Gekko feasible in smaller problem while infeasible in larger problem - python-3.x

I am trying to solve the problem as follows with Gekko in python.
I_s is an indicator variable in the problem whose value is 1 if theta is positive and 0 if theta is zero.
I wrote the problem in a code using Gekko, python.
In contrast to my previous posts, I add some constraints with respect to I, which is an indicator variable.
If I set N=10, the solution, theta is all zero, which is the result that I want.
But if I set N=100 or 200, the solution cannot be found. I cannot understand why this happens.
I want to check if theta is also zero in larger N (200).
Is there any way to solve this issue?
My code is as belows.
# Import package
from gekko import GEKKO
import numpy as np
# Define parameters
P_CO = 600 # $/tonCO
beta_CO2 = 1 # no unit
P_CO2 = 80 # $/tonCO2eq
E_ref = 3.1022616 # tonCO2eq/tonCO
E_dir = -1.600570692 # tonCO2eq/tonCO
E_indir_others = 0.3339226804 # tonCO2eq/tonCO
E_indir_elec_cons = 18.46607256 # GJ/tonCO
C1_CAPEX = 285695 # no unit
C2_CAPEX = 188.42 # no unit
C1_FOX = 82282 # no unit
C2_FOX = 24.094 # no unit
C1_ROX = 4471.5 # no unit
C2_ROX = 96.034 # no unit
C1_UOX = 7934.9 # no unit
C2_UOX = 986.9 # no unit
r = 0.08 # discount rate
N = 10 # number of scenarios
T = 30 # total time period
GWP_init = 0.338723235 # 2020 Electricity GWP in EU 27 countries
theta_max = 1600000 # Max capacity
# Function to make GWP_EU matrix (TxN matrix)
def Electricity_GWP(GWP_init, n_years, num_episodes):
GWP_mean = 0.36258224*np.exp(-0.16395611*np.arange(1, n_years+2)) + 0.03091272
GWP_mean = GWP_mean.reshape(-1,1)
GWP_Yearly = np.tile(GWP_mean, num_episodes)
noise = np.zeros((n_years+1, num_episodes))
stdev2050 = GWP_mean[-1] * 0.25
stdev = np.arange(0, stdev2050 * (1 + 1/n_years), stdev2050/n_years)
for i in range(n_years+1):
noise[i,:] = np.random.normal(0, stdev[i], num_episodes)
GWP_forecast = GWP_Yearly + noise
return GWP_forecast
GWP_EU = Electricity_GWP(GWP_init, T, N) # (T+1)*N matrix
GWP_EU = GWP_EU[1:,:] # T*N matrix
print(np.shape(GWP_EU))
# Build Gekko model
m = GEKKO(remote=False)
theta = m.Array(m.Var, N, lb=0, ub=theta_max)
I = m.Array(m.Var, N, lb=0, ub=1, integer=True)
demand = np.ones((T,1))
demand[0] = 8031887.589
for k in range(1,11):
demand[k] = demand[k-1] * 1.026
for k in range(11,21):
demand[k] = demand[k-1] * 1.016
for k in range(21,T):
demand[k] = demand[k-1] * 1.011
demand = 0.12 * demand
demand = np.tile(demand, N) # T*N matrix
print(np.shape(demand))
m3 = [[m.min3(demand[t,s],theta[s]) for t in range(T)] for s in range(N)]
obj = m.sum([sum([((1/(1+r))**(t+1))*((P_CO*m3[s][t]) \
+ (beta_CO2*P_CO2*m3[s][t]*(E_ref-E_dir-E_indir_others-E_indir_elec_cons*GWP_EU[t,s])) \
- (C1_CAPEX*I[s]+C2_CAPEX*theta[s]+C1_FOX*I[s]+C2_FOX*theta[s])\
- (C1_ROX*I[s]+C2_ROX*m3[s][t]+C1_UOX*I[s]+C2_UOX*m3[s][t])) for t in range(T)]) for s in range(N)])
for i in range(N):
m.Equation(theta[i]<=1000000*I[i])
m.Equation(-theta[i]<1000000*(1-I[i]))
# obj = m.sum([m.sum([((1/(1+r))**(t+1))*((P_CO*m.min3(demand[t,s], theta[s])) \
# + (beta_CO2*P_CO2*m.min3(demand[t,s], theta[s])*(E_ref-E_dir-E_indir_others-E_indir_elec_cons*GWP_EU[t,s])) \
# - (C1_CAPEX+C2_CAPEX*theta[s]+C1_FOX+C2_FOX*theta[s])-(C1_ROX+C2_ROX*m.min3(demand[t,s], theta[s])+C1_UOX+C2_UOX*m.min3(demand[t,s], theta[s]))) for t in range(T)]) for s in range(N)])
m.Maximize(obj/N)
m.solve(disp=True)
# s = m.sum(m.sum(((1/(1+r))**(t+1))*((P_CO*m.min3(demand[t,s], theta[s])) \
# + beta_CO2*P_CO2*m.min3(demand[t,s], theta[s])*(E_ref-E_dir-E_indir_others-E_indir_elec_cons*GWP_EU[t,s]) \
# - (C1_CAPEX + C2_CAPEX*theta[s]) - (C1_FOX + C2_FOX*theta[s]) - (C1_ROX + C2_ROX*m.min3(demand[t,s], theta[s])) - (C1_UOX + C2_UOX*m.min3(demand[t,s], theta[s])))
# for s in range(N)) for t in range(T))/N
print(theta)

