def __init__(self):
SupervisedDataSet.__init__(self, 2, 1)
with open('C:\Users\Brian\Desktop\Brian\Universitetet\Kandidat\Master Thesis\WeLoveGREEN-ENERGY\DATASET_FOR_GREEN_ENERGY_PLOTTING\WIND_TEMP_PRODUCTION_AVERAGE.csv', 'rb') as csvfile:
dat = csv.reader(csvfile, delimiter=';')
for row in dat:
# print 'sample 0: ' + row[0] + ' sample 1: ' + row[1]
self.addSample([int(row[1]),int(row[2])],[int(row[0])])
def __init__(self, filename=None):
SupervisedDataSet.__init__(self,0,0)
self.nCls = 0
self.nSamples = 0
self.classHist = {}
self.filename = ''
if filename is not None:
self.loadData(filename)
def __init__(self, filename=None):
SupervisedDataSet.__init__(self, 0, 0)
self.nCls = 0
self.nSamples = 0
self.classHist = {}
self.filename = ''
if filename is not None:
self.loadData(filename)
def _setDataFields( self, x, y ):
if not len(x): raise Exception("no input data found")
SupervisedDataSet.__init__( self, len(x[0]), 1 )
self.setField( 'input' , x )
self.setField( 'target' , y )
flat_labels = list( self.getField('target').flatten() )
classes = list(set( flat_labels ))
self._classes = classes
self.nClasses = len(classes)
for class_ in classes:
self.classHist[class_] = flat_labels.count(class_)
def _setDataFields(self, x, y):
if not len(x): raise Exception("no input data found")
SupervisedDataSet.__init__(self, len(x[0]), 1)
self.setField('input', x)
self.setField('target', y)
flat_labels = list(self.getField('target').flatten())
classes = list(set(flat_labels))
self._classes = classes
self.nClasses = len(classes)
for class_ in classes:
self.classHist[class_] = flat_labels.count(class_)
def __init__(self, oneInN=False):
if oneInN:
SupervisedDataSet.__init__(self, 2, 2)
self.addSample([0, 0], [0, 1])
self.addSample([0, 1], [1, 0])
self.addSample([1, 0], [1, 0])
self.addSample([1, 1], [0, 1])
else:
SupervisedDataSet.__init__(self, 2, 1)
self.addSample([0, 0], [0])
self.addSample([0, 1], [1])
self.addSample([1, 0], [1])
self.addSample([1, 1], [0])
def __init__(self, oneInN=False):
if oneInN:
SupervisedDataSet.__init__(self, 2, 2)
self.addSample([0, 0], [0, 1])
self.addSample([0, 1], [1, 0])
self.addSample([1, 0], [1, 0])
self.addSample([1, 1], [0, 1])
else:
SupervisedDataSet.__init__(self, 2, 1)
self.addSample([0, 0], [0])
self.addSample([0, 1], [1])
self.addSample([1, 0], [1])
self.addSample([1, 1], [0])
def __init__(self,begin=0,end=40000):
SupervisedDataSet.__init__(self, 5, 1)
rid_url = fileio.read_file_to_dict(FEATURE_PATH+"url_id_feature.dat")
rid_sent = fileio.read_file_to_dict(FEATURE_PATH+"rid_sentratio.dict")
rid_general = fileio.read_file_to_dict(FEATURE_PATH+"rid_general.dict")
rid_len = fileio.read_file_to_dict(FEATURE_PATH+"rid_lenratio.dict")
rid_cate = fileio.read_file_to_dict(FEATURE_PATH+"rid_cateratio.dict",delimiter=None)
fake = fileio.read_file_to_list("data/target/all_replicaId.dat")
for rid in rid_url.keys()[begin:end]:
inps = [rid_url[rid],rid_sent[rid],rid_general[rid],rid_len[rid],rid_cate[rid]]
target = [1 if rid in fake else 0]
self.addSample(inps,target)
def __init__(self, number_of_days_before, quotes):
SupervisedDataSet.__init__(self, number_of_days_before, 1)
gains = []
for i, quote in enumerate(quotes):
if i >= 1:
gain = (quote - quotes[i-1])/quotes[i-1]
gains.append(gain)
for i, quote in enumerate(gains):
if i >= number_of_days_before:
first_day = i - number_of_days_before
input = gains[first_day:i]
output = [gains[i]]
self.addSample(input, output)
def __init__(self):
SupervisedDataSet.__init__(self, 2, 1)
self.addSample([7,28],[743])
