cbur24

import datacube
import matplotlib.pyplot as plt
from matplotlib.pyplot import cm
from matplotlib.patches import Patch
import numpy as np
import sys
import xarray as xr
sys.path.append('../Scripts')
from deafrica_datahandling import load_ard

cbur24

from datacube.utils.geometry import assign_crs
import datacube
import numpy as np
import sys
import xarray as xr

sys.path.append('../Scripts')
from deafrica_bandindices import calculate_indices
from deafrica_temporal_statistics import temporal_statistics
from deafrica_classificationtools import HiddenPrints

cbur24

def random_sampling(da,
                    n,
                    sampling='stratified_random',
                    manual_class_ratios=None,
                    out_fname=None
                   ):
    
    """
    Creates randomly sampled points for post-classification
    accuracy assessment.

cbur24

    
import cartopy.crs as ccrs

def plot_towns(ax, lats, lons, resolution='10m', transform=ccrs.PlateCarree(), zorder=3):
    """
    This function will download the 'populated_places' shapefile from
    NaturalEarth, trim the shapefile based on the limits of the provided
    lat & long coords, and then plot the locations and names of the towns
    on a given GeoAxes.
    

cbur24

import numpy as np
import xarray as xr
from scipy import stats

def significance_tests(xarray_a, xarray_b, t_test=False, levene_test=False,
                       equal_variance = False, nan_policy= 'omit', mask_not_sig = False, 
                       level_of_sig = 0.05, center='mean'):
    """
    This function operates on a per-pixel basis and contains two types of significance tests:
    

cbur24

import xarray as xr
import numpy as np
import joblib
import dask.array as da
from datacube.utils.geometry import assign_crs
from dask_ml.wrappers import ParallelPostFit

def predict_xr(model,
               input_xr,
               chunk_size=None,

cbur24

import sys
import datacube
import xarray as xr
import geopandas as gpd
from datacube.utils import geometry

sys.path.append('../Scripts')
from deafrica_datahandling import load_ard
from deafrica_spatialtools import xr_rasterize

cbur24

import datacube
import numpy as np
import xarray as xr
from odc.algo import xr_reproject
from pyproj import Proj, transform
from datacube.utils.geometry import assign_crs
from datacube.testutils.io import rio_slurp_xarray
from deafrica_tools.bandindices import calculate_indices

def common_ops(ds, era):

cbur24

import xarray as xr
import geopandas as gpd

from dea_tools.spatial import xr_rasterize

#read shapefile
mask_vector = gpd.read_file('mask.shp')

#import xarray ds
ds = xr.open_dataset('testing.nc')

cbur24

import xarray as xr
import numpy as np
import dask
import hdstats
from odc.algo import randomize, reshape_for_geomedian
from odc.algo._dask import reshape_yxbt
from datacube.utils.geometry import assign_crs

def xr_geomad(ds, axis='time', where=None, **kw):
    """