I am running an mapply loop on a huge set of data to graph 13 parameters for 19 groups. This is working great except the p-value position. Due to the data varying for each plot I cannot assign position using label.y = 125 for example, in some plots it is in the middle of the bar/error bar. However, I can't assign it higher without having it way to high on other graphs. Is there a way to adjust to the data and error bars?
This is my graphing function and like I said the graph is great, except p-value position. Specifically, the stat compare means anova line.
ANOVA_plotter <- function(Variable, treatment, Grouping, df){
Inputdf <- df %>%
filter(Media == treatment, Group == Grouping) %>%
ggplot(aes_(x = ~ID, y = as.name(Variable))) +
geom_bar(aes(fill = ANOVA_Status), stat = "summary", fun = "mean", width = 0.9) +
stat_summary(geom = "errorbar", fun.data = "mean_sdl", fun.args = list(mult = 1), size = 1) +
labs(title = paste(Variable, "in", treatment, "in Group", Grouping, sep = " ")) +
theme(legend.position = "none",axis.title.x=element_blank(), axis.text = element_text(face="bold", size = 18 ), axis.text.x = element_text(angle = 45, hjust = 1)) +
stat_summary(geom = "errorbar", fun.data = "mean_sdl", fun.args = list(mult = 1), width = 0.2) +
stat_compare_means(method = "anova", label.y = 125) +
stat_compare_means(label = "p.signif", method = "t.test", paired = FALSE, ref.group = "Control")
}
I get graphs that look like this
(https://i.stack.imgur.com/hV9Ad.jpg)
But I can't assign it to label.y = 200 because of plots like this
(https://i.stack.imgur.com/uStez.jpg)
I'm working with 2 imu's. I need to offset all frames with the first frame from the sensor. I have created a fictive scenario, where I precisely know the rotation and the wanted result. I need the two sensors to show the same result when their initial (start) orientation is subtracted.
import numpy as np
# Sensor 0,1 and 2 start orientation in degrees
s0_x = 30
s0_y = 0
s0_z = 0
s1_x = 0
s1_y = 40
s1_z = 0
s2_x = 10
s2_y = 40
s2_z= -10
# Change from start frame 1
x1 = 20
y1 = 10
z1 = 0
# Change from start frame 2
x2 = 60
y2 = 30
z2 = 30
GCS= [[1,0,0],[0,1,0],[0,0,1]]
sensor0 = [[s0_x, s0_y, s0_z], [s0_x, s0_y, s0_z], [s0_x, s0_y, s0_z]]
sensor1 = [[s1_x, s1_y, s1_z], [s1_x + x1, s1_y + y1, s1_z + z1],[s1_x + x1 + x2, s1_y + y1+ y2, s1_z + z1+ z2]]
sensor2 = [[s2_x, s2_y, s2_z], [s2_x + x1, s2_y + y1, s2_z + z1], [s2_x + x1+ x2, s2_y + y1+ y2, s2_z + z1+ z2]]
def Rot_Mat_X(theta):
r = np.array([[1,0,0],[0,np.cos(np.deg2rad(theta)),-np.sin(np.deg2rad(theta))],[0,np.sin(np.deg2rad(theta)),np.cos(np.deg2rad(theta))]])
return r
# rotation the rotation matrix around the Y axis (input in deg)
def Rot_Mat_Y(theta):
r = np.array([[np.cos(np.deg2rad(theta)),0,np.sin(np.deg2rad(theta))],
[0,1,0],
[-np.sin(np.deg2rad(theta)),0,np.cos(np.deg2rad(theta))]])
return r
# rotation the rotation matrix around the Z axis (input in deg)
def Rot_Mat_Z(theta):
r = np.array([[np.cos(np.deg2rad(theta)),-np.sin(np.deg2rad(theta)),0],
[np.sin(np.deg2rad(theta)),np.cos(np.deg2rad(theta)),0],
