# Own graphical library
from graph_lib import gl
# Import functions independent of DataStructure
import utilities_lib as ul
# For statistics. Requires statsmodels 5.0 or more
# Analysis of Variance (ANOVA) on linear models
import basicMathlib as bMA
import DDBB_lib as DBl
import CEM as CEM
import CDistribution as Cdist
import specific_plotting_func as spf
gl.close("all")
##############################################
########## FLAGS ############################
trading_graph = 0
remove_gap_return = 1
preprocess_data = 1
perform_EM = 1
perform_HMM_after_EM = 0
final_clusters_graph = 1
responsibility_graph = 1
def generate_images_iterations_ll(Xs,mus,covs, Ks ,myDManager, logl,theta_list,model_theta_list,folder_images_gif):
# os.remove(folder_images_gif) # Remove previous images if existing
"""
WARNING: MEANT FOR ONLY 3 Distributions due to the color RGB
"""
import shutil
ul.create_folder_if_needed(folder_images_gif)
shutil.rmtree(folder_images_gif)
ul.create_folder_if_needed(folder_images_gif)
######## Plot the original data #####
Xdata = np.concatenate(Xs,axis = 1).T
colors = ["r","b","g"]
K_G,K_W,K_vMF = Ks
### FOR EACH ITERATION
for i in range(len(theta_list)): # theta_list
indx = i
gl.init_figure()
ax1 = gl.subplot2grid((1,2), (0,0), rowspan=1, colspan=1)
## Get the relative ll of the Gaussian denoising cluster.
ll = myDManager.pdf_log_K(Xdata,theta_list[indx])
N,K = ll.shape
# print ll.shape
for j in range(N): # For every sample
#TODO: Can this not be done without a for ?
# Normalize the probability of the sample being generated by the clusters
Marginal_xi_probability = gf.sum_logs(ll[j,:])
ll[j,:] = ll[j,:]- Marginal_xi_probability
ax1 = gl.scatter(Xdata[j,0],Xdata[j,1], labels = ['EM Evolution. Kg:'+str(K_G)+ ', Kw:' + str(K_W) + ', K_vMF:' + str(K_vMF), "X1","X2"],
color = (np.exp(ll[j,1]), np.exp(ll[j,0]), np.exp(ll[j,2])) , ### np.exp(ll[j,2])
alpha = 1, nf = 0)
# Only doable if the clusters dont die
for k_c in myDManager.clusterk_to_Dname.keys():
k = myDManager.clusterk_to_thetak[k_c]
distribution_name = myDManager.clusterk_to_Dname[k_c] # G W
if (distribution_name == "Gaussian"):
## Plot the ecolution of the mu
#### Plot the Covariance of the clusters !
mean,w,h,theta = bMA.get_gaussian_ellipse_params( mu = theta_list[indx][k][0], Sigma = theta_list[indx][k][1], Chi2val = 2.4477)
r_ellipse = bMA.get_ellipse_points(mean,w,h,theta)
gl.plot(r_ellipse[:,0], r_ellipse[:,1], ax = ax1, ls = "-.", lw = 3,
AxesStyle = "Normal2",
legend = ["Kg(%i). pi:%0.2f"%(k, float(model_theta_list[indx][0][0,k]))])
elif(distribution_name == "Watson"):
#### Plot the pdf of the distributino !
## Distribution parameters for Watson
kappa = float(theta_list[indx][k][1]); mu = theta_list[-1][k][0]
Nsa = 1000
# Draw 2D samples as transformation of the angle
Xalpha = np.linspace(0, 2*np.pi, Nsa)
Xgrid= np.array([np.cos(Xalpha), np.sin(Xalpha)])
probs = [] # Vector with probabilities
for i in range(Nsa):
probs.append(np.exp(Wad.Watson_pdf_log(Xgrid[:,i],[mu,kappa]) ))
probs = np.array(probs)
# Plot it in polar coordinates
X1_w = (1 + probs) * np.cos(Xalpha)
X2_w = (1 + probs) * np.sin(Xalpha)
gl.plot(X1_w,X2_w,
alpha = 1, lw = 3, ls = "-.", legend = ["Kw(%i). pi:%0.2f"%(k, float(model_theta_list[indx][0][0,k]))])
elif(distribution_name == "vonMisesFisher"):
