def db2(samples=1000):
import numpy as np
import testSystems as ts
var = 0.01
noise = np.sqrt(var)*np.random.randn(samples)
s = ts.testSystems(samples = samples+2, systemType = "4.2_AKB")
u = np.array([s[-samples-1:-1],s[-samples-2:-2]]).T
d = np.array(s[-samples:]).reshape(-1,1) + noise.reshape(-1,1)
return u,d
def db3(samples=1000):
import testSystems as ts
return ts.testSystems(samples=samples, systemType="4.1_AKB")
def kafSearch_MC(filterName,systemName,n_samples,trainSplit,MC_runs):
import KAF
from tqdm import tqdm
from sklearn.metrics import r2_score
from sklearn.metrics import mean_squared_error
import pandas as pd
import numpy as np
n_paramters = 0
# 1. Generate data for grid search
n_train = int(n_samples*trainSplit)
n_test = n_samples - n_train
folder = 'GridSearchWang2/'
attractors = ['lorenz','wang', 'rossler', 'rikitake']
if systemName in attractors:
signalEmbedding = 5
import TimeSeriesGenerator
inputSignal, y, z = TimeSeriesGenerator.chaoticSystem(samples=(n_samples+signalEmbedding)*MC_runs,systemType=systemName)
inputSignal -= inputSignal.mean()
inputSignal /= inputSignal.std()
y -= y.mean()
y /= y.std()
z -= z.mean()
z /= z.std()
elif systemName == "4.1":
signalEmbedding = 5
import testSystems as ts
inputSignal, targetSignal = ts.testSystems(samples = (n_samples+signalEmbedding)*MC_runs, systemType = "4.1_AKB")
# inputSignal -= inputSignal.mean()
# inputSignal /= inputSignal.std()
elif systemName == "4.2":
signalEmbedding = 2
import testSystems as ts
inputSignal = ts.testSystems(samples = (n_samples+signalEmbedding)*MC_runs, systemType = "4.2_AKB")
inputSignal -= inputSignal.mean()
inputSignal /= inputSignal.std()
else:
raise ValueError("Database does not exist")
# 2. Pick filter
if filterName == "QKLMS":
# 2.1. Generate parameters for QKLMS grid search
if systemName in attractors:
eta = [0.05, 0.1, 0.3, 0.5, 0.9]
sigma = [1e-2, 1e-1, 1, 2, 4, 8]
epsilon = [1e-1, 0.5, 1, 2]
elif systemName == "chua":
eta = [0.05, 0.1, 0.5, 0.9]
sigma = [1e-2, 1e-1, 0, 2, 4]
epsilon = [1e-2, 1e-1, 1,2]
elif systemName == "4.1":
eta = [0.05, 0.1, 0.5, 0.9]
sigma = [1e-2, 1e-1, 0, 2, 4]
epsilon = [1e-2, 1e-1, 1,2]
elif systemName == "4.2":
eta = [0.05, 0.1, 0.5, 0.9]
sigma = [1e-2, 1e-1, 0, 2, 4]
epsilon = [1e-2, 1e-1, 1,2]
params = [{'eta':et,'epsilon':ep, 'sigma':s } for et in eta for ep in epsilon for s in sigma]
# 2.2. Search over QKLMS with Montecarlo Simulation
results = []
testing_mse_xRun = []
CB_size_xRun = []
tradeOff_dist_xRun = []
signalPower = inputSignal.var()
singleRunDataSize = n_samples
trainLength = n_train
for run in range(MC_runs):
print("\n\nRunning Monte Carlo simulation #{}...\n".format(run))
try:
u_train, u_test, d_train, d_test = trainAndTestSplitWithEmbedding(inputSignal, targetSignal,signalEmbedding, run, singleRunDataSize, trainLength)
except:
u_train, u_test, d_train, d_test = customEmbeddingForKAFs(inputSignal, signalEmbedding, run, singleRunDataSize, trainLength)