I solved this issue by increasing the big M in the constraint for an indicator variable I, 1000000 to 10000000.
for i in range(N):
m.Equation(theta[i]<=10000000*I[i])
m.Equation(-theta[i]<10000000*(1-I[i]))
I didn't understand why this worked, but the result gave me the solution of 200*1 array with all zero.

Related

Negative degrees of fredom when using GEKKO python

I'm trying to solve the optimization problem as above.
And my code is as belows.
It worked, but I got the negative degrees of freedom problem.
And the objective value was also negative, which I did not expect to be. I expected the positive one.
I can't understand why this happened and don't know how this problem can be solved.
Can somebody give me a suggestion?
Code
# Import package
from gekko import GEKKO
import numpy as np
# Define parameters
P_CO = 600 # $/tonCO
beta_CO2 = 1 # no unit
P_CO2 = 60 # $/tonCO2eq
E_ref = 3.1022616 # tonCO2eq/tonCO
E_dir = -1.600570692 # tonCO2eq/tonCO
E_indir_others = 0.3339226804 # tonCO2eq/tonCO
E_indir_elec_cons = 18.46607256 # GJ/tonCO
C1_CAPEX = 285695 # no unit
C2_CAPEX = 188.42 # no unit
C1_FOX = 82282 # no unit
C2_FOX = 24.094 # no unit
C1_ROX = 4471.5 # no unit
C2_ROX = 96.034 # no unit
C1_UOX = 1983.7 # no unit
C2_UOX = 249.79 # no unit
r = 0.08 # discount rate
N = 10 # number of scenarios
T = 30 # total time period
GWP_init = 0.338723235 # 2020 Electricity GWP in EU 27 countries
theta_max = 1600000 # Max capacity
# Function to make GWP_EU matrix (TxN matrix)
def Electricity_GWP(GWP_init, n_years, num_episodes):
GWP_mean = 0.36258224*np.exp(-0.16395611*np.arange(1, n_years+2)) + 0.03091272
GWP_mean = GWP_mean.reshape(-1,1)
GWP_Yearly = np.tile(GWP_mean, num_episodes)
noise = np.zeros((n_years+1, num_episodes))
stdev2050 = GWP_mean[-1] * 0.25
stdev = np.arange(0, stdev2050 * (1 + 1/n_years), stdev2050/n_years)
for i in range(n_years+1):
noise[i,:] = np.random.normal(0, stdev[i], num_episodes)
GWP_forecast = GWP_Yearly + noise
return GWP_forecast
GWP_EU = Electricity_GWP(GWP_init, T, N) # (T+1)*N matrix
GWP_EU = GWP_EU[1:,:] # T*N matrix
print(np.shape(GWP_EU))
# Build Gekko model
m = GEKKO(remote=False)
theta = m.Array(m.Var, N, lb=0, ub=theta_max)
demand = np.ones((T,1))
demand[0] = 8031887.589
for k in range(1,11):
demand[k] = demand[k-1] * 1.026
for k in range(11,21):
demand[k] = demand[k-1] * 1.016
for k in range(21,T):
demand[k] = demand[k-1] * 1.011
demand = 0.12 * demand
demand = np.tile(demand, N) # T*N matrix
print(np.shape(demand))
obj = m.sum([m.sum([((1/(1+r))**(t+1))*((P_CO*m.min3(demand[t,s], theta[s])) \
+ (beta_CO2*P_CO2*m.min3(demand[t,s], theta[s])*(E_ref-E_dir-E_indir_others-E_indir_elec_cons*GWP_EU[t,s])) \
- (C1_CAPEX+C2_CAPEX*theta[s]+C1_FOX+C2_FOX*theta[s])-(C1_ROX+C2_ROX*m.min3(demand[t,s], theta[s])+C1_UOX+C2_UOX*m.min3(demand[t,s], theta[s]))) for t in range(T)]) for s in range(N)])
m.Maximize(obj/N)
m.solve()
Output message
(30, 10)
(30, 10)
----------------------------------------------------------------
APMonitor, Version 1.0.0
APMonitor Optimization Suite
----------------------------------------------------------------
--------- APM Model Size ------------
Each time step contains
Objects : 11
Constants : 0
Variables : 5121
Intermediates: 0
Connections : 321
Equations : 3901
Residuals : 3901
Number of state variables: 5121
Number of total equations: - 3911
Number of slack variables: - 2400
---------------------------------------
Degrees of freedom : -1190
* Warning: DOF <= 0
----------------------------------------------
Steady State Optimization with APOPT Solver
----------------------------------------------
Iter: 1 I: 0 Tm: 18.61 NLPi: 5 Dpth: 0 Lvs: 0 Obj: -1.87E+09 Gap: 0.00E+00
Successful solution
---------------------------------------------------
Solver : APOPT (v1.0)
Solution time : 18.619200000000003 sec
Objective : -1.8677021320161405E+9
Successful solution
---------------------------------------------------
The negative DOF warning is because of the slack variables that are created when using the min3() function. It is only a warning that if all of the inequalities are active then this could lead to an over-specified system of equations (more equations than variables). If there is a successful solution then this warning can be ignored.
The negative objective is because most solvers require a minimization of the objective. Gekko automatically converts m.Maximize(obj) to m.Minimize(-obj). This is an equivalent objective. If you'd like to report the maximization and the positive objective, use the following at the end:
print('Objective: ',-m.options.OBJFCNVAL)