#### Plot the pdf of the distributino !
## Distribution parameters for Watson
kappa = float(theta_list[indx][k][1]); mu = theta_list[indx][k][0]
Nsa = 1000
# Draw 2D samples as transformation of the angle
Xalpha = np.linspace(0, 2*np.pi, Nsa)
Xgrid= np.array([np.cos(Xalpha), np.sin(Xalpha)])
probs = [] # Vector with probabilities
for i in range(Nsa):
probs.append(np.exp(vMFd.vonMisesFisher_pdf_log(Xgrid[:,i],[mu,kappa]) ))
probs = np.array(probs)
probs = probs.reshape((probs.size,1)).T
# Plot it in polar coordinates
X1_w = (1 + probs) * np.cos(Xalpha)
X2_w = (1 + probs) * np.sin(Xalpha)
# print X1_w.shape, X2_w.shape
gl.plot(X1_w,X2_w,
alpha = 1, lw = 3, ls = "-.", legend = ["Kvmf(%i). pi:%0.2f"%(k, float(model_theta_list[indx][0][0,k]))])
gl.set_zoom(xlim = [-6,6], ylim = [-6,6], ax = ax1)
ax2 = gl.subplot2grid((1,2), (0,1), rowspan=1, colspan=1)
if (indx == 0):
gl.add_text(positionXY = [0.1,.5], text = r' Initilization Incomplete LogLike: %.2f'%(logl[0]),fontsize = 15)
pass
elif (indx >= 1):
gl.plot(range(1,np.array(logl).flatten()[1:].size +1),np.array(logl).flatten()[1:(indx+1)], ax = ax2,
legend = ["Iteration %i, Incom LL: %.2f"%(indx, logl[indx])], labels = ["Convergence of LL with generated data","Iterations","LL"], lw = 2)
gl.scatter(1, logl[1], lw = 2)
pt = 0.05
gl.set_zoom(xlim = [0,len(logl)], ylim = [logl[1] - (logl[-1]-logl[1])*pt,logl[-1] + (logl[-1]-logl[1])*pt], ax = ax2)
gl.subplots_adjust(left=.09, bottom=.10, right=.90, top=.95, wspace=.2, hspace=0.01)
gl.savefig(folder_images_gif +'gif_'+ str(indx) + '.png',
dpi = 100, sizeInches = [16, 8], close = "yes",bbox_inches = None)
gl.close("all")
from graph_lib import gl
import numpy as np
X = np.array(range(0, 100))
Y = np.sin(1.5 * (2 * np.pi / X.size) * X)
X2 = np.array(range(0, 50))
Y2 = (-15 + np.array(range(0, 50))) / 25.0
gl.close("all")
type_graph = 2
folder_images = "../pics/gl/"
dpi = 100
sizeInches = [2 * 8, 2 * 3]
# Subplot Type 1
if (type_graph == 1):
gl.set_subplots(nr=1, nc=2)
gl.plot(X,
Y,
nf=1,
color="k",
lw=5,
alpha=0.7,
labels=["Sine chart", "Time (s)", "Voltage(V)"],
legend=["Rolling measurement"])
gl.stem(X2,
Y2,
nf=1,
def generate_images_iterations_ll(Xs, mus, covs, Ks, myDManager, logl,
theta_list, model_theta_list,
folder_images_gif):
# os.remove(folder_images_gif) # Remove previous images if existing
"""
WARNING: MEANT FOR ONLY 3 Distributions due to the color RGB
"""
import shutil
ul.create_folder_if_needed(folder_images_gif)
shutil.rmtree(folder_images_gif)
ul.create_folder_if_needed(folder_images_gif)
######## Plot the original data #####
Xdata = np.concatenate(Xs, axis=1).T
colors = ["r", "b", "g"]
K_G, K_W, K_vMF = Ks
### FOR EACH ITERATION
for i in range(len(theta_list)): # theta_list
indx = i
gl.init_figure()
ax1 = gl.subplot2grid((1, 2), (0, 0), rowspan=1, colspan=1)
## Get the relative ll of the Gaussian denoising cluster.
ll = myDManager.pdf_log_K(Xdata, theta_list[indx])
N, K = ll.shape
# print ll.shape
for j in range(N): # For every sample
#TODO: Can this not be done without a for ?