# u_train, u_test, d_train, d_test = customExogenousEmbeddingForKAFs(inputSignal, y, z, signalEmbedding, run, singleRunDataSize, trainLength)
for p in tqdm(params):
try:
f = KAF.QKLMS(eta=p['eta'],epsilon=p['epsilon'],sigma=p['sigma'])
y = f.evaluate(u_train,d_train)
y_pred = f.predict(u_test)
err = d_test-y_pred.reshape(-1,1)
t_mse = np.mean(err**2)
testing_mse_xRun.append(t_mse/signalPower)
CB_size_xRun.append(len(f.CB))
except:
testing_mse_xRun.append(np.nan)
CB_size_xRun.append(np.nan)
allTestingMSEs = np.array(testing_mse_xRun).reshape(MC_runs,-1)
allCB_sizes = np.array(CB_size_xRun).reshape(MC_runs,-1)
testing_mse_average = np.nanmean(allTestingMSEs, axis=0)
CB_size_average = np.nanmean(allCB_sizes, axis=0)
tradeOff_distance = [tradeOffDistance(testing_mse_average[j],CB_size_average[j]/n_train) for j in range(len(params))]
results = [p for p in params]
results_df = pd.DataFrame(data=results)
results_df['testing_mse'] = testing_mse_average
results_df['CB_size'] = CB_size_average
results_df['CB_size'] = results_df['CB_size'].astype(int)
results_df['tradeOff_dist'] = tradeOff_distance
results_df.to_csv(folder + filterName + '_' + systemName + '_' + str(n_samples) + '.csv')
elif filterName == "QKLMS_AKB":
# 2.1. Generate parameters for QKLMS_AKB grid search
import numpy as np
if systemName in attractors:
eta = [0.05, 0.1, 0.3, 0.9]
sigma = [ 1e-1, 1, 2]
epsilon = [1e-1, 0.5, 1, 2]
mu = [1e-3, 1e-1, 0.1, 1]
K = [2,5,10,20]
elif systemName == "chua":
eta = [0.1, 0.5, 0.9]
sigma = [1e-2, 1e-1, 2, 4]
epsilon = [1e-2, 1e-1, 1]
mu = [1e-3, 1e-1, 0.1, 1]
K = [2,5,10,20]
elif systemName == "4.1":
eta = [0.1, 0.5, 0.9]
sigma = [1e-2, 1e-1, 2, 4]
epsilon = [1e-2, 1e-1, 1]
mu = [1e-3, 1e-1, 0.1, 1]
K = [2,5,10,20]
elif systemName == "4.2":
eta = [0.1, 0.5, 0.9]
sigma = [1e-2, 1e-1, 2, 4]
epsilon = [1e-2, 1e-1, 1]
mu = [1e-3, 1e-1, 0.1, 1]
K = [2,5,10,20]
params = [{'eta':et,'epsilon':ep, 'sigma_init':s, 'mu':m, 'K':int(k) } for et in eta for ep in epsilon for s in sigma for m in mu for k in K]
# 2.2. Search over QKLMS AKB with Montecarlo Simulation
results = []
testing_mse_xRun = []
CB_size_xRun = []
tradeOff_dist_xRun = []
signalPower = inputSignal.var()
singleRunDataSize = n_samples
trainLength = n_train
for run in range(MC_runs):
print("\n\nRunning Monte Carlo simulation #{}...\n".format(run))
try:
u_train, u_test, d_train, d_test = trainAndTestSplitWithEmbedding(inputSignal, targetSignal,signalEmbedding, run, singleRunDataSize, trainLength)
except:
# u_train, u_test, d_train, d_test = customEmbeddingForKAFs(inputSignal, signalEmbedding, run, singleRunDataSize, trainLength)
u_train, u_test, d_train, d_test = customExogenousEmbeddingForKAFs(inputSignal, y, z, signalEmbedding, run, singleRunDataSize, trainLength)
for p in tqdm(params):
try:
f = KAF.QKLMS_AKB(eta=p['eta'],epsilon=p['epsilon'],sigma_init=p['sigma_init'], mu=p['mu'], K=p['K'])
y = f.evaluate(u_train,d_train)
y_pred = f.predict(u_test)
err = d_test-y_pred.reshape(-1,1)
t_mse = np.mean(err**2)
testing_mse_xRun.append(t_mse/signalPower)
CB_size_xRun.append(len(f.CB))