Speed Up a for Loop - Python

I have a code that works perfectly well but I wish to speed up the time it takes to converge. A snippet of the code is shown below:
def myfunction(x, i):
y = x + (min(0, target[i] - data[i, :]x))*data[i]/(norm(data[i])**2))
return y
rows, columns = data.shape
start = time.time()
iterate = 0
iterate_count = []
norm_count = []
res = 5
x_not = np.ones(columns)
norm_count.append(norm(x_not))
iterate_count.append(0)
while res > 1e-8:
for row in range(rows):
y = myfunction(x_not, row)
x_not = y
iterate += 1
iterate_count.append(iterate)
norm_count.append(norm(x_not))
res = abs(norm_count[-1] - norm_count[-2])
print('Converge at {} iterations'.format(iterate))
print('Duration: {:.4f} seconds'.format(time.time() - start))
I am relatively new in Python. I will appreciate any hint/assistance.
Ax=b is the problem we wish to solve. Here, 'A' is the 'data' and 'b' is the 'target'
Ugh! After spending a while on this I don't think it can be done the way you've set up your problem. In each iteration over the row, you modify x_not and then pass the updated result to get the solution for the next row. This kind of setup can't be vectorized easily. You can learn the thought process of vectorization from the failed attempt, so I'm including it in the answer. I'm also including a different iterative method to solve linear systems of equations. I've included a vectorized version -- where the solution is updated using matrix multiplication and vector addition, and a loopy version -- where the solution is updated using a for loop to demonstrate what you can expect to gain.
1. The failed attempt
Let's take a look at what you're doing here.
def myfunction(x, i):
y = x + (min(0, target[i] - data[i, :] # x)) * (data[i] / (norm(data[i])**2))
return y
You subtract
the dot product of (the ith row of data and x_not)
from the ith row of target,
limited at zero.
You multiply this result with the ith row of data divided my the norm of that row squared. Let's call this part2
Then you add this to the ith element of x_not
Now let's look at the shapes of the matrices.
data is (M, N).
target is (M, ).
x_not is (N, )
Instead of doing these operations rowwise, you can operate on the entire matrix!
1.1. Simplifying the dot product.
Instead of doing data[i, :] # x, you can do data # x_not and this gives an array with the ith element giving the dot product of the ith row with x_not. So now we have data # x_not with shape (M, )
Then, you can subtract this from the entire target array, so target - (data # x_not) has shape (M, ).
So far, we have
part1 = target - (data # x_not)
Next, if anything is greater than zero, set it to zero.
part1[part1 > 0] = 0
1.2. Finding rowwise norms.
Finally, you want to multiply this by the row of data, and divide by the square of the L2-norm of that row. To get the norm of each row of a matrix, you do
rownorms = np.linalg.norm(data, axis=1)
This is a (M, ) array, so we need to convert it to a (M, 1) array so we can divide each row. rownorms[:, None] does this. Then divide data by this.
part2 = data / (rownorms[:, None]**2)
1.3. Add to x_not
Finally, we're adding each row of part1 * part2 to the original x_not and returning the result
result = x_not + (part1 * part2).sum(axis=0)
Here's where we get stuck. In your approach, each call to myfunction() gives a value of part1 that depends on target[i], which was changed in the last call to myfunction().
2. Why vectorize?
Using numpy's inbuilt methods instead of looping allows it to offload the calculation to its C backend, so it runs faster. If your numpy is linked to a BLAS backend, you can extract even more speed by using your processor's SIMD registers
The conjugate gradient method is a simple iterative method to solve certain systems of equations. There are other more complex algorithms that can solve general systems well, but this should do for the purposes of our demo. Again, the purpose is not to have an iterative algorithm that will perfectly solve any linear system of equations, but to show what kind of speedup you can expect if you vectorize your code.
