def _getTrainingData(self, startPos=0, numSamples=5000):
galaxyFactory = GalaxyFactory(isTrainingData=True)
sr = SolutionReader(TRAINING_SOLUTIONS_PATH)
sr.skipTo(startPos)
galaxyIds = []
solution_data = [[], [], []]
training_data = []
galaxyIndex = 0
trainingSol = sr.next()
while trainingSol:
galaxy = galaxyFactory.getGalaxyForImage(os.path.join(TRAINING_IMAGE_PATH,
str(trainingSol.GalaxyID) + '.jpg'))
aspectRatio = galaxy.getAspectRatio()
if not math.isnan(aspectRatio):
galaxyIds.append(galaxy.id)
training_data.append([aspectRatio])
solution_data[0].append(trainingSol.Class2_1)
solution_data[1].append(trainingSol.Class2_2)
galaxyIndex += 1
if galaxyIndex > numSamples:
break
trainingSol = sr.next()
return {'galaxyIds': galaxyIds, 'training_data': training_data, 'solution_data': solution_data}
def generateTestResults():
classifiers = getClassifiers()
print "Scoring Solutions"
galaxyFactory = GalaxyFactory()
results = SolutionWriter(config.TEST_SOLUTION_OUTPUT_PATH)
#numSamples =100
sampleNum = 0
for imagePath in glob.glob(config.TEST_IMAGE_PATH + '/*.jpg'):
galaxy = galaxyFactory.getGalaxyForImage(imagePath)
solution = [galaxy.id]
for classifier in classifiers:
predictions = classifier.predict(galaxy)
predictions = [prediction if prediction >= 0.0 else 0.0 for prediction in predictions]
solution.extend(predictions)
if len(solution) != 38:
print "Problem with galaxy with id %s. Solution is not the correct length." % galaxy.id
else:
results.append(Solution._make(solution))
if not sampleNum % 10:
print sampleNum
sampleNum += 1
#if sampleNum > numSamples:
# break
results.close()
def generateSolutionsFromTrainingSet(startPos, numSamples):
classifiers = getClassifiers()
print "Classifying Solutions"
galaxyFactory = GalaxyFactory()
reader = SolutionReader(config.TRAINING_SOLUTIONS_PATH)
results = SolutionWriter(config.TRAINING_SOLUTION_OUTPUT_PATH)
reader.skipTo(startPos)
sampleNum = 0
solution = reader.next()
while solution:
imagePath = os.path.join(config.TRAINING_IMAGE_PATH, str(solution.GalaxyID) + '.jpg')
galaxy = galaxyFactory.getGalaxyForImage(imagePath)
predictedSolution = [galaxy.id]
for classifier in classifiers:
predictedSolution.extend(classifier.predict(galaxy))
if len(solution) != 38:
print "Problem with galaxy with id %s. Solution is not the correct length." % galaxy.id
else:
results.append(Solution._make(predictedSolution))
sampleNum += 1
if sampleNum > numSamples:
break
solution = reader.next()
results.close()
def plot(self):
c = Class4()
c.train()
sr = SolutionReader(TRAINING_SOLUTIONS_PATH)
sr.skipTo(15000)
galaxyFactory = GalaxyFactory(isTrainingData=True)
trainingSol = sr.next()
galaxy = galaxyFactory.getGalaxyForImage(os.path.join(TRAINING_IMAGE_PATH, str(trainingSol.GalaxyID) + '.jpg'))
print c.predict(galaxy)
def _getTrainingData(self, startPos=0, numSamples=5000, verbose=False):
galaxyFactory = GalaxyFactory(isTrainingData=True)
sr = SolutionReader(TRAINING_SOLUTIONS_PATH)
sr.skipTo(startPos)
galaxyIds = []
solution_data = [[], [], [], []]
training_data = []
success = []
galaxyIndex = 0
trainingSol = sr.next()
while trainingSol:
galaxy = galaxyFactory.getGalaxyForImage(
os.path.join(TRAINING_IMAGE_PATH, str(trainingSol.GalaxyID) + ".jpg")
)
if galaxy.initSuccess:
if galaxy.ellipse.ellipse_area() > 0:
features = self._extractFeatures(galaxy, useCache=True)
if features:
training_data.append(
[
features["bulgeIntensity"],
features["R"] - features["G"],
features["bulgeBlobFractionalArea"],
]
)
solution_data[0].append(trainingSol.Class5_1)
solution_data[1].append(trainingSol.Class5_2)
solution_data[2].append(trainingSol.Class5_3)
solution_data[3].append(trainingSol.Class5_4)
