def calcMinChi2(flux_target, templateDir, waveRange):
minChi2 = 0
templatePath = ""
minCoeff = None
templatePaths = util.listDirFiles(templateDir)
for path in templatePaths:
data = np.loadtxt(path)
wave, flux = formatWaveAndFlux(data[:, 0], data[:, 1], waveRange)
try:
coeff = mathUtil.calcChi2Coeff(flux_target, flux, wave)
except Exception, ex:
exUtil.printTagMessage(ex, "error", path)
continue
chi2_value = mathUtil.chi2_ploy(wave, flux_target, flux, coeff[0], coeff[1], coeff[2])
if minChi2 == 0 or chi2_value < minChi2:
minChi2 = chi2_value
templatePath = path
minCoeff = coeff
def calcMinChi22(flux_target, templateDir, waveRange):
minChi2 = 0
templatePath = ""
templatePaths = util.listDirFiles(templateDir)
for path in templatePaths:
data = np.loadtxt(path)
wave, flux = formatWaveAndFlux(data[:, 0], data[:, 1], waveRange)
chi2_value = mathUtil.chi2(flux_target, flux)
if minChi2 == 0 or chi2_value < minChi2:
minChi2 = chi2_value
templatePath = path
return templatePath, minChi2
def testData(data):
m, n = data.shape
tags = data[:, n - 1]
errorCount = 0
for i in range(m):
print "%d : classification" % i
maxPro = 0
maxClass = 0
for key in classMeanVar.keys():
p = 1.0
for j in range(n - 1):
if j < 3:
num = classMeanVar[key][j][2]
var = classMeanVar[key][j][1]
mean = classMeanVar[key][j][0]
p = p * MathUtil.calcNormPDF(mean, var, data[i][j])
else:
bp = (float(classMeanVar[key][j] + 1) / (subClassCount[key] + 1))
if data[i][j] == 0:
p *= 1 - bp
else:
p *= bp
p = p * subClassCount[key] / m
print "subclass %d MAP: %f" % (key, p)
if p > maxPro:
maxPro = p
maxClass = key
if maxClass == 0:
continue
if maxClass != tags[i]:
errorCount += 1
print "Error! Estimate : %d, True : %d" % (maxClass, tags[i])
return float(errorCount) / m
def formatWaveAndFlux(wave, flux, waveRange):
tck = interpolate.splrep(wave, flux)
flux_spl = interpolate.splev(waveRange, tck)
wave_range, flux_range = getMetalRegion(waveRange, flux_spl)
flux_normalize = mathUtil.normalize(flux_range)
return wave_range, flux_normalize
inputFile = "data_v4.txt"
data = util.loadTxtData(inputFile)
m, n = data.shape
testCount = int(m * 0.2)
testData = data[0:testCount, :]
trainData = data[testCount:m, :]
subClassData, subClassCount = astroUtil.formatClassifyData(trainData)
classMeanVar = {}
for key in subClassData.keys():
classMeanVar[key] = []
for i in range(len(subClassData[key])):
if i < 3:
mean, var, num = MathUtil.calcMeanVarCount(subClassData[key][i])
classMeanVar[key].append([mean, var, num])
else:
classMeanVar[key].append(np.sum(subClassData[key][i]))
def testData(data):
m, n = data.shape
tags = data[:, n - 1]
errorCount = 0
for i in range(m):
print "%d : classification" % i
maxPro = 0
maxClass = 0
for key in classMeanVar.keys():