except:
testing_mse_xRun.append(np.nan)
CB_size_xRun.append(np.nan)
allTestingMSEs = np.array(testing_mse_xRun).reshape(MC_runs,-1)
allCB_sizes = np.array(CB_size_xRun).reshape(MC_runs,-1)
testing_mse_average = np.nanmean(allTestingMSEs, axis=0)
CB_size_average = np.nanmean(allCB_sizes, axis=0)
tradeOff_distance = [tradeOffDistance(testing_mse_average[j],CB_size_average[j]/n_train) for j in range(len(params))]
results = [p for p in params]
results_df = pd.DataFrame(data=results)
results_df['testing_mse'] = testing_mse_average
results_df['CB_size'] = CB_size_average
results_df['CB_size'] = results_df['CB_size'].astype(int)
results_df['tradeOff_dist'] = tradeOff_distance
results_df.to_csv(folder + filterName + '_' + systemName + '_' + str(n_samples) + '.csv')
elif filterName == "QKLMS_AMK":
# 2.1. Generate parameters for QKLMS_AKB grid search
import numpy as np
if systemName in attractors:
mu = [0.1, 0.5,1,1.5]
eta = [0.05, 0.1, 0.3, 0.5, 0.9]
epsilon = [1e-1, 0.5, 1, 2]
K = [5,10,15,20]
elif systemName == "chua":
eta = np.linspace(0.02,1,n_paramters)
epsilon = np.linspace(1e-3,100,n_paramters)
mu = np.linspace(1e-4,1,n_paramters)
K = np.linspace(2,20,n_paramters)
elif systemName == "4.1":
mu = [1e-3,1e-1, 0.1,1]
eta = [0.05, 0.1,0.5,0.9]
epsilon = [1e-2, 1e-1, 1, 1.5, 2]
K = [2,5,10,15,20]
elif systemName == "4.2":
mu = [1e-3,1e-1, 0.1,1]
eta = [0.05, 0.1,0.5,0.9]
epsilon = [1e-2, 1e-1, 1, 1.5, 2]
K = [2,5,10,15,20]
params = [{'eta':et,'epsilon':ep, 'mu':m, 'K':int(k)} for et in eta for ep in epsilon for m in mu for k in K]
# 2.2. Search over QKLMS_AMK with Montecarlo Simulation
results = []
testing_mse_xRun = []
CB_size_xRun = []
tradeOff_dist_xRun = []
signalPower = inputSignal.var()
singleRunDataSize = n_samples
trainLength = n_train
for run in range(MC_runs):
print("\n\n Running Monte Carlo simulation #{}...\n".format(run))
try:
u_train, u_test, d_train, d_test = trainAndTestSplitWithEmbedding(inputSignal, targetSignal,signalEmbedding, run, singleRunDataSize, trainLength)
except:
u_train, u_test, d_train, d_test = customEmbeddingForKAFs(inputSignal, signalEmbedding, run, singleRunDataSize, trainLength)
# u_train, u_test, d_train, d_test = customExogenousEmbeddingForKAFs(inputSignal, y, z, signalEmbedding, run, singleRunDataSize, trainLength)
for p in tqdm(params):
try:
f = KAF.QKLMS_AMK(eta=p['eta'],epsilon=p['epsilon'], mu=p['mu'], Ka=p['K'], A_init="pca")
y = f.evaluate(u_train,d_train)
y_pred = f.predict(u_test)
err = d_test-y_pred.reshape(-1,1)
t_mse = np.mean(err**2)
testing_mse_xRun.append(t_mse/signalPower)
CB_size_xRun.append(len(f.CB))
except:
testing_mse_xRun.append(np.nan)
CB_size_xRun.append(np.nan)
allTestingMSEs = np.array(testing_mse_xRun).reshape(MC_runs,-1)
allCB_sizes = np.array(CB_size_xRun).reshape(MC_runs,-1)
testing_mse_average = np.nanmean(allTestingMSEs, axis=0)
CB_size_average = np.nanmean(allCB_sizes, axis=0)
tradeOff_distance = [tradeOffDistance(testing_mse_average[j],CB_size_average[j]/n_train) for j in range(len(params))]
