def test_centroid(self):
Xc,yc = load_historical_data(centroid=True,return_X_y=True)
Xc_file, yc_file= load_historical_data(centroid=True)
assert(os.path.exists(Xc_file))
assert(os.path.exists(yc_file))
assert(Xc.shape[0] == processing.read_vector_values(vector,'Type').shape[0])
def test_zonal_stats(self):
raster,vector = datasets.load_historical_data()
copyfile(vector,'/tmp/train.gpkg')
median,amax,std = stats.zonal_stats(raster,'/tmp/train.gpkg',False)
assert(median.shape == amax.shape == std.shape)
assert(np.sum(std)<np.sum(median)< np.sum(amax))
Compute substract and addition between two raster bands. """ ############################################################################## # Import librairies # ------------------------------------------- from museotoolbox.processing import RasterMath from museotoolbox import datasets import numpy as np ############################################################################## # Load HistoricalMap dataset # ------------------------------------------- raster, vector = datasets.load_historical_data() ############################################################################## # Initialize rasterMath with raster # ------------------------------------ rM = RasterMath(raster) print(rM.get_random_block()) ########################## # Let's suppose you want compute the difference between blue and green band. # I suggest you to define type in numpy array to save space while creating the raster! X = rM.get_random_block()
import numpy as np
from museotoolbox import ai
from museotoolbox.datasets import load_historical_data
from museotoolbox.processing import image_mask_from_vector
from osgeo import gdal
import os
import tempfile
tempdir = tempfile.mkdtemp()
import shutil
from sklearn.ensemble import RandomForestClassifier
raster, vector = load_historical_data(low_res=True)
X, y, g = load_historical_data(return_X_y_g=True, low_res=True)
param_grid = dict(n_estimators=[1, 10])
classifier = RandomForestClassifier()
image_mask_from_vector(vector, raster, os.path.join(tempdir, 'mask.tif'))
class TestStats(unittest.TestCase):
def test_superLearner(self):
n_cv = 2
for tf in [True, False]:
verbose = tf + 1
model = ai.SuperLearner(classifier,
param_grid=param_grid,
n_jobs=1,
##############################################################################
# Import librairies
# -------------------------------------------
from museotoolbox.ai import SequentialFeatureSelection
from museotoolbox.cross_validation import LeavePSubGroupOut
from museotoolbox import datasets
from sklearn.ensemble import RandomForestClassifier
from sklearn import metrics
import numpy as np
##############################################################################
# Load HistoricalMap dataset
# -------------------------------------------
X, y, g = datasets.load_historical_data(return_X_y_g=True, low_res=True)
##############################################################################
# Create CV
# -------------------------------------------
LSGO = LeavePSubGroupOut(valid_size=0.8,
n_repeats=2,
random_state=12,
verbose=False)
##############################################################################
# Initialize Random-Forest and metrics
# --------------------------------------
classifier = RandomForestClassifier(random_state=12, n_jobs=1)
50% for each class.
"""
##############################################################################
# Import librairies
# -------------------------------------------
from museotoolbox.cross_validation import RandomStratifiedKFold
from museotoolbox import datasets, processing
##############################################################################
# Load HistoricalMap dataset
# -------------------------------------------
raster, vector = datasets.load_historical_data(low_res=True)
field = 'Class'
y = processing.read_vector_values(vector, field)
##############################################################################
# Create CV
# -------------------------------------------
SKF = RandomStratifiedKFold(n_splits=2,
n_repeats=2,
random_state=12,
verbose=False)
for tr, vl in SKF.split(X=None, y=y):
print(tr, vl)
###############################################################################
""" ############################################################################## # Import librairies # ------------------------------------------- from museotoolbox.ai import SuperLearner from museotoolbox.cross_validation import RandomStratifiedKFold from museotoolbox.charts import PlotConfusionMatrix from museotoolbox import datasets from sklearn.ensemble import RandomForestClassifier ############################################################################## # Load HistoricalMap dataset # ------------------------------------------- X, y = datasets.load_historical_data(low_res=True, return_X_y=True) ############################################################################## # Create CV # ------------------------------------------- RSKF = RandomStratifiedKFold(n_splits=2, random_state=12, verbose=False) ############################################################################## # Initialize Random-Forest # --------------------------- classifier = RandomForestClassifier() ############################################################################## # Start learning # ---------------------------
# -*- coding: utf-8 -*-
"""
Created on Sun Nov 24 12:03:31 2019
@author: nicolas
"""
# -*- coding: utf-8 -*-
import unittest
import os
import numpy as np
from museotoolbox.datasets import load_historical_data
from museotoolbox import cross_validation
from museotoolbox import processing
raster, vector = load_historical_data()
X, y, g = load_historical_data(return_X_y_g=True)
distance_matrix = processing.get_distance_matrix(raster, vector)
n_class = len(np.unique(y, return_counts=True)[1])
smallest_class = np.min(np.unique(y, return_counts=True)[1])
class TestCV(unittest.TestCase):
def test_loo(self):
for split in [False, 1, 2, 5]:
cv = cross_validation.LeaveOneOut(n_repeats=split,
random_state=split,
verbose=split)
if split == False:
assert (cv.get_n_splits(X, y) == np.min(
Create a raster mask from vector. """ ############################################################################## # Import librairies # ------------------------------------------- from museotoolbox.processing import image_mask_from_vector from museotoolbox.datasets import load_historical_data ############################################################################## # Load HistoricalMap dataset # ------------------------------------------- raster, vector = load_historical_data() ############################################################################## # Rasterize vector # ----------------------------------------- ############################################################################## # Default, invert is False, it means only polygons will be kept (the rest is set to nodata) image_mask_from_vector(vector, raster, '/tmp/mask.tif', invert=False) ############################################################################## # If invert is set to True, it means polygons will be set to nodata image_mask_from_vector(vector, raster, '/tmp/maskInvert.tif', invert=True) ####################### # Plot result
This example shows how to make a Spatial Leave-One-SubGroup-Out.
"""
##############################################################################
# Import librairies
# -------------------------------------------
import numpy as np
from museotoolbox.cross_validation import SpatialLeaveOneSubGroupOut
from museotoolbox import datasets, processing
##############################################################################
# Load HistoricalMap dataset
# -------------------------------------------
_, centroid = datasets.load_historical_data(low_res=True, centroid=True)
raster, vector = datasets.load_historical_data(low_res=True)
field = 'Class'
##############################################################################
# Extract label ('Class' field) and groups ('uniquefid' field)
# Compute distanceMatrix with centroid (one point per group)
X, y, groups = processing.extract_ROI(raster, vector, field, 'uniquefid')
distance_matrix, distance_label = processing.get_distance_matrix(
raster, centroid, 'uniquefid')
##############################################################################
# Create CV
# -------------------------------------------
This example shows how to make a Leave One Out for each class.
"""
##############################################################################
# Import librairies
# -------------------------------------------
from museotoolbox.cross_validation import LeaveOneOut
from museotoolbox import datasets
##############################################################################
# Load HistoricalMap dataset
# -------------------------------------------
X,y = datasets.load_historical_data(return_X_y=True,low_res=True)
##############################################################################
# Create CV
# -------------------------------------------
LOOPC = LeaveOneOut(random_state=8,verbose=False)
for tr,vl in LOOPC.split(X=None,y=y):
print(tr,vl)
###############################################################################
# .. note::
# Split is made to generate each fold
# Show label
for tr,vl in LOOPC.split(X=None,y=y):
