------------------Operator registration---------------------
toolbox.register("evaluate", evalOneMax)
toolbox.register("mate", tools.cxTwoPoint)
toolbox.register("mutate", tools.mutFlipBit, indpb=0.05)
toolbox.register("select", tools.selTournament, tournsize=3)

设计运行程序,获取我们想要的结果

def main():
    random.seed(64)
    # hash(64)is used

    # random.seed方法的作用是给随机数对象一个种子值，用于产生随机序列。
    # 对于同一个种子值的输入，之后产生的随机数序列也一样。
    # 通常是把时间秒数等变化值作为种子值，达到每次运行产生的随机系列都不一样

    # create an initial population of 300 individuals (where
    # each individual is a list of integers)
    pop = toolbox.population(n=300)  # 定义300个个体的种群

    # CXPB  is the probability with which two individuals
    #       are crossed
    #
    # MUTPB is the probability for mutating an individual
    #
    # NGEN  is the number of generations for which the
    #       evolution runs   迭代次数
    CXPB, MUTPB, NGEN = 0.5, 0.2, 100

    print("Start of evolution")

    # Evaluate the entire population
    fitnesses = list(map(toolbox.evaluate, pop))
    # for ind, fit in zip(pop, fitnesses):
    #     ind.fitness.values = fit

    print("  Evaluated %i individuals" % len(pop))  # 这时候，pop的长度还是300呢
    print("  迭代 %i 次" % NGEN)

    t1 = time.clock()
    # Begin the evolution      开始进化了哈！！！注意注意注意！就是一个for循环里了！NGEN次--代数
    for g in range(NGEN):
        if g % 10 == 0:
            print("-- Generation %i --" % g)

        # Select the next generation individuals
        offspring = toolbox.select(pop, len(pop))
        # Clone the selected individuals
        offspring = list(map(toolbox.clone, offspring))

        # Apply crossover and mutation on the offspring
        for child1, child2 in zip(offspring[::2], offspring[1::2]):

            # cross two individuals with probability CXPB
            if random.random() < CXPB:
                toolbox.mate(child1, child2)

                # fitness values of the children
                # must be recalculated later
                del child1.fitness.values
                del child2.fitness.values

        for mutant in offspring:

            # mutate an individual with probability MUTPB
            if random.random() < MUTPB:
                toolbox.mutate(mutant)
                del mutant.fitness.values

        # Evaluate the individuals with an invalid fitness
        invalid_ind = [ind for ind in offspring if not ind.fitness.valid]
        fitnesses = map(toolbox.evaluate, invalid_ind)
        for ind, fit in zip(invalid_ind, fitnesses):
            ind.fitness.values = fit

        # print("  Evaluated %i individuals" % len(invalid_ind))

        # The population is entirely replaced by the offspring
        pop[:] = offspring

        # Gather all the fitnesses in one list and print the stats
        fits = [ind.fitness.values[0] for ind in pop]

        length = len(pop)
        mean = sum(fits) / length
        sum2 = sum(x * x for x in fits)
        std = abs(sum2 / length - mean ** 2) ** 0.5

        # print("  Min %s" % min(fits))
        # print("  Max %s" % max(fits))
        # print("  Avg %s" % mean)
        # print("  Std %s" % std)

    print("-- End of (successful) evolution --")

    best_ind = tools.selBest(pop, 1)[0]
    print("Best individual is %s, %s" % (best_ind, best_ind.fitness.values))

    print('预测数据')
    # PevalOneMax([0.6222847026584997, 0.9952779203368345, 0.10901692485431957, 0.8966275594961192, 0.9692993203252058])
    print('该次遗传算法的出的最好的参数的通过数:')
    PevalOneMax(best_ind)

    print('出题方给的定价规律的预测通过数',TevalOneMax())
    t2 = time.clock()
    print(t2 - t1)

全部代码

# - * - coding: utf - 8 -*-
# 作者：田丰(FontTian)
# 创建时间:'2017/9/17'
#    This file is part of DEAP.
#
#    DEAP is free software: you can redistribute it and/or modify
#    it under the terms of the GNU Lesser General Public License as
#    published by the Free Software Foundation, either version 3 of
#    the License, or (at your option) any later version.
#
#    DEAP is distributed in the hope that it will be useful,
#    but WITHOUT ANY WARRANTY; without even the implied warranty of
#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
#    GNU Lesser General Public License for more details.
#
#    You should have received a copy of the GNU Lesser General Public
#    License along with DEAP. If not, see .