Given your system
data # x_not = target
Let's define some variables:
A = data.T # data
b = data.T # target
And we'll solve the system A # x = b
x = np.zeros((columns,)) # Initial guess. Can be anything
resid = b - A # x
p = resid
while (np.abs(resid) > tolerance).any():
Ap = A # p
alpha = (resid.T # resid) / (p.T # Ap)
x = x + alpha * p
resid_new = resid - alpha * Ap
beta = (resid_new.T # resid_new) / (resid.T # resid)
p = resid_new + beta * p
resid = resid_new + 0
To contrast the fully vectorized approach with one that uses iterations to update the rows of x and resid_new, let's define another implementation of the CG solver that does this.
def solve_loopy(data, target, itermax = 100, tolerance = 1e-8):
A = data.T # data
b = data.T # target
rows, columns = data.shape
x = np.zeros((columns,)) # Initial guess. Can be anything
resid = b - A # x
resid_new = b - A # x
p = resid
niter = 0
while (np.abs(resid) > tolerance).any() and niter < itermax:
Ap = A # p
alpha = (resid.T # resid) / (p.T # Ap)
for i in range(len(x)):
x[i] = x[i] + alpha * p[i]
resid_new[i] = resid[i] - alpha * Ap[i]
# resid_new = resid - alpha * A # p
beta = (resid_new.T # resid_new) / (resid.T # resid)
p = resid_new + beta * p
resid = resid_new + 0
niter += 1
return x
And our original vector method:
def solve_vect(data, target, itermax = 100, tolerance = 1e-8):
A = data.T # data
b = data.T # target
rows, columns = data.shape
x = np.zeros((columns,)) # Initial guess. Can be anything
resid = b - A # x
resid_new = b - A # x
p = resid
niter = 0
while (np.abs(resid) > tolerance).any() and niter < itermax:
Ap = A # p
alpha = (resid.T # resid) / (p.T # Ap)
x = x + alpha * p
resid_new = resid - alpha * Ap
beta = (resid_new.T # resid_new) / (resid.T # resid)
p = resid_new + beta * p
resid = resid_new + 0
niter += 1
return x
Let's solve a simple system to see if this works first:
2x1 + x2 = -5
−x1 + x2 = -2
should give a solution of [-1, -3]
data = np.array([[ 2, 1],
[-1, 1]])
target = np.array([-5, -2])
print(solve_loopy(data, target))
print(solve_vect(data, target))
Both give the correct solution [-1, -3], yay! Now on to bigger things:
data = np.random.random((100, 100))
target = np.random.random((100, ))
Let's ensure the solution is still correct:
sol1 = solve_loopy(data, target)
np.allclose(data # sol1, target)
# Output: False
sol2 = solve_vect(data, target)
np.allclose(data # sol2, target)
# Output: False
Hmm, looks like the CG method doesn't work for badly conditioned random matrices we created. Well, at least both give the same result.
np.allclose(sol1, sol2)
# Output: True
But let's not get discouraged! We don't really care if it works perfectly, the point of this is to demonstrate how amazing vectorization is. So let's time this:
import timeit
timeit.timeit('solve_loopy(data, target)', number=10, setup='from __main__ import solve_loopy, data, target')
# Output: 0.25586539999994784
timeit.timeit('solve_vect(data, target)', number=10, setup='from __main__ import solve_vect, data, target')
# Output: 0.12008900000000722
Nice! A ~2x speedup simply by avoiding a loop while updating our solution!
For larger systems, this will be even better.
for N in [10, 50, 100, 500, 1000]:
data = np.random.random((N, N))
target = np.random.random((N, ))
t_loopy = timeit.timeit('solve_loopy(data, target)', number=10, setup='from __main__ import solve_loopy, data, target')
t_vect = timeit.timeit('solve_vect(data, target)', number=10, setup='from __main__ import solve_vect, data, target')
print(N, t_loopy, t_vect, t_loopy/t_vect)
This gives us:
N t_loopy t_vect speedup
00010 0.002823 0.002099 1.345390
00050 0.051209 0.014486 3.535048
00100 0.260348 0.114601 2.271773
00500 0.980453 0.240151 4.082644
01000 1.769959 0.508197 3.482822