[0,0,1]])
return r
# Creating the rotation matrices
r_sensor0 = []
r_sensor1= []
r_sensor2= []
for i in range(len(sensor1)):
r_sensor1_z = np.matmul(Rot_Mat_X(sensor1[i][0]),GCS)
r_sensor1_zy = np.matmul(Rot_Mat_Y(sensor1[i][1]),r_sensor1_z)
r_R_Upperarm_medial_zyx = np.matmul(Rot_Mat_Z(sensor1[i][2]),r_sensor1_zy )
r_sensor1.append(r_R_Upperarm_medial_zyx )
r_sensor2_z = np.matmul(Rot_Mat_X(sensor2[i][0]),GCS)
r_sensor2_zy = np.matmul(Rot_Mat_Y(sensor2[i][1]),r_sensor2_z )
r_sensor2_zyx = np.matmul(Rot_Mat_Z(sensor2[i][2]),r_sensor2_zy )
r_sensor2.append(r_sensor2_zyx )
r_start_sensor1 = r_sensor1[0]
r_start_sensor2 = r_sensor2[0]
r_offset_sensor1 = []
r_offset_sensor2 = []
for i in range(len(sensor0)):
r_offset_sensor1.append(np.matmul(np.transpose(r_start_sensor1),r_sensor1[i]))
r_offset_sensor2.append(np.matmul(np.transpose(r_start_sensor2),r_sensor2[i]))
# result:
r_offset_sensor1[0] = [[1,0,0],[0,1,0],[0,0,1]]
r_offset_sensor1[1] = [[0.984,0.059,0.163],[0,0.939,-0.342],[-0.173,0.336,0.925]]
r_offset_sensor1[2] = [[0.748,0.466,0.471],[0.086,0.635,-0.767],[-0.657,0.615,0.434]]
r_offset_sensor2[0] = [[1,0,0],[0,1,0],[0,0,1]]
r_offset_sensor2[1] = [[0.984,0.086,0.150],[-0.03,0.938,-0.344],[-0.171,0.334,0.926]]
r_offset_sensor2[2] = [[0.748,0.541,0.383],[-0.028,0.603,-0.797],[-0.662,0.585,0.466]]
I expect the result of sensors 1 and 2 to be equal for all frames but it doesn't? And they should be:
frame[0] = [1,0,0],[0,1,0],[0,0,1]
frame[1] = [0.984,0,0.173],[0.059,0.939,-0.336],[-0.163,0.342,0.9254]
frame[2] = [0.750,-0.433,0.50],[0.625,0.216,-0.750],[0.216,0.875,0.433]
I am doing a projectile motion where i need to plot curves between position x and y for various angles but the scilab shows only one plot. I am confused.
My code below
function[H,R,T]=projectile(m,r,h,c,rho,theta,v0,x0,y0,t0)
g=9.8
A=%pi*r^2
k=c*rho*A/2;
i=1
t(i)=t0
x(i)=x0
y(i)=y0
for j=0:5
thetha=theta+j*15;
vx(i)=v0*cos(thetha*%pi/180);
vy(i)=v0*sin(thetha*%pi/180);
while (y(i)>=0)
v=sqrt(vx(i)^2+vy(i)^2);
t(i+1)=t(i)+h;
vx(i+1)=vx(i)-h*(k*v*vx(i)/m);
vy(i+1)=vy(i)-h*(g+k*v*vy(i)/m);
x(i+1)=x(i)+h*vx(i)
y(i+1)=y(i)+h*vy(i)
i=i+1;
end
plot(x(i),y(i),'.');
end
n=i-1
R=x(n)-x(1);
T=t(n);
H=max(y)
endfunction
You should use vectors to improve compacity and readability of your code. Here is my proposition of improved (and working) code:
function [H,R,T] = projectile(m,r,h,c,rho,theta0,v0,x0,y0,t0)
g = 9.81
A = %pi*r^2
k = c*rho*A/2;
for theta = theta0 + (0:15:75)
v = v0*[cos(theta*%pi/180); sin(theta*%pi/180)];
t = t0
xy = [x0;y0]
i = 1
while xy(2,i) >= 0
t(i+1) = t(i)+h;
v = v + h*([0;-g] - k*norm(v)*v/m);
xy(:,i+1) = xy(:,i) + h*v;
i = i+1;
end
plot(xy(1,:), xy(2,:));
end
R = xy(1,$) - xy(1,1);
T = t($);
H = max(xy(2,:))
endfunction
clf
[H,R,T] = projectile(1,0.1,0.001,2,1000,5,1,0,0,0)
I implemented the LSDD changepoint detection method decribed in [1] in Julia, to see if I could make it faster than the existing python implementation [2], which is based on a grid search that looks for the optimal parameters.