self.addSample([5,28],[701])
self.addSample([8,28],[676])
self.addSample([8,28],[641])
self.addSample([7,28],[642])
self.addSample([8,28],[671])
self.addSample([8,28],[659])
self.addSample([8,29],[629])
self.addSample([8,30],[596])
self.addSample([8,29],[550])
self.addSample([10,30],[533])
self.addSample([11,30],[499])
self.addSample([413,28],[528])
self.addSample([12,30],[567])
self.addSample([10,29],[574])
def __init__(self):
SupervisedDataSet.__init__(self, 3, 1)
for file_name, expected in DATA:
with open(file_name, 'rb') as csvfile:
csvreader = csv.reader(csvfile, delimiter=',')
for row in csvreader:
row_data = []
for d in row:
try:
row_data.append(float(d))
except ValueError:
pass
if row_data:
self.addSample([row_data[i] for i in [0, 6, 9]],
[expected])
#self.addSample(row_data, [expected])
print self
def __init__(self, inp, target=1, nb_classes=0, class_labels=None):
"""Initialize an empty dataset.
`inp` is used to specify the dimensionality of the input. While the
number of targets is given by implicitly by the training samples, it can
also be set explicity by `nb_classes`. To give the classes names, supply
an iterable of strings as `class_labels`."""
# FIXME: hard to keep nClasses synchronized if appendLinked() etc. is used.
SupervisedDataSet.__init__(self, inp, target)
self.addField('class', 1)
self.nClasses = nb_classes
if len(self) > 0:
# calculate class histogram, if we already have data
self.calculateStatistics()
self.convertField('target', int)
if class_labels is None:
self.class_labels = list(set(self.getField('target').flatten()))
else:
self.class_labels = class_labels
# copy classes (may be changed into other representation)
self.setField('class', self.getField('target'))
def __init__(self, inp, target=1, nb_classes=0, class_labels=None):
"""Initialize an empty dataset.
`inp` is used to specify the dimensionality of the input. While the
number of targets is given by implicitly by the training samples, it can
also be set explicity by `nb_classes`. To give the classes names, supply
an iterable of strings as `class_labels`."""
# FIXME: hard to keep nClasses synchronized if appendLinked() etc. is used.
SupervisedDataSet.__init__(self, inp, target)
self.addField('class', 1)
self.nClasses = nb_classes
if len(self) > 0:
# calculate class histogram, if we already have data
self.calculateStatistics()
self.convertField('target', int)
if class_labels is None:
self.class_labels = list(set(self.getField('target').flatten()))
else:
self.class_labels = class_labels
# copy classes (may be changed into other representation)
self.setField('class', self.getField('target'))
def __init__(self, imgnames=None):
SupervisedDataSet.__init__(self, 10*15, 1)
'''
if imgnames==None:
imgnames = os.listdir('./dataset')
map(lambda a: './dataset/'+a, imgnames)
'''
imgnames.sort()
for iname in imgnames:
img = Image.open(iname)
w,h = img.size
assert(w*h==150)
pixels=[]
for i in range(w):
for j in range(h):
p = img.getpixel((i,j))
#All the 3 fields of p are equal, always.
#Therefore we need only one to represent.
pixels.append(float(p[0])/255)
num = iname[rfind(iname,'/')+1:rfind(iname,'.')]
assert(len(pixels)==150)
self.addSample(pixels, [int(num)])
def __init__(self):
SupervisedDataSet.__init__(self, 2, 1)
self.addSample([0,0],[0])
self.addSample([0,1],[1])
self.addSample([1,0],[1])
self.addSample([1,1],[0])
def __init__(self):
SupervisedDataSet.__init__(self, 2, 1)
self.addSample([0, 0], [0])
self.addSample([0, 1], [1])
self.addSample([1, 0], [1])
self.addSample([1, 1], [0])