results = [p for p in params]
results_df = pd.DataFrame(data=results)
results_df['testing_mse'] = testing_mse_average
results_df['CB_size'] = CB_size_average
results_df['CB_size'] = results_df['CB_size'].astype(int)
results_df['tradeOff_dist'] = tradeOff_distance
results_df.to_csv(folder + filterName + '_' + systemName + '_' + str(n_samples) + '.csv')
else:
raise ValueError("Filter does not exist")
return
def kafSearch(filterName,systemName,n_samples,trainSplit):
import KAF
from tqdm import tqdm
from sklearn.metrics import r2_score
from sklearn.metrics import mean_squared_error
import pandas as pd
import numpy as np
n_paramters = 0
# 1. Generate data for grid search
n_train = int(n_samples*trainSplit)
n_test = n_samples - n_train
if systemName == "lorenz" or systemName == "chua":
embedding = 5
import TimeSeriesGenerator
x, y, z = TimeSeriesGenerator.chaoticSystem(samples=200000,systemType='lorenz')
x -= x.mean()
x /= x.std()
u_train = np.array([x[i-embedding:i] for i in range(embedding,n_train)])
d_train = np.array([x[i] for i in range(embedding,n_train)]).reshape(-1,1)
u_test = np.array([x[i-embedding:i] for i in range(n_train,n_samples)])
d_test = np.array([x[i] for i in range(n_train,n_samples)]).reshape(-1,1)
elif systemName == "4.2":
embedding = 2
import testSystems as ts
x = ts.testSystems(samples = n_samples+embedding, systemType = "4.2_AKB")
x -= x.mean()
x /= x.std()
u_train = np.array([x[i-embedding:i] for i in range(embedding,n_train)])
d_train = np.array([x[i] for i in range(embedding,n_train)]).reshape(-1,1)
u_test = np.array([x[i-embedding:i] for i in range(n_train,n_samples)])
d_test = np.array([x[i] for i in range(n_train,n_samples)]).reshape(-1,1)
else:
raise ValueError("Database does not exist")
# 2. Pick filter
if filterName == "QKLMS":
# 2.1. Generate parameters for QKLMS grid search
import numpy as np
if systemName == "lorenz":
eta = [0.1, 0.5, 0.9]
sigma = [1e-2, 1e-1, 0, 2, 4]
epsilon = [1e-2, 1e-1, 1]
elif systemName == "chua":
# eta = np.linspace(0.1,0.9,n_paramters)
# sigma = np.linspace(100,500,n_paramters)
# epsilon = np.linspace(0.01,20,n_paramters)
a = 0
elif systemName == "4.2":
eta = [0.1, 0.5, 0.9]
sigma = [1e-2, 1e-1, 0, 2, 4]
epsilon = [1e-2, 1e-1, 1]
params = [{'eta':et,'epsilon':ep, 'sigma':s } for et in eta for ep in epsilon for s in sigma]
# 2.2. Search over QKLMS
results = []
for p in tqdm(params):
try:
f = KAF.QKLMS(eta=p['eta'],epsilon=p['epsilon'],sigma=p['sigma'])
y = f.evaluate(u_train,d_train)
y_pred = f.predict(u_test)
err = d_test-y_pred.reshape(-1,1)
t_mse = np.mean(err**2)
signalPower = x.var()
p['testing_mse'] = t_mse/signalPower
p['CB_size'] = len(f.CB)
p['tradeOff_dist'] = tradeOffDistance(p['testing_mse'],p['CB_size']/n_train)
except:
p['testing_mse'] = np.nan
p['CB_size'] = np.nan
p['tradeOff_dist'] = np.nan
results.append(p)
pd.DataFrame(data=results).to_csv('GridSearchResults2ndRun/' + filterName + '_' + systemName + '_' + str(n_samples) + '.csv')
elif filterName == "QKLMS_AKB":
