cbur24

from pylab import *
import numpy as np

n=17
cmap = cm.get_cmap('magma', n)  

for i,j in zip(range(cmap.N), np.arange(0,0.425,0.025)):
    rgba = cmap(i)
    # rgb2hex accepts rgb or rgba
    print("{'value': "+str(round(j,3))+", 'color': "+"'"+  matplotlib.colors.rgb2hex(rgba)+"'"+"},")

cbur24

import odc.algo

#Extract boolean mask
mask = odc.algo.enum_to_bool(ds.SCL, 
                             categories=['cloud shadows', 'cloud medium probability',
                                         'cloud high probability', 'thin cirrus'])
                             
# Close mask to remove small holes in cloud, open mask to 
# remove narrow false positive cloud, then dilate
mask = odc.algo.binary_closing(mask, 2)

cbur24

import xarray as xr
import numpy as np
import dask
import hdstats
from odc.algo import randomize
from odc.algo._dask import reshape_yxbt
from odc.geo.xr import assign_crs

def xr_geomad_dask(ds, **kw):
    """

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):
    """

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 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 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 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 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 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.