I obtain the desired results but despite my best efforts, my grid search version of it takes about the same time to compute as the python one, which is still way too long for real applications.
I also tried using the Optimize package which only makes things worse (2 or 3 times slower).
Here is the grid search that I implemented :
using Random
using LinearAlgebra
function squared_distance(X::Array{Float64,1},C::Array{Float64,1})
sqd = zeros(length(X),length(C))
for i in 1:length(X)
for j in 1:length(C)
sqd[i,j] = X[i]^2 + C[j]^2 - 2*X[i]*C[j]
end
end
return sqd
end
function lsdd(x::Array{Float64,1},y::Array{Float64,1}; folds = 5, sigma_list = nothing , lambda_list = nothing)
lx,ly = length(x), length(y)
b = min(lx+ly,300)
C = shuffle(vcat(x,y))[1:b]
CC_dist2 = squared_distance(C,C)
xC_dist2, yC_dist2 = squared_distance(x,C), squared_distance(y,C)
Tx,Ty = length(x) - div(lx,folds), length(y) - div(ly,folds)
#Define the training and testing data sets
cv_split1, cv_split2 = floor.(collect(1:lx)*folds/lx), floor.(collect(1:ly)*folds/ly)
cv_index1, cv_index2 = shuffle(cv_split1), shuffle(cv_split2)
tr_idx1,tr_idx2 = [findall(x->x!=i,cv_index1) for i in 1:folds], [findall(x->x!=i,cv_index2) for i in 1:folds]
te_idx1,te_idx2 = [findall(x->x==i,cv_index1) for i in 1:folds], [findall(x->x==i,cv_index2) for i in 1:folds]
xTr_dist, yTr_dist = [xC_dist2[i,:] for i in tr_idx1], [yC_dist2[i,:] for i in tr_idx2]
xTe_dist, yTe_dist = [xC_dist2[i,:] for i in te_idx1], [yC_dist2[i,:] for i in te_idx2]
if sigma_list == nothing
sigma_list = [0.25, 0.5, 0.75, 1, 1.2, 1.5, 2, 2.5, 2.2, 3, 5]
end
if lambda_list == nothing
lambda_list = [1.00000000e-03, 3.16227766e-03, 1.00000000e-02, 3.16227766e-02,
1.00000000e-01, 3.16227766e-01, 1.00000000e+00, 3.16227766e+00,
1.00000000e+01]
end
#memory prealocation
score_cv = zeros(length(sigma_list),length(lambda_list))
H = zeros(b,b)
hx_tr, hy_tr = [zeros(b,1) for i in 1:folds], [zeros(b,1) for i in 1:folds]
hx_te, hy_te = [zeros(1,b) for i in 1:folds], [zeros(1,b) for i in 1:folds]
#h_tr,h_te = zeros(b,1), zeros(1,b)
theta = zeros(b)
for (sigma_idx,sigma) in enumerate(sigma_list)
#the expression of H is different for higher dimension
#H = sqrt((sigma^2)*pi)*exp.(-CC_dist2/(4*sigma^2))
set_H(H,CC_dist2,sigma,b)
#check if the sum is performed along the right dimension
set_htr(hx_tr,xTr_dist,sigma,Tx), set_htr(hy_tr,yTr_dist,sigma,Ty)
set_hte(hx_te,xTe_dist,sigma,lx-Tx), set_hte(hy_te,yTe_dist,sigma,ly-Ty)
for i in 1:folds
h_tr = hx_tr[i] - hy_tr[i]