Hyperbolic sin and cos of an array

I'm trying to define some function for an eady stream function model as shown in the next line:
# Geometry of the wave / domain / mean state:
Lx = 3800 # Zonal Wavelength in km
H = 10000 # tropopause height in meters
Shear = 30/H # shear in sec^-1
k = 2*np.pi/(Lx*1000) # wavenumber (zonal)
l = np.pi/3.e6 # meridional wavenumber in 1/m
# Constants:
cor = 2*(7.292e-5)*np.sin(np.pi/4) # Coriolis parameter
bv2 = 1.e-4 # buoyancy frequency squared
sigma = 2.e-6 # static stability parameter
R = 287 # gas constant
# Grid points on which fields are computed:
xx = np.linspace(0,1.5*Lx,151) # gridpoints in x
yy = np.linspace( -1500,1500,101) # gridpoints in y
zz = np.linspace(0,H,51) # gridpoints in z
# Set array for grid system in x, y, and z
x,y,z = np.meshgrid(xx*1000, yy*1000, zz)
# Define coefficients for the model
mu2 = ((bv2*(H**2))/cor**2)*(k**2 + l**2)
mu = np.sqrt(mu2)
c = (Shear*H/2) + ((Shear*H)/mu)*np.sqrt((mu/2 - coth(mu/2))*(mu/2 - tanh(mu/2)))
# Note: try switching this to (Shear*H/2) - (Shear*H/mu)*...
ci = np.imag(c)
cr = np.real(c)
t = 0*np.pi/(10*cr*k)
A = 2.e7 # streamfunction amplitude (arbitrary)
B = -A*Shear*H/(mu*c)
Psi_z = A*cosh(mu*z/H) + B*sinh(mu*z/H)
I noticed that I'm getting an error when it comes to taking the hyperbolic sin and cos of the array with the following message:
TypeError: cannot create mpf from array (mu*z/H) for both sin and cos.
I've never encountered this error message before, so I'm not familiar enough to try and figure out an approach to this error.

