clip = gpd.read_file('data/eastern_south.shp') input_data = gpd.overlay(input_data,clip, how='intersection').reset_index() #------------------------------------------- #predicting using annual MADs and pre-computed other feature saved to disk # load the column_names with open(training_data, 'r') as file: header = file.readline() column_names = header.split()[1:] #load data for calculating annual gm+mads with HiddenPrints(): ds = load_ard(dc=dc, products=products, dask_chunks=dask_chunks, **query) ds = ds / 10000 #compute annual tmads (requires computing annual gm) mads = xr_geomedian_tmad(ds).compute() mads['sdev'] = -np.log(mads['sdev']) mads['bcdev'] = -np.log(mads['bcdev']) mads['edev'] = -np.log(mads['edev']) mads = mads[['sdev','bcdev','edev']] #drop gm mads.to_netcdf(results+ 'input/annual_mads/Eastern_tile_'+g_id+'_annual_mads.nc') mads = mads.chunk(dask_chunks) #load other data - data = xr.open_dataset(results+'input/Eastern_tile_'+g_id+'_inputs.nc').chunk(dask_chunks)
def get_training_data_for_shp(gdf, index, row, out_arrs, out_vars, products, dc_query, custom_func=None, field=None, calc_indices=None, reduce_func=None, drop=True, zonal_stats=None): """ Function to extract data from the ODC for training a machine learning classifier using a geopandas geodataframe of labelled geometries. This function provides a number of pre-defined methods for producing training data, including calcuating band indices, reducing time series using several summary statistics, and/or generating zonal statistics across polygons. The 'custom_func' parameter provides a method for the user to supply a custom function for generating features rather than using the pre-defined methods. Parameters ---------- gdf : geopandas geodataframe geometry data in the form of a geopandas geodataframe products : list a list of products to load from the datacube. e.g. ['ls8_usgs_sr_scene', 'ls7_usgs_sr_scene'] dc_query : dictionary Datacube query object, should not contain lat and long (x or y) variables as these are supplied by the 'gdf' variable field : string A string containing the name of column with class labels. Field must contain numeric values. out_arrs : list An empty list into which the training data arrays are stored. out_vars : list An empty list into which the data varaible names are stored. custom_func : function, optional A custom function for generating feature layers. If this parameter is set, all other options (excluding 'zonal_stats'), will be ignored. The result of the 'custom_func' must be a single xarray dataset containing 2D coordinates (i.e x, y - no time dimension). The custom function has access to the datacube dataset extracted using the 'dc_query' params, along with access to the 'dc_query' dictionary itself, which could be used to load other products besides those specified under 'products'. calc_indices: list, optional If not using a custom func, then this parameter provides a method for calculating a number of remote sensing indices (e.g. `['NDWI', 'NDVI']`). reduce_func : string, optional Function to reduce the data from multiple time steps to a single timestep. Options are 'mean', 'median', 'std', 'max', 'min', 'geomedian'. Ignored if 'custom_func' is provided. drop : boolean, optional , If this variable is set to True, and 'calc_indices' are supplied, the spectral bands will be dropped from the dataset leaving only the band indices as data variables in the dataset. Default is True. zonal_stats : string, optional An optional string giving the names of zonal statistics to calculate for each polygon. Default is None (all pixel values are returned). Supported values are 'mean', 'median', 'max', 'min', and 'std'. Will work in conjuction with a 'custom_func'. Returns -------- Two lists, a list of numpy.arrays containing classes and extracted data for each pixel or polygon, and another containing the data variable names. """ # prevent function altering dictionary kwargs dc_query = deepcopy(dc_query) # remove dask chunks if supplied as using # mulitprocessing for parallization if 'dask_chunks' in dc_query.keys(): dc_query.pop('dask_chunks', None) # connect to datacube dc = datacube.Datacube(app='training_data') # set up query based on polygon (convert to WGS84) geom = geometry.Geometry(gdf.geometry.values[index].