# Normalize the probability of the sample being generated by the clusters
Marginal_xi_probability = gf.sum_logs(ll[j, :])
ll[j, :] = ll[j, :] - Marginal_xi_probability
ax1 = gl.scatter(
Xdata[j, 0],
Xdata[j, 1],
labels=[
'EM Evolution. Kg:' + str(K_G) + ', Kw:' + str(K_W) +
', K_vMF:' + str(K_vMF), "X1", "X2"
],
color=(np.exp(ll[j, 1]), np.exp(ll[j, 0]),
np.exp(ll[j, 2])), ### np.exp(ll[j,2])
alpha=1,
nf=0)
# Only doable if the clusters dont die
for k_c in myDManager.clusterk_to_Dname.keys():
k = myDManager.clusterk_to_thetak[k_c]
distribution_name = myDManager.clusterk_to_Dname[k_c] # G W
if (distribution_name == "Gaussian"):
## Plot the ecolution of the mu
#### Plot the Covariance of the clusters !
mean, w, h, theta = bMA.get_gaussian_ellipse_params(
mu=theta_list[indx][k][0],
Sigma=theta_list[indx][k][1],
Chi2val=2.4477)
r_ellipse = bMA.get_ellipse_points(mean, w, h, theta)
gl.plot(r_ellipse[:, 0],
r_ellipse[:, 1],
ax=ax1,
ls="-.",
lw=3,
AxesStyle="Normal2",
legend=[
"Kg(%i). pi:%0.2f" %
(k, float(model_theta_list[indx][0][0, k]))
])
elif (distribution_name == "Watson"):
#### Plot the pdf of the distributino !
## Distribution parameters for Watson
kappa = float(theta_list[indx][k][1])
mu = theta_list[-1][k][0]
Nsa = 1000
# Draw 2D samples as transformation of the angle
Xalpha = np.linspace(0, 2 * np.pi, Nsa)
Xgrid = np.array([np.cos(Xalpha), np.sin(Xalpha)])
probs = [] # Vector with probabilities
for i in range(Nsa):
probs.append(
np.exp(Wad.Watson_pdf_log(Xgrid[:, i], [mu, kappa])))
probs = np.array(probs)
# Plot it in polar coordinates
X1_w = (1 + probs) * np.cos(Xalpha)
X2_w = (1 + probs) * np.sin(Xalpha)
gl.plot(X1_w,
X2_w,
alpha=1,
lw=3,
ls="-.",
legend=[
"Kw(%i). pi:%0.2f" %
(k, float(model_theta_list[indx][0][0, k]))
])
elif (distribution_name == "vonMisesFisher"):
#### Plot the pdf of the distributino !
## Distribution parameters for Watson
kappa = float(theta_list[indx][k][1])
mu = theta_list[indx][k][0]
Nsa = 1000
# Draw 2D samples as transformation of the angle
Xalpha = np.linspace(0, 2 * np.pi, Nsa)
Xgrid = np.array([np.cos(Xalpha), np.sin(Xalpha)])
probs = [] # Vector with probabilities
for i in range(Nsa):
probs.append(
np.exp(
vMFd.vonMisesFisher_pdf_log(
Xgrid[:, i], [mu, kappa])))
probs = np.array(probs)
probs = probs.reshape((probs.size, 1)).T
# Plot it in polar coordinates
X1_w = (1 + probs) * np.cos(Xalpha)
X2_w = (1 + probs) * np.sin(Xalpha)
# print X1_w.shape, X2_w.shape
gl.plot(X1_w,
X2_w,
alpha=1,
lw=3,
ls="-.",
legend=[
"Kvmf(%i). pi:%0.2f" %
(k, float(model_theta_list[indx][0][0, k]))
])
gl.set_zoom(xlim=[-6, 6], ylim=[-6, 6], ax=ax1)
ax2 = gl.subplot2grid((1, 2), (0, 1), rowspan=1, colspan=1)
if (indx == 0):
gl.add_text(positionXY=[0.1, .5],
text=r' Initilization Incomplete LogLike: %.2f' %
(logl[0]),
fontsize=15)
pass
elif (indx >= 1):
gl.plot(
range(1,
np.array(logl).flatten()[1:].size + 1),
np.array(logl).flatten()[1:(indx + 1)],
ax=ax2,
legend=["Iteration %i, Incom LL: %.2f" % (indx, logl[indx])],
labels=[
"Convergence of LL with generated data", "Iterations", "LL"
],
lw=2)
gl.scatter(1, logl[1], lw=2)
pt = 0.05
gl.set_zoom(xlim=[0, len(logl)],
ylim=[
logl[1] - (logl[-1] - logl[1]) * pt,
logl[-1] + (logl[-1] - logl[1]) * pt
],
ax=ax2)
gl.subplots_adjust(left=.09,
bottom=.10,
right=.90,
top=.95,
wspace=.2,
hspace=0.01)
gl.savefig(folder_images_gif + 'gif_' + str(indx) + '.png',
dpi=100,
sizeInches=[16, 8],
close="yes",
bbox_inches=None)
gl.close("all")