h_te = hx_te[i] - hy_te[i]
#set_h(h_tr,hx_tr[i],hy_tr[i],b)
#set_h(h_te,hx_te[i],hy_te[i],b)
for (lambda_idx,lambda) in enumerate(lambda_list)
set_theta(theta,H,lambda,h_tr,b)
score_cv[sigma_idx,lambda_idx] += dot(theta,H*theta) - 2*dot(theta,h_te)
end
end
end
#retrieve the value of the optimal parameters
sigma_chosen = sigma_list[findmin(score_cv)[2][2]]
lambda_chosen = lambda_list[findmin(score_cv)[2][2]]
#calculating the new "optimal" solution
H = sqrt((sigma_chosen^2)*pi)*exp.(-CC_dist2/(4*sigma_chosen^2))
H_lambda = H + lambda_chosen*Matrix{Float64}(I, b, b)
h = (1/lx)*sum(exp.(-xC_dist2/(2*sigma_chosen^2)),dims = 1) - (1/ly)*sum(exp.(-yC_dist2/(2*sigma_chosen^2)),dims = 1)
theta_final = H_lambda\transpose(h)
f = transpose(theta_final).*sum(exp.(-vcat(xC_dist2,yC_dist2)/(2*sigma_chosen^2)),dims = 1)
L2 = 2*dot(theta_final,h) - dot(theta_final,H*theta_final)
return L2
end
function set_H(H::Array{Float64,2},dist::Array{Float64,2},sigma::Float64,b::Int16)
for i in 1:b
for j in 1:b
H[i,j] = sqrt((sigma^2)*pi)*exp(-dist[i,j]/(4*sigma^2))
end
end
end
function set_theta(theta::Array{Float64,1},H::Array{Float64,2},lambda::Float64,h::Array{Float64,2},b::Int64)
Hl = (H + lambda*Matrix{Float64}(I, b, b))
LAPACK.posv!('L', Hl, h)
theta = h
end
function set_htr(h::Array{Float64,1},dists::Array{Float64,2},sigma::Float64,T::Int16)
for (CVidx,dist) in enumerate(dists)
for (idx,value) in enumerate((1/T)*sum(exp.(-dist/(2*sigma^2)),dims = 1))
h[CVidx][idx] = value
end
end
end
function set_hte(h::Array{Float64,1},dists::Array{Float64,2},sigma::Array{Float64,1},T::Int16)
for (CVidx,dist) in enumerate(dists)
for (idx,value) in enumerate((1/T)*sum(exp.(-dist/(2*sigma^2)),dims = 1))
h[CVidx][idx] = value
end
end
end
function set_h(h,h1,h2,b)
for i in 1:b
h[i] = h1[i] - h2[i]
end
end
The set_H, set_h and set_theta functions are there because I read somewhere that modifying prealocated memory in place with a function was faster, but it did not make a great difference.
To test it, I use two random distribution as input data :
x,y = rand(500),1.5*rand(500)
lsdd(x,y) #returns a value around 0.3
Now here is the version of the code where I try to use Optimizer :
function Theta(sigma::Float64,lambda::Float64,x::Array{Float64,1},y::Array{Float64,1},folds::Int8)
lx,ly = length(x), length(y)
b = min(lx+ly,300)
C = shuffle(vcat(x,y))[1:b]
CC_dist2 = squared_distance(C,C)
xC_dist2, yC_dist2 = squared_distance(x,C), squared_distance(y,C)
#the subsets are not be mutually exclusive !