Monte Carlo simulation of a system of polymer chain

I want to perform Monte Carlo simulation to the particles which are interacting via Lennard-Jones potential + FENE potential. I'm getting negative values in the FENE potential which have the log value in it. The error is "RuntimeWarning: invalid value encountered in log return (-0.5 * K * R**2 * np.log(1-((np.sqrt(rij2) - r0) / R)**2))" The FENE potential is given by:
import numpy as np
def gen_chain(N, R0):
x = np.linspace(1, (N-1)*0.8*R0, num=N)
y = np.zeros(N)
z = np.zeros(N)
return np.column_stack((x, y, z))
def lj(rij2):
sig_by_r6 = np.power(sigma/rij2, 3)
sig_by_r12 = np.power(sig_by_r6, 2)
lje = 4.0 * epsilon * (sig_by_r12 - sig_by_r6)
return lje
def fene(rij2):
return (-0.5 * K * R**2 * np.log(1-((np.sqrt(rij2) - r0) / R)**2))
def total_energy(coord):
# Non-bonded
e_nb = 0
for i in range(N):
for j in range(i-1):
ri = coord[i]
rj = coord[j]
rij = ri - rj
rij2 = np.dot(rij, rij)
if (np.sqrt(rij2) < rcutoff):
e_nb += lj(rij2)
# Bonded
e_bond = 0
for i in range(1, N):
ri = coord[i]
rj = coord[i-1]
rij = ri - rj
rij2 = np.dot(rij, rij)
e_bond += fene(rij2)
return e_nb + e_bond
def move(coord):
trial = np.ndarray.copy(coord)
for i in range(N):
delta = (2.0 * np.random.rand(3) - 1) * max_delta
trial[i] += delta
return trial
def accept(delta_e):
beta = 1.0/T
if delta_e <= 0.0:
return True
random_number = np.random.rand(1)
p_acc = np.exp(-beta*delta_e)
if random_number < p_acc:
return True
return False
if __name__ == "__main__":
# FENE parameters
K = 40
R = 0.3
r0 = 0.7
# LJ parameters
sigma = r0/0.33
epsilon = 1.0
# MC parameters
N = 50 # number of particles
rcutoff = 2.5*sigma
max_delta = 0.01
n_steps = 10000000
T = 0.5
coord = gen_chain(N, R)
energy_current = total_energy(coord)
traj = open('traj.xyz', 'w')
for step in range(n_steps):
if step % 1000 == 0:
traj.write(str(N) + '\n\n')
for i in range(N):
traj.write("C %10.5f %10.5f %10.5f\n" % (coord[i][0], coord[i][1], coord[i][2]))
print(step, energy_current)
coord_trial = move(coord)
energy_trial = total_energy(coord_trial)
delta_e = energy_trial - energy_current
if accept(delta_e):
coord = coord_trial
energy_current = energy_trial
traj.close()
The problem is that calculating rij2 = np.dot(rij, rij) in total energy with the constant values you use is always a very small number. Looking at the expression inside the log used to calculate FENE, np.log(1-((np.sqrt(rij2) - r0) / R)**2), I first noticed that you're taking the square root of rij2 which is not consistent with the formula you provided.
Secondly, notice that ((rij2 - r0) / R)**2 is the same as ((r0 - rij2) / R)**2, since the sign gets lost when squaring. Because rij2 is very small (already in the first iteration -- I checked by printing the values), this will be more or less equal to ((r0 - 0.05)/R)**2 which will be a number bigger than 1. Once you subtract this value from 1 in the log expression, 1-((np.sqrt(rij2) - r0) / R)**2 will be equal to np.nan (standing for "Not A Number"). This will propagate through all the function calls (for example, calling energy_trial = total_energy(coord_trial) will effectively set energy_trial to np.nan), until an error will be raised by some function.
Maybe you could do something with np.isnan() call, documented here. Moreover, you should check how you iterate through the coord (there's some inconsistencies throughout the code) -- I suggest you check the code review community as well.