# 2.1. Generate parameters for QKLMS_AKB grid search
import numpy as np
if systemName == "lorenz":
eta = [0.1, 0.9]
sigma = [1e-2, 1e-1, 2]
epsilon = [1e-2, 1e-1, 1]
mu = [1e-3, 1e-1, 0.1,1]
K = [2,5,10,20]
elif systemName == "chua":
eta = np.linspace(0.1,0.9,n_paramters)
sigma = np.linspace(0.01,200,n_paramters)
epsilon = np.linspace(1e-3,100,n_paramters)
mu = np.linspace(1e-4,1,n_paramters)
K = np.linspace(2,20,n_paramters)
elif systemName == "4.2":
eta = np.linspace(0.1,0.9,n_paramters)
sigma = np.linspace(0.01,200,n_paramters)
epsilon = np.linspace(1e-3,100,n_paramters)
mu = np.linspace(1e-4,1,n_paramters)
K = np.linspace(2,20,n_paramters)
params = [{'eta':et,'epsilon':ep, 'sigma_init':s, 'mu':m, 'K':int(k) } for et in eta for ep in epsilon for s in sigma for m in mu for k in K]
# 2.2. Search over QKLMS
results = []
for p in tqdm(params):
try:
f = KAF.QKLMS_AKB(eta=p['eta'],epsilon=p['epsilon'],sigma_init=p['sigma_init'], mu=p['mu'], K=p['K'])
y = f.evaluate(u_train,d_train)
y_pred = f.predict(u_test)
err = d_test-y_pred.reshape(-1,1)
t_mse = np.mean(err**2)
signalPower = x.var()
p['testing_mse'] = t_mse/signalPower
p['CB_size'] = len(f.CB)
p['tradeOff_dist'] = tradeOffDistance(p['testing_mse'],p['CB_size']/n_train)
except:
p['testing_mse'] = np.nan
p['CB_size'] = np.nan
p['tradeOff_dist'] = np.nan
results.append(p)
pd.DataFrame(data=results).to_csv('GridSearchResults2ndRun/' + filterName + '_' + systemName + '_' + str(n_samples) + '.csv')
elif filterName == "QKLMS_AMK":
# 2.1. Generate parameters for QKLMS_AKB grid search
import numpy as np
if systemName == "lorenz":
mu = [1e-3,1e-1, 0.1,1,1.5,2]
eta = [0.05, 0.1,0.5,0.9]
epsilon = [1e-2, 1e-1, 1, 1.5, 2]
K = [2,5,10,15,20]
elif systemName == "chua":
eta = np.linspace(0.02,1,n_paramters)
epsilon = np.linspace(1e-3,100,n_paramters)
mu = np.linspace(1e-4,1,n_paramters)
K = np.linspace(2,20,n_paramters)
elif systemName == "4.2":
mu = [1e-3,1e-1, 0.1,1]
eta = [0.05, 0.1,0.5,0.9]
epsilon = [1e-2, 1e-1, 1, 1.5, 2]
K = [2,5,10,15,20]
params = [{'eta':et,'epsilon':ep, 'mu':m, 'K':int(k)} for et in eta for ep in epsilon for m in mu for k in K]
# 2.2. Search over QKLMS_AMK
results = []
for p in tqdm(params):
try:
f = KAF.QKLMS_AMK(eta=p['eta'],epsilon=p['epsilon'], mu=p['mu'], Ka=p['K'], A_init="pca")
y = f.evaluate(u_train,d_train)
y_pred = f.predict(u_test)
err = d_test-y_pred.reshape(-1,1)
t_mse = np.mean(err**2)
signalPower = x.var()
p['testing_mse'] = t_mse/signalPower
p['CB_size'] = len(f.CB)
p['tradeOff_dist'] = tradeOffDistance(p['testing_mse'],p['CB_size']/n_train)
except:
p['testing_mse'] = np.nan
p['CB_size'] = np.nan
p['tradeOff_dist'] = np.nan
results.append(p)
pd.DataFrame(data=results).to_csv('GridSearchResults2ndRun/' + filterName + '_' + systemName + '_' + str(n_samples) + '.csv')
else:
raise ValueError("Filter does not exist")
return
sR_KLMS_BGMM = search.searchKLMS_BGMM(u, d, wcp, "wang", batchSize)
QKLMS_RESULTS = pd.concat([QKLMS_RESULTS, sR_QKLMS])
KRLS_RESULTS = pd.concat([KRLS_RESULTS, sR_KRLS])