Tx,Ty = length(x) - div(lx,folds), length(y) - div(ly,folds)
shuffled_x, shuffled_y = [shuffle(1:lx) for i in 1:folds], [shuffle(1:ly) for i in 1:folds]
cv_index1, cv_index2 = floor.(collect(1:lx)*folds/lx)[shuffle(1:lx)], floor.(collect(1:ly)*folds/ly)[shuffle(1:ly)]
tr_idx1,tr_idx2 = [i[1:Tx] for i in shuffled_x], [i[1:Ty] for i in shuffled_y]
te_idx1,te_idx2 = [i[Tx:end] for i in shuffled_x], [i[Ty:end] for i in shuffled_y]
xTr_dist, yTr_dist = [xC_dist2[i,:] for i in tr_idx1], [yC_dist2[i,:] for i in tr_idx2]
xTe_dist, yTe_dist = [xC_dist2[i,:] for i in te_idx1], [yC_dist2[i,:] for i in te_idx2]
score_cv = 0
Id = Matrix{Float64}(I, b, b)
H = sqrt((sigma^2)*pi)*exp.(-CC_dist2/(4*sigma^2))
hx_tr, hy_tr = [transpose((1/Tx)*sum(exp.(-dist/(2*sigma^2)),dims = 1)) for dist in xTr_dist], [transpose((1/Ty)*sum(exp.(-dist/(2*sigma^2)),dims = 1)) for dist in yTr_dist]
hx_te, hy_te = [(lx-Tx)*sum(exp.(-dist/(2*sigma^2)),dims = 1) for dist in xTe_dist], [(ly-Ty)*sum(exp.(-dist/(2*sigma^2)),dims = 1) for dist in yTe_dist]
for i in 1:folds
h_tr, h_te = hx_tr[i] - hy_tr[i], hx_te[i] - hy_te[i]
#theta = (H + lambda * Id)\h_tr
theta = copy(h_tr)
Hl = (H + lambda*Matrix{Float64}(I, b, b))
LAPACK.posv!('L', Hl, theta)
score_cv += dot(theta,H*theta) - 2*dot(theta,h_te)
end
return score_cv,(CC_dist2,xC_dist2,yC_dist2)
end
function cost(params::Array{Float64,1},x::Array{Float64,1},y::Array{Float64,1},folds::Int8)
s,l = params[1],params[2]
return Theta(s,l,x,y,folds)[1]
end
"""
Performs the optinization
"""
function lsdd3(x::Array{Float64,1},y::Array{Float64,1}; folds = 4)
start = [1,0.1]
b = min(length(x)+length(y),300)
lx,ly = length(x),length(y)
#result = optimize(params -> cost(params,x,y,folds),fill(0.0,2),fill(50.0,2),start, Fminbox(LBFGS(linesearch=LineSearches.BackTracking())); autodiff = :forward)
result = optimize(params -> cost(params,x,y,folds),start, BFGS(),Optim.Options(f_calls_limit = 5, iterations = 5))
#bboptimize(rosenbrock2d; SearchRange = [(-5.0, 5.0), (-2.0, 2.0)])
#result = optimize(cost,[0,0],[Inf,Inf],start, Fminbox(AcceleratedGradientDescent()))
sigma_chosen,lambda_chosen = Optim.minimizer(result)
CC_dist2, xC_dist2, yC_dist2 = Theta(sigma_chosen,lambda_chosen,x,y,folds)[2]
H = sqrt((sigma_chosen^2)*pi)*exp.(-CC_dist2/(4*sigma_chosen^2))
h = (1/lx)*sum(exp.(-xC_dist2/(2*sigma_chosen^2)),dims = 1) - (1/ly)*sum(exp.(-yC_dist2/(2*sigma_chosen^2)),dims = 1)
theta_final = (H + lambda_chosen*Matrix{Float64}(I, b, b))\transpose(h)
f = transpose(theta_final).*sum(exp.(-vcat(xC_dist2,yC_dist2)/(2*sigma_chosen^2)),dims = 1)
L2 = 2*dot(theta_final,h) - dot(theta_final,H*theta_final)
return L2
end
No matter, which kind of option I use in the optimizer, I always end up with something too slow. Maybe the grid search is the best option, but I don't know how to make it faster... Does anyone have an idea how I could proceed further ?
[1] : http://www.mcduplessis.com/wp-content/uploads/2016/05/Journal-IEICE-2014-CLSDD-1.pdf
[2] : http://www.ms.k.u-tokyo.ac.jp/software.html