def avaliacao(metrica, arq):
arquivo = open('arquivo.txt', 'r') #abrir o arquivo
subjectscores = open(arq, 'r') #ler arquivo
conteudo_texto = arquivo.read() #
conteudo_texto1 = subjectscores.read() #
a = conteudo_texto.split('\n') # separar por quebra de linha
c = a[:-1] #tirar ultimo elemento
aa = conteudo_texto1.split('\n') #separar por espaco
cc = aa[:-1]
arquivo.close() #fechar arquivo
subjectscores.close()
x = np.array([])
y = np.array([])
l = np.array([])
total_pontos = 0
#plotar grafico
for i in xrange(0, len(cc)):
w = cc[i].split('\t') #buscar linha
q = len(w) #tamanho da linha
ww = w[2:q] #tirar primeiro elemento
total_pontos = len(ww) + total_pontos
b = c[i].split(';') #separar por ,
psnr = b[metrica] #buscar psnr
h = np.asarray(ww[0:13]) #criando vetor com media de mos
t = h.astype(np.float)
v = np.mean(t)
if (psnr !=str('inf')):
x = np.insert(x,0,psnr) #guardar
y = np.insert(y,0,v) #vetor media mos
r = float(psnr) #converter para float
p = q-1.0 #tamanho da linha menos o 1 item
d = np.zeros(p) #criar vetor de 0s
dd = d + r #criar vetor de psnr do tm d mos
#plt.plot(dd, ww, 'o', color='r') #plotar psnr x mos
out = outlier.outlier(t) #calcular outliers
l = np.append(l, out) #vetor com n de outliers por coluna mos
razao_outliers = np.sum(l)/total_pontos
coeficiente_spearman = spearman.spearman(x,y) #spearman/s = stats.spearmanr(x,y)
coeficiente_pearson = pearson.pearson(x,y) #pearson/p = stats.pearsonr(x,y)
a, b = regressaoLinear.regressaoLinear(x,y) #regressao linear
x, t, y, v = levenbergMarquart.levenberg(x,y) #funcao logistica
linear = '(' + str(a) + ')*x + (' + str(b) + ')'
logistica = '(' + str(v[0])+ ') * (' + str(0.5) + '-(' + str(v[1]) + ')/(exp(' + str(v[1]) + '*(x-(' + str(v[2])+ '))))) + (' + str(v[3])+ ') * x+(' + str(v[4]) + ')'
return razao_outliers, coeficiente_spearman, coeficiente_pearson, logistica, linear
def avaliacao(metrica, arq):
arquivo = open('arquivo.txt', 'r')
subjectscores = open(arq, 'r')
conteudo_texto = arquivo.read()
conteudo_texto1 = subjectscores.read()
a = conteudo_texto.split('\n')
c = a[:-1]
aa = conteudo_texto1.split('\n')
cc = aa[:-1]
arquivo.close()
subjectscores.close()
x = np.array([])
y = np.array([])
l = np.array([])
total_pontos = 0
for i in xrange(0, len(cc)):
w = cc[i].split('\t') #buscar linha
q = len(w) #tamanho da linha
ww = w[2:q] #tirar primeiro elemento
total_pontos = len(ww) + total_pontos
b = c[i].split(';') #separar por ,
psnr = b[metrica] #buscar metrica
h = np.asarray(ww[0:13]) #criando vetor com media de mos
t = h.astype(np.float)
v = np.mean(t)
if (psnr !=str('inf')):
x = np.insert(x,0,psnr) #guardar
y = np.insert(y,0,v) #vetor media mos
r = float(psnr) #converter para float
p = q-1.0 #tamanho da linha menos o 1 item
d = np.zeros(p) #criar vetor de 0s
dd = d + r #criar vetor de psnr do tm d mos
out = outlier.outlier(t) #calcular outliers
l = np.append(l, out) #vetor com n de outliers por coluna mos
razao_outliers = np.sum(l)/total_pontos
coeficiente_spearman = spearman.spearman(x,y) #spearman/s = stats.spearmanr(x,y)
coeficiente_pearson = pearson.pearson(x,y) #pearson/p = stats.pearsonr(x,y)
a, b = regressaoLinear.regressaoLinear(x,y) #regressao linear
x, t, y, v = levenbergMarquart.levenberg(x,y) #funcao logistica
linear = '(' + str(a) + ')*x + (' + str(b) + ')'
logistica = '(' + str(v[0])+ ') * (' + str(0.5) + '-(' + str(v[1]) + ')/(exp(' + str(v[1]) + '*(x-(' + str(v[2])+ '))))) + (' + str(v[3])+ ') * x+(' + str(v[4]) + ')'
return razao_outliers, coeficiente_spearman, coeficiente_pearson, logistica, linear
if (maxG < g):
maxG=g
imax=i
jmax=j
clusNuevo=clus[imax] + clus[jmax]
aux = clus[jmax]