#    example which maximizes the sum of a list of integers
#    each of which can be 0 or 1

import random

from deap import base
from deap import creator
from deap import tools

import time

ThresholdValue = 28.6670026583

creator.create("FitnessMax", base.Fitness, weights=(1.0,))  # 定义最大化适应度
creator.create("Individual", list, fitness=creator.FitnessMax)  # 这里的list种群的数据类型

toolbox = base.Toolbox()

# Attribute generator: define 'attr_bool' to be an attribute ('gene')
#                      which corresponds to integers sampled uniformly
#                      from the range [0,1] (i.e. 0 or 1 with equal
#                      probability)


toolbox.register("attr_bool", random.random)  # 包含了0,1的随机整数,初始化种群

# Structure initializers: define 'individual' to be an individual
#                         consisting of 100 'attr_bool' elements ('genes')
toolbox.register("individual", tools.initRepeat, creator.Individual,
                 toolbox.attr_bool, 5)

# define the population to be a list of 'individual's
toolbox.register("population", tools.initRepeat, list, toolbox.individual)

import pandas as pd

df2 = pd.read_csv('/home/fonttian/Data/MM2017/db.csv')

npones = df2['npones']
level = df2['level']
length = df2['length']
MiDu = df2['MiDu']
npjt = df2['npjt']
listlen = df2['listlen']
price = df2['price']


def evalOneMax(individual):
    newPrice = (individual[0] - 0.5) * npones * 20 + (individual[1] - 0.5) * length * 20 + (individual[2] - 0.5) * MiDu * 20 + (individual[3] - 0.5) * level * 20 + (individual[4]) * 100 +listlen * 65.7
    # npones,nplength,npMiDuList3
    w2 = [-0.01633732, 0.83539635, -0.06544261, -0.00280863]
    xjb = length * w2[0] + level * w2[1] + MiDu * w2[2] + npjt * w2[3]
    xjb = xjb * newPrice
    sums = 0
    for i in range(len(xjb)):
        # yuzhi = 28.6670026583
        # if xjb[i] >= yuzhi and newPrice[i] <= price[i] *1.1: # 608
        # if xjb[i] >= yuzhi: # 655
        # yuzhi = 0.474373718686

        if xjb[i] >= ThresholdValue and sum(newPrice) <= 57707.5 * 1.3: # 655
            sums += 1
        else:
            pass

    return sums,

def PevalOneMax(individual):
    print((individual[0] - 0.5) * 20, (individual[1] - 0.5) * 20, (individual[2] - 0.5) * 20, (individual[3] - 0.5) * 20, (individual[4]) * 100)
    newPrice = (individual[0] - 0.5) * npones * 20 + (individual[1] - 0.5) * length * 20 + (individual[2] - 0.5) * MiDu * 20 + (individual[3] - 0.5) * level * 20 + (individual[4]) * 100
    w2 = [-0.01633732, 0.83539635, -0.06544261, -0.00280863]
    xjb = length * w2[0] + level * w2[1] + MiDu * w2[2] + npjt * w2[3]
    xjb = xjb * newPrice
    sums = 0
    for i in range(len(xjb)):
        if xjb[i] >= ThresholdValue:
            sums += 1
        else:
            pass

    print(sums)
    print("新的总价:",sum(newPrice),'旧的总价:',sum(price))

    return sums,

# ---------------------Operator registration---------------------
toolbox.register("evaluate", evalOneMax)
toolbox.register("mate", tools.cxTwoPoint)
toolbox.register("mutate", tools.mutFlipBit, indpb=0.05)
toolbox.register("select", tools.selTournament, tournsize=3)


def TevalOneMax():
    # 原定价模型的通过率
    w2 = [-0.01633732, 0.83539635, -0.06544261, -0.00280863]
    xjb = length * w2[0] + level * w2[1] + MiDu * w2[2] + npjt * w2[3]
    xjb = xjb * price
    sum = 0
    for i in range(len(xjb)):
        if xjb[i] >= ThresholdValue:
            sum += 1
        else:
            pass
    return sum

