我试图将理论模型与历史数据进行比较.我的计划是用Gekko将真实世界的数据从几个pandas数据框输入到方程中(跳到#方程#):
import pandas as pd
import pylab as plt
import numpy as np
from gekko import GEKKO
#DATA#
#oil supply
data = pd.read_html('https://www.eia.gov/dnav/pet/hist/LeafHandler.ashx?n=pet&s=mcrfpus2&f=m')
s=data[4]
sply = s.loc[s['Year'] >= 1984]
supplyvalues = sply.filter(items = ['Jan', 'Feb', 'Mar', 'Apr', 'May','Jun','Jul','Aug','Sep', 'Oct', 'Nov','Dec'])
val2 = supplyvalues.dropna()
protoval3 = supplyvalues.shift(1)
val3=protoval3.dropna()
#price of oil
p = pd.read_html('https://www.eia.gov/dnav/pet/hist/LeafHandler.ashx?n=PET&s=EMA_EPM0_PTG_NUS_DPG&f=M')
Op=p[4]
prc = Op.loc[Op['Year'] >= 1984]
pricevalues = prc.filter(items = ['Jan', 'Feb', 'Mar', 'Apr', 'May','Jun','Jul','Aug','Sep', 'Oct', 'Nov','Dec'])
val1 = pricevalues.dropna()
#EQUATION#
m=GEKKO()
tm = np.linspace(0,10,50)
t=m.Param(value = tm)
m.time = tm
m.options.IMODE=4
#forming equation
a,b,c = m.Array(m.Param,3)
a.value = val1.values
b.value = val2.values
c.value = val3.values
x = m.Var()
m.Equation(a == c-a*b)
m.solve(disp=False)
问题是，每次try 时，都会出现以下错误:
Exception: Data arrays must have the same length, and match time discretization in dynamic problems
我判断了数据帧的形状，它们是相等的，所以我不确定出了什么问题.有点烦，因为我觉得我真的很亲近.如果你能给我任何帮助，我将不胜感激！
p、 s:我还是一个编程初学者，所以如果你能描述一下你的新代码行的功能(如果你有)，我也会非常感激.这是完全可选的！