random_state=12,
verbose=False)
for tr, vl in SKF.split(X=None, y=y):
print(tr, vl)
###############################################################################
# .. note::
# Split is made to generate each fold
# Show label
for tr, vl in SKF.split(X=None, y=y):
print(y[tr], y[vl])
##############################################################################
# .. note::
# The first one is made with polygon only.
# When learning/predicting, all pixels will be taken in account
# TO generate a full X and y labels, extract samples from ROI
X, y = processing.extract_ROI(raster, vector, field)
for tr, vl in SKF.split(X, y):
print(tr, vl)
print(tr.shape, vl.shape)
##########################
# Plot example
from __drawCVmethods import plotMethod
plotMethod('SKF-pixel')
# Load HistoricalMap dataset
# -------------------------------------------
raster, vector = datasets.historicalMap(low_res=True)
field = 'Class'
X, y = raster_tools.getSamplesFromROI(raster, vector, field)
distanceMatrix = vector_tools.getDistanceMatrix(raster, vector)
##############################################################################
# Create CV
# -------------------------------------------
# n_splits will be the number of the least populated class
SLOPO = SpatialLeaveOneOut(distanceThresold=100,
distanceMatrix=distanceMatrix,
random_state=12)
print(SLOPO.get_n_splits(X, y))
###############################################################################
# .. note::
# Split is made to generate each fold
for tr, vl in SLOPO.split(X, y):
print(tr.shape, vl.shape)
#############################################
# Draw image
from __drawCVmethods import plotMethod
plotMethod('SLOO-pixel')
# Create CV
# -------------------------------------------
# if n_splits is False (default), the number of splits will be the smallest
# number of subgroup of all labels.
valid_size = 0.5 # Means 50%
LOSGO = LeaveOneSubGroupOut(verbose=False, random_state=12) #
###############################################################################
# .. note::
# Split is made to generate each fold
LOSGO.get_n_splits(X, y, s)
for tr, vl in LOSGO.split(X, y, s):
print(tr.shape, vl.shape)
###############################################################################
# Differences with sklearn
# -------------------------------------------
# Sklearn do not use subgroups (only groups), so no hierarchical dependances.
from sklearn.model_selection import LeaveOneGroupOut
LOGO = LeaveOneGroupOut()
for tr, vl in LOGO.split(X=X, y=y, groups=s):
print(tr.shape, vl.shape)
###############################################################################
# Plot example
from __drawCVmethods import plotMethod
plotMethod('LOO-group')
print(tr.shape, vl.shape)
print('y label with number of samples')
print(np.unique(y[tr], return_counts=True))
##############################################################################
# Differences with scikit-learn
# -------------------------------------------
from sklearn.model_selection import LeavePGroupsOut
# You need to specify the number of groups
LPGO = LeavePGroupsOut(n_groups=2)
for tr, vl in LPGO.split(X, y, g):
print(tr.shape, vl.shape)
##############################################################################
# With GroupShuffleSplit, won't keep the percentage per subgroup
# This generate unbalanced classes
from sklearn.model_selection import GroupShuffleSplit
GSS = GroupShuffleSplit(test_size=0.5, n_splits=2)
for tr, vl in GSS.split(X, y, g):
print(tr.shape, vl.shape)
print('y label with number of samples')
print(np.unique(y[tr], return_counts=True))
###############################################################################
# Plot example in image
from __drawCVmethods import plotMethod
plotMethod('SKF-group')