def getSampleData(data, mode='trapezoidal'): # only for feature plot
copydata = copy.deepcopy(data)
random.shuffle(copydata)
if mode == 'trapezoidal':
dataset = preprocess.removeDataTrapezoidal(copydata)
if mode == 'variable':
dataset = preprocess.removeRandomData(copydata)
else:
"ERROR, WRONG STREAM_MODE"
all_keys = set().union(*(d.keys() for d in dataset))
X, y = [], []
for row in dataset:
for key in all_keys:
if key not in row.keys(): row[key] = 0
y.append(row['class_label'])
del row['class_label']
if 0 not in row.keys(): start = 1
if 0 in row.keys(): start = 0
for row in dataset:
X_row = []
for i in range(start, len(row)):
X_row.append(row[i])
X.append(X_row)
return X, y
def getShuffledData(self,
mode=p.stream_mode
): # generate data for cross validation
data = self.data
copydata = copy.deepcopy(data)
random.shuffle(copydata)
if mode == 'trapezoidal':
dataset = preprocess.removeDataTrapezoidal(copydata)
if mode == 'variable': dataset = preprocess.removeRandomData(copydata)
else: dataset = copydata
all_keys = set().union(*(d.keys() for d in dataset))
X, y = [], []
for row in dataset:
for key in all_keys:
if key not in row.keys(): row[key] = 0
y.append(row['class_label'])
del row['class_label']
if 0 not in row.keys(): start = 1
if 0 in row.keys(): start = 0
for row in dataset:
X_row = []
for i in range(start, len(row)):
X_row.append(row[i])
X.append(X_row)
self.X, self.y = X, y
def getShuffledTrapezoidalData(data):
copydata = copy.deepcopy(data)
random.shuffle(copydata)
dataset = p.removeDataTrapezoidal(copydata)
all_keys = set().union(*(d.keys() for d in dataset))
X, y = [], []
for row in dataset:
for key in all_keys:
if key not in row.keys(): row[key] = 0
y.append(row['class_label'])
del row['class_label']
if 0 not in row.keys(): start = 1
if 0 in row.keys(): start = 0
for row in dataset:
X_row = []
for i in range(start, len(row)):
X_row.append(row[i])
X.append(X_row)
return X, y
def getShuffledData(self): # generate data for cross validation
data = self.data
copydata = copy.deepcopy(data)
random.Random(p.random_seed).shuffle(copydata)
dataset = preprocess.removeDataTrapezoidal(copydata)
all_keys = set().union(*(d.keys() for d in dataset))
X, y = [], []
for row in dataset:
for key in all_keys:
if key not in row.keys(): row[key] = 0
y.append(row['class_label'])
del row['class_label']
if 0 not in row.keys(): start = 1
if 0 in row.keys(): start = 0
for row in dataset:
X_row = []
for i in range(start, len(row)):
X_row.append(row[i])
X.append(X_row)
self.X, self.y = X, y