QKLMS_base_RESULTS = pd.concat([QKLMS_base_RESULTS, sR_QKLMS_base])
KLMS_BGMM_RESULTS = pd.concat([KLMS_BGMM_RESULTS, sR_KLMS_BGMM])
"""
SISTEMA 1 :
x = Proceso Gaussiano con media 0 y varianza 1+
t = Filtro FIR en x
"""
import testSystems
u, d = testSystems.testSystems(samples=samples, systemType="1")
u = u.reshape(-1, 1)
d = d.reshape(-1, 1)
epList = np.linspace(1e-1, 300, 300)
sR_QKLMS = search.searchQKLMS(u, d, epList, "Sistema 2")
sgmList = np.linspace(0.1, np.max(u), 20)
epList = np.linspace(1e-6, 1e-1, 20)
sR_KRLS = search.searchKRLS_ALD(u, d, sgmList, epList, "Sistema 1")
sgmList = np.linspace(0.1, np.max(u), 20)
epList = np.linspace(1e-1, 300, 300)
sR_QKLMS_base = search.searchQKLMS_base(u, d, sgmList, epList, "Sistema 1")
wcp = np.linspace(1e-6, 1e-2, 50)
params = selectBestResultFromKafSearch(folder + '/' + AMK_42)
import KAF
import TimeSeriesGenerator
n_samples = 5000
n_train = int(n_samples * 0.8)
'''lorenz'''
# embedding = 5
# x, y, z = TimeSeriesGenerator.chaoticSystem(samples=n_samples+embedding,systemType='lorenz')
# x -= x.mean()
# x /= x.std()
'''4.2'''
embedding = 2
import testSystems as ts
x = ts.testSystems(samples=n_samples + embedding, systemType="4.2_AKB")
x -= x.mean()
x /= x.std()
u_train = np.array([x[i - embedding:i] for i in range(embedding, n_train)])
d_train = np.array([x[i] for i in range(embedding, n_train)]).reshape(-1, 1)
u_test = np.array([x[i - embedding:i] for i in range(n_train, n_samples)])
d_test = np.array([x[i] for i in range(n_train, n_samples)]).reshape(-1, 1)
# f = KAF.QKLMS(eta=params['eta'], epsilon=params['epsilon'], sigma=params['sigma'])
# f = KAF.QKLMS_AKB(eta=params['eta'], epsilon=params['epsilon'], sigma_init= params['sigma_init'], mu=params['mu'], K=int(params['K']))
f = KAF.QKLMS_AMK(eta=params['eta'],
epsilon=params['epsilon'],
mu=params['mu'],
Ka=int(params['K']),
# -*- coding: utf-8 -*-
"""
Created on Wed Apr 21 00:28:14 2021
@author: USUARIO
"""
import numpy as np
import testSystems as ts
N = 5000
u,d = ts.testSystems(N,'4.1_AKB')
import TimeSeriesGenerator
x, y, z = TimeSeriesGenerator.chaoticSystem(samples=6000,systemType='wang')
def std(x):
x = x - x.mean()
return x/x.std()
# signalEmbedding = 5
# X = np.array([u[i-signalEmbedding:i] for i in range(signalEmbedding,len(u))])
# y = np.array([d[i] for i in range(signalEmbedding,len(u))]).reshape(-1,1)
u = d = std(x)
import KAF
f = KAF.QKLMS_AMK(eta=0.01,epsilon=0.5,embedding=10, Ka=10, mu=0.05)
f.evaluate(u[:100],d[:100])
f.fit(u[:4000],d[:4000])
# from OA import artifactRemoval # ar = artifactRemoval(th=2) # ar.fit(Xdata,labels) # cleanEEG = ar.transform(Xdata) from KAF import QKLMS_v2 f = QKLMS_v2(epsilon=0.0, sigma=0.1) import testSystems as ts import numpy as np N = 200 L = 5 u, d = ts.testSystems(N, "4.1_AKB") X = np.array([u[i - L:i] for i in range(L, len(u))]) y = np.array([d[i] for i in range(L, len(d))]) f.fit(X, y) y_pred = f.predict(X) plt.plot(y) plt.plot(y_pred) plt.show() # from KAF import QKLMS # f = QKLMS(epsilon=0.0) # import testSystems as ts