galaxyIds.append(trainingSol.GalaxyID)
success.append(True)
if verbose and not galaxyIndex % 10:
print galaxyIndex
galaxyIndex += 1
if galaxyIndex > numSamples:
break
else:
galaxyIds.append(trainingSol.GalaxyID)
success.append(False)
trainingSol = sr.next()
return {"galaxyIds": galaxyIds, "training_data": training_data, "solution_data": solution_data}
def _getTrainingData(self, startPos=0, numSamples=5000, verbose=False):
galaxyFactory = GalaxyFactory(isTrainingData=True)
sr = SolutionReader(TRAINING_SOLUTIONS_PATH)
sr.skipTo(startPos)
galaxyIds = []
solution_data = [[], []]
rot_line_test = []
rot_line_test_deriv = []
scaled_img = []
rot_bias = []
galaxyIndex = 0
trainingSol = sr.next()
while trainingSol:
galaxy = galaxyFactory.getGalaxyForImage(os.path.join(TRAINING_IMAGE_PATH,
str(trainingSol.GalaxyID) + '.jpg'))
features = self._extractFeatures(galaxy, useCache=True)
if features != None and features['rotLineTestResult'] != None:
galaxyIds.append(galaxy.id)
rot_line_test.append(features['rotLineTestResult'])
rot_line_test_deriv.append(features['rotLineTestDerivative'])
scaled_img.append(features['scaledImg'])
rot_bias.append(features['rotBias'])
solution_data[0].append(trainingSol.Class4_1)
solution_data[1].append(trainingSol.Class4_2)
if verbose and not galaxyIndex % 10:
print galaxyIndex
galaxyIndex += 1
if galaxyIndex > numSamples:
break
trainingSol = sr.next()
return {'galaxyIds': galaxyIds,
'rot_line_test': rot_line_test,
'rot_line_test_deriv': rot_line_test_deriv,
'scaled_img': scaled_img,
'rot_bias': rot_bias,
'solution_data': solution_data}
def _getTrainingData(self, startPos=0, numSamples=5000, verbose=False):
galaxyFactory = GalaxyFactory(isTrainingData=True)
sr = SolutionReader(TRAINING_SOLUTIONS_PATH)
sr.skipTo(startPos)
galaxyIds = []
solution_data = [[], [], []]
training_data = []
success = []
galaxyIndex = 0
trainingSol = sr.next()
while trainingSol:
galaxy = galaxyFactory.getGalaxyForImage(os.path.join(TRAINING_IMAGE_PATH,
str(trainingSol.GalaxyID) + '.jpg'))
if galaxy.initSuccess:
features = self._extractFeatures(galaxy, useCache=True)
if features:
training_data.append([features['bulgeIntensity'],
features['R'] - features['G'],
features['asymScore'],
features['rotBias']])
solution_data[0].append(trainingSol.Class1_1)
solution_data[1].append(trainingSol.Class1_2)
solution_data[2].append(trainingSol.Class1_3)
galaxyIds.append(trainingSol.GalaxyID)
success.append(True)
if verbose and not galaxyIndex % 10:
print galaxyIndex
galaxyIndex += 1
if galaxyIndex > numSamples:
break
else:
galaxyIds.append(trainingSol.GalaxyID)
success.append(False)
trainingSol = sr.next()
return {'galaxyIds': galaxyIds, 'training_data': training_data, 'solution_data': solution_data, 'success': success}
def _getTrainingData(self, startPos=0, numSamples=5000, verbose=False):
galaxyFactory = GalaxyFactory(isTrainingData=True)
sr = SolutionReader(TRAINING_SOLUTIONS_PATH)
sr.skipTo(startPos)
galaxyIds = []
solution_data = [[], [], []]
training_data = []
galaxyIndex = 0
trainingSol = sr.next()
while trainingSol:
galaxy = galaxyFactory.getGalaxyForImage(
os.path.join(TRAINING_IMAGE_PATH, str(trainingSol.GalaxyID) + ".jpg")
)
aspectRatio = galaxy.getAspectRatio()
if not math.isnan(aspectRatio):
galaxyIds.append(galaxy.id)
training_data.append([aspectRatio])
solution_data[0].append(trainingSol.Class7_1)
solution_data[1].append(trainingSol.Class7_2)
solution_data[2].append(trainingSol.Class7_3)
galaxyIndex += 1
if galaxyIndex > numSamples:
break
if verbose and not galaxyIndex % 10:
print galaxyIndex
trainingSol = sr.next()
return {"galaxyIds": galaxyIds, "training_data": training_data, "solution_data": solution_data}