Why isn’t NUTS sampling with tt.dot or pm.math.dot?

I am trying to implement parts of Facebook's prophet with some help from this example.
https://github.com/luke14free/pm-prophet/blob/master/pmprophet/model.py
This goes well :), but I am having some problems with the dot product I don't understand. Note that I am implementing the linear trends.
ds = pd.to_datetime(df['dagindex'], format='%d-%m-%y')
m = pm.Model()
changepoint_prior_scale = 0.05
n_changepoints = 25
changepoints = pd.date_range(
start=pd.to_datetime(ds.min()),
end=pd.to_datetime(ds.max()),
periods=n_changepoints + 2
)[1: -1]
with m:
# priors
sigma = pm.HalfCauchy('sigma', 10, testval=1)
#trend
growth = pm.Normal('growth', 0, 10)
prior_changepoints = pm.Laplace('changepoints', 0, changepoint_prior_scale, shape=len(changepoints))
y = np.zeros(len(df))
# indexes x_i for the changepoints.
s = [np.abs((ds - i).values).argmin() for i in changepoints]
g = growth
x = np.arange(len(ds))
# delta
d = prior_changepoints
regression = x * g
base_piecewise_regression = []
for i in s:
local_x = x.copy()[:-i]
local_x = np.concatenate([np.zeros(i), local_x])
base_piecewise_regression.append(local_x)
piecewise_regression = np.array(base_piecewise_regression)
# this dot product doesn't work?
piecewise_regression = pm.math.dot(theano.shared(piecewise_regression).T, d)
# If I comment out this line and use that one as dot product. It works fine
# piecewise_regression = (piecewise_regression.T * d[None, :]).sum(axis=-1)
regression += piecewise_regression
y += regression
obs = pm.Normal('y',
mu=(y - df.gebruikers.mean()) / df.gebruikers.std(),
sd=sigma,
observed=(df.gebruikers - df.gebruikers.mean()) / df.gebruikers.std())
start = pm.find_MAP(maxeval=10000)
trace = pm.sample(500, step=pm.NUTS(), start=start)
If I run the snippet above with
piecewise_regression = (piecewise_regression.T * d[None, :]).sum(axis=-1)
the model works as expected. However I cannot get it to work with a dot product. The NUTS sampler doesn't sample at all.
piecewise_regression = pm.math.dot(theano.shared(piecewise_regression).T, d)
EDIT
Ive got a minimal working example
The problem still occurs with theano.shared. I’ve got a minimal working example:
np.random.seed(5)
n_changepoints = 10
t = np.arange(1000)
s = np.sort(np.random.choice(t, size=n_changepoints, replace=False))
a = (t[:, None] > s) * 1
real_delta = np.random.normal(size=n_changepoints)
y = np.dot(a, real_delta) * t
with pm.Model():
sigma = pm.HalfCauchy('sigma', 10, testval=1)
delta = pm.Laplace('delta', 0, 0.05, shape=n_changepoints)
g = tt.dot(a, delta) * t
obs = pm.Normal('obs',
mu=(g - y.mean()) / y.std(),
sd=sigma,
observed=(y - y.mean()) / y.std())
trace = pm.sample(500)
It seems to have something to do with the size of matrix a. NUTS doesnt’t sample if I start with
t = np.arange(1000)
however the example above does sample when I reduce the size of t to:
t = np.arange(100)

Resources