clus.remove(clus[imax])
clus.remove(aux)
clus.append(clusNuevo)
return clus
datos=outlier(N=150,outliers=0.2)
datos=datos[:,range(0,2)]
r = ROCK(datos,10)
clusters = r.ejecutar(4,0.5)
#Los dibujo
figure()
plt.plot(datos[clusters[0],0],datos[clusters[0],1],'ro')
plt.plot(datos[clusters[1],0],datos[clusters[1],1],'bo')
plt.plot(datos[clusters[2],0],datos[clusters[2],1],'go')
plt.plot(datos[clusters[3],0],datos[clusters[3],1],'yo')
plt.show()
def avaliacao(metrica, arq):
# abrir arquivo de avaliacoes objetivas (metricas)
arquivo = open('metricas.txt', 'r')
conteudo_texto = arquivo.read()
a = conteudo_texto.split('\n')
c = a[:-1]
arquivo.close()
# abrir aquivo de avaliacoes subjetivas
subjectscores = open(arq, 'r')
conteudo_texto1 = subjectscores.read()
aa = conteudo_texto1.split('\n')
cc = aa[:-1]
subjectscores.close()
# abrir arquivo de avaliacoes objetivas (metricas)
arquivo2 = open('jpeginfo.txt', 'r')
conteudo_texto2 = arquivo2.read()
aaa = conteudo_texto2.split('\n')
ccc = aaa[:-1]
arquivo2.close()
#inicializacao das variaveis
x = np.array([])
y = np.array([])
l = np.array([])
total_pontos = 0
ref = ''
ab = ''
#plot METRICA X DMOS
for i in xrange(0, len(cc)):
w = aa[i].split('\t')
for line in ccc:
if w[0] in line:
#print line
cond = line.split()
#print cond[2]
if cond[2] == '0':
ab = cond[1]
#q = len(w)
for line in cc:
if ab in line:
w0 = line
w1 = w0.split('\t')
ww = w[2:(len(w))]
ww1 = w1[2:(len(w))]
#print ww1
total_pontos = len(ww) + total_pontos
b = c[i].split(';')
psnr = b[metrica]
h = np.asarray(
ww[0:12]) #substituir numeracao por eliminacao de valores nulos
h1 = np.asarray(ww1[0:12])
#t = h.astype(np.float)
v2 = np.mean(h1.astype(np.float))
v1 = np.mean(h.astype(np.float))
v = v2 - v1
if (psnr != str('inf')):
x = np.insert(x, 0, psnr)
y = np.insert(y, 0, v1)
r = float(psnr)
#p = (len(w))-1.0
#outlier
out = outlier.outlier(h.astype(np.float))
l = np.append(l, out)
razao_outliers = np.sum(l) / total_pontos
coeficiente_spearman = spearman.spearman(
x, y) #spearman/s = stats.spearmanr(x,y)
coeficiente_pearson = pearson.pearson(x,
y) #pearson/p = stats.pearsonr(x,y)
coeficiente_anova_F, coeficiente_anova_p, relacao_anova = anova.anova(x, y)
a, b = regressaoLinear.regressaoLinear(x, y) #regressao linear
x, t, y, v = levenbergMarquart.levenberg(x, y) #funcao logistica
linear = '(' + str(a) + ')*x + (' + str(b) + ')'
logistica = '(' + str(v[0]) + ') * (' + str(0.5) + '-(' + str(
v[1]) + ')/(exp(' + str(v[1]) + '*(x-(' + str(
v[2]) + '))))) + (' + str(v[3]) + ') * x+(' + str(v[4]) + ')'
return razao_outliers, coeficiente_spearman, coeficiente_pearson, coeficiente_anova_F, coeficiente_anova_p, relacao_anova, logistica, linear
import numpy as np
import retrieve
import outlier
import util
if __name__ == '__main__':
## initial data retrieval (parts a - f)
# parts a-f: retrieve data
data = retrieve.retrieve_data('example_data.csv')
# part c: filter outliers
data = outlier.outlier(data, 3)
## split training and test, remove outliers if new data
# part d
training = outlier.outlier(data[3::4], 3)
test = outlier.outlier(np.delete(data, np.s_[3::4], axis=0), 3)
# part f
# training = outlier.outlier(data, 3)
# test = outlier.outlier(retrieve.retrieve_data('trip_data_2.csv'), 3)
# part i
# training = outlier.outlier(retrieve.retrieve_data('trip_data_1.csv'), 3)
# test = outlier.outlier(retrieve.retrieve_data('trip_data_2.csv'), 3)
## normalize the matrix
# part h - don't normalize train 2 (pickup time) bc of the binary modification
for count in range(0, 8):
if count != 2:
training = util.normalize(training, count)
test = util.normalize(test, count)
## plot the graphs
