时间序列(一)

# -*- coding: utf-8 -*-
"""
Created on Fri Jan 13 11:20:10 2017

@author: DaiPuWei
"""

'''
    时间序列简单平移法：以预测12月份的销售收入为例
'''

import math

def Forecast(profit,N,month):
    '''
        预测函数：profit为销售收入数据
        N为预测周期，month为需要预测的月份
    '''
    result = []
    if month >=1 and month <= 12:
        #预测值
        forecast= 0
        for i in range(month-N-1,month-1):
            forecast += profit[i]
        forecast = forecast / 4
        result.append(forecast)

        #标准误差
        error = 0
        for i in range(N,len(profit)):
            tmp = forecast - profit[i]
            error = error + tmp * tmp
        error = error / (len(profit) - N)
        error = math.sqrt(error)
        result.append(error)
    else:
       print('月份不正确，请重新输入月份(1-12)')    
    return result

def run_main():
    '''
        这是组函数
    '''
    #销售收入
    profit = [553.8,574.6,606.9,649.8,705.1,772.0,816.4,892.7,963.9,1015.1,1102.7]

    #以4为预测周期的预测值
    forecast1 = Forecast(profit,4,12)

    #以4为预测周期的预测值
    forecast2 = Forecast(profit,5,12)

    if forecast1[1] < forecast2[1]:
        print('12月份的预测值为%g'%forecast1[0])
    else:
        print('12月份的预测值为%g'%forecast2[0])

if __name__ == '__main__':
    run_main()

# -*- coding: utf-8 -*-
"""
Created on Fri Jan 13 11:58:31 2017

@author: DaiPuWei
"""

'''
    时间序列加权移动平均法:以预测1989年原煤产量为例
'''

import pandas as pd

def Weighted_Forecast(data,weight,N):
    '''
        data是统计数据
        weight是权重
        N是预测周期
        index是要预测的下标
    '''

    #各个权重之和
    sum_weight = sum(weight)

    #预测值
    forecast  = 0
    length = len(data)

     #预测年份
    year = data.index[length-1]+1

    j = 0
    for i in range(length-N,length):
        forecast = forecast + weight[j] * data[data.columns[0]][data.index[i]]
        j = j + 1
    forecast = forecast / sum_weight
    print('%d年原煤产量未校对的预测值为:'%year)
    print(forecast)

    #data中数据的预测值
    forecast_data = []
    for i in range(N):
        forecast_data.append(data[data.columns[0]][data.index[i]])
    for i in range(N,length):
        tmp = 0
        k = 0
        for j in range(i-N,i):
            tmp = tmp + data[data.columns[0]][data.index[j]]*weight[k]
            k = k + 1
        forecast_data.append(tmp/sum_weight)
    print('所有的预测值为:')
    for i in range(length):
        print(data.index[i],forecast_data[i])

    #相对误差
    error_rate = []
    for i in range(length):
        error_rate.append(1-forecast_data[i]/data[data.columns[0]][data.index[i]])
    sum_error = sum(error_rate)
    sum_data = sum(data[data.columns[0]][data.index[N:]])
    avg_rate = 0

    #校正预测值
    forecast = forecast/(1-avg_rate)

    return forecast


def run_main():
    '''
        这是主函数
    '''

    #读取数据
    data = pd.read_excel('E:\\Program Files (x86)\\大学数学\\算法大全pdf\\第24章   时间序列模型\\原煤产量统计.xlsx')

    #周期数
    N = 3


    #权重
    weight = []
    for i in range(N):
        weight.append(i+1)

    forecast = Weighted_Forecast(data,weight,N)
    length = len(data)
    year = data.index[length-1]+1
    print('%d年的原煤产量预测值为:'%year)
    print(forecast)

if __name__ == '__main__':
    run_main()

# -*- coding: utf-8 -*-
"""
Created on Fri Jan 13 17:56:56 2017

@author: DaiPuWei
"""

'''
    时间序列趋势移动平均法，以1965-1985年发电总量为数据集合预测1986年与1987年
    的发电总量
'''

import pandas as pd

def Forecast(data,N):
    '''
        预测函数：data为销售收入数据
        N为预测周期,
    '''
    forecast_data = [] 
    length = len(data)
    for i in range(N,length):
        tmp = 0
        for j in range(i-N,i):
            tmp = tmp + data[j]
        tmp = tmp / N
        forecast_data.append(tmp)
    result = forecast_data[len(forecast_data)-1]

    return result,forecast_data

def Model(data,N,year,init):
    '''
        模型为:y(t+T) = a + b * T
        a = 2 * M1 - M2
        b = 2* (M1 - M2) / (N - 2)
    '''

    #一次移动平均的预测值以及预测数据
    M1,first_forecast = Forecast(data,N)

    #二次移动平均的预测值以及预测数据
    M2,Second_forecast = Forecast(first_forecast,N)

    #趋势移动平均模型参数a,b
    a = 2 * M1 - M2
    b = 2 *(M1 - M2) / (N - 2)
    print('预测模型为：y(T) = ',a,'+',b,'*(T-',init,')')

    #预测值
    forecast = a + b * (year -init)

    return forecast

def run_main():
    '''
        这是主函数
    '''

    #读取数据集
    sample = pd.read_excel('E:\\Program Files (x86)\\大学数学\\算法大全pdf\\第24章   时间序列模型\\1965-1985年发电总量统计.xlsx')
    data = sample['发电总量']

    #预测周期
    N = 6

    #初始年份
    init = sample['年份'][len(sample)-1]

    #1986年预测值
    forecast_1986 = Model(data,N,1986,init)
    print('1986年发电总量的预测值为:%f'%forecast_1986)

    #1987年预测值
    forecast_1987 = Model(data,N,1987,init)
    print('1987年发电总量的预测值为:%f'%forecast_1987)

if __name__ == '__main__':
    run_main()