# --------------------- main ---------------------

def main():
    random.seed(64)
    # hash(64)is used

    # random.seed方法的作用是给随机数对象一个种子值，用于产生随机序列。
    # 对于同一个种子值的输入，之后产生的随机数序列也一样。
    # 通常是把时间秒数等变化值作为种子值，达到每次运行产生的随机系列都不一样

    # create an initial population of 300 individuals (where
    # each individual is a list of integers)
    pop = toolbox.population(n=300)  # 定义300个个体的种群

    # CXPB  is the probability with which two individuals
    #       are crossed
    #
    # MUTPB is the probability for mutating an individual
    #
    # NGEN  is the number of generations for which the
    #       evolution runs   迭代次数
    CXPB, MUTPB, NGEN = 0.5, 0.2, 100

    print("Start of evolution")

    # Evaluate the entire population
    fitnesses = list(map(toolbox.evaluate, pop))
    # for ind, fit in zip(pop, fitnesses):
    #     ind.fitness.values = fit

    print("  Evaluated %i individuals" % len(pop))  # 这时候，pop的长度还是300呢
    print("  迭代 %i 次" % NGEN)

    t1 = time.clock()
    # Begin the evolution      开始进化了哈！！！注意注意注意！就是一个for循环里了！NGEN次--代数
    for g in range(NGEN):
        if g % 10 == 0:
            print("-- Generation %i --" % g)

        # Select the next generation individuals
        offspring = toolbox.select(pop, len(pop))
        # Clone the selected individuals
        offspring = list(map(toolbox.clone, offspring))

        # Apply crossover and mutation on the offspring
        for child1, child2 in zip(offspring[::2], offspring[1::2]):

            # cross two individuals with probability CXPB
            if random.random() < CXPB:
                toolbox.mate(child1, child2)

                # fitness values of the children
                # must be recalculated later
                del child1.fitness.values
                del child2.fitness.values

        for mutant in offspring:

            # mutate an individual with probability MUTPB
            if random.random() < MUTPB:
                toolbox.mutate(mutant)
                del mutant.fitness.values

        # Evaluate the individuals with an invalid fitness
        invalid_ind = [ind for ind in offspring if not ind.fitness.valid]
        fitnesses = map(toolbox.evaluate, invalid_ind)
        for ind, fit in zip(invalid_ind, fitnesses):
            ind.fitness.values = fit

        # print("  Evaluated %i individuals" % len(invalid_ind))

        # The population is entirely replaced by the offspring
        pop[:] = offspring

        # Gather all the fitnesses in one list and print the stats
        fits = [ind.fitness.values[0] for ind in pop]

        length = len(pop)
        mean = sum(fits) / length
        sum2 = sum(x * x for x in fits)
        std = abs(sum2 / length - mean ** 2) ** 0.5

        # print("  Min %s" % min(fits))
        # print("  Max %s" % max(fits))
        # print("  Avg %s" % mean)
        # print("  Std %s" % std)

    print("-- End of (successful) evolution --")

    best_ind = tools.selBest(pop, 1)[0]
    print("Best individual is %s, %s" % (best_ind, best_ind.fitness.values))

    print('预测数据')
    # PevalOneMax([0.6222847026584997, 0.9952779203368345, 0.10901692485431957, 0.8966275594961192, 0.9692993203252058])
    print('该次遗传算法的出的最好的参数的通过数:')
    PevalOneMax(best_ind)

    print('出题方给的定价规律的预测通过数',TevalOneMax())
    t2 = time.clock()
    print(t2 - t1)

if __name__ == "__main__":
    # t1 = time.clock()
    main()
    # t2 = time.clock()
    # print(t2-t1)

下载数据文件

链接: https://pan.baidu.com/s/1gfcTzpx 密码: dibq

转载于:https://www.cnblogs.com/fonttian/p/8480726.html