__geo_interface__, geometry.CRS('epsg:4326')) # print(geom) q = {"geopolygon": geom} # merge polygon query with user supplied query params dc_query.update(q) # Identify the most common projection system in the input query output_crs = mostcommon_crs(dc=dc, product=products, query=dc_query) # load_ard doesn't handle geomedians # TODO: Add support for other sensors if 'ga_ls8c_gm_2_annual' in products: ds = dc.load(product='ga_ls8c_gm_2_annual', **dc_query) ds = ds.where(ds != 0, np.nan) else: # load data with HiddenPrints(): ds = load_ard(dc=dc, products=products, output_crs=output_crs, **dc_query) # create polygon mask with HiddenPrints(): mask = xr_rasterize(gdf.iloc[[index]], ds) # mask dataset ds = ds.where(mask) # Use custom function for training data if it exists if custom_func is not None: with HiddenPrints(): data = custom_func(ds) else: # first check enough variables are set to run functions if (len(ds.time.values) > 1) and (reduce_func == None): raise ValueError( "You're dataset has " + str(len(ds.time.values)) + " time-steps, please provide a reduction function," + " e.g. reduce_func='mean'") if calc_indices is not None: # determine which collection is being loaded if 'level2' in products[0]: collection = 'c2' elif 'gm' in products[0]: collection = 'c2' elif 'sr' in products[0]: collection = 'c1' elif 's2' in products[0]: collection = 's2' if len(ds.time.values) > 1: if reduce_func in ['mean', 'median', 'std', 'max', 'min']: with HiddenPrints(): data = calculate_indices(ds, index=calc_indices, drop=drop, collection=collection) # getattr is equivalent to calling data.reduce_func method_to_call = getattr(data, reduce_func) data = method_to_call(dim='time') elif reduce_func == 'geomedian': data = GeoMedian().compute(ds) with HiddenPrints(): data = calculate_indices(data, index=calc_indices, drop=drop, collection=collection) else: raise Exception( reduce_func + " is not one of the supported" + " reduce functions ('mean','median','std','max','min', 'geomedian')" ) else: with HiddenPrints(): data = calculate_indices(ds, index=calc_indices, drop=drop, collection=collection) # when band indices are not required, reduce the # dataset to a 2d array through means or (geo)medians if calc_indices is None: if len(ds.time.values) > 1: if reduce_func == 'geomedian': data = GeoMedian().compute(ds) elif reduce_func in ['mean', 'median', 'std', 'max', 'min']: method_to_call = getattr(ds, reduce_func) data = method_to_call('time') else: data = ds.squeeze() if zonal_stats is None: # If no zonal stats were requested then extract all pixel values flat_train = sklearn_flatten(data) # Make a labelled array of identical size flat_val = np.repeat(row[field], flat_train.shape[0]) stacked = np.hstack((np.expand_dims(flat_val, axis=1), flat_train)) elif zonal_stats in ['mean', 'median', 'std', 'max', 'min']: method_to_call = getattr(data, zonal_stats) flat_train = method_to_call() flat_train = flat_train.to_array() stacked = np.hstack((row[field], flat_train)) else: raise Exception( zonal_stats + " is not one of the supported" + " reduce functions ('mean','median','std','max','min')") # Append training data and labels to list out_arrs.append(stacked) out_vars.append([field] + list(data.data_vars))
def get_training_data_for_shp(polygons, out, products, dc_query, field=None, calc_indices=None, reduce_func='median', drop=True, zonal_stats=None, collection='c1'): """ Function to extract data for training a classifier using a shapefile of labelled polygons. Parameters ---------- polygons : geopandas geodataframe polygon data in the form of a geopandas geodataframe out : list Empty list to contain output data. products : list a list of products ot load from the datacube. e.g. ['ls8_usgs_sr_scene', 'ls7_usgs_sr_scene'] dc_query : dictionary Datacube query object, should not contain lat and long (x or y) variables as these are supplied by the 'polygons' variable field : string A string containing name of column with labels in shapefile attribute table. Field must contain numeric values. calc_indices: list, optional An optional list giving the names of any remote sensing indices to be calculated on the loaded data (e.g. `['NDWI', 'NDVI']`. reduce_func : string, optional Function to reduce the data from multiple time steps to a single timestep. Options are 'mean' drop : booleam, optional , 'median', or 'geomedian' If this variable is set to True, and 'calc_indices' are supplied, the spectral bands will be dropped from the dataset leaving only the band indices as data variables in the dataset. Default is False. zonal_stats: string, optional An optional string giving the names of zonal statistics to calculate for the polygon. Default is None (all pixel values). Supported values are 'mean' or 'median' collection: string, optional to calculate band indices, the satellite collection is required. Options include 'c1' for Landsat C1, 'c2' for Landsat C2, and 's2' for Sentinel 2. Returns -------- A list of numpy.arrays containing classes and extracted data for each pixel or polygon. """ #prevent function altering dictionary kwargs dc_query = deepcopy(dc_query) dc = datacube.Datacube(app='training_data') #set up some print statements i = 0 if calc_indices is not None: print("Calculating indices: " + str(calc_indices)) if reduce_func is not None: print("Reducing data using: " + reduce_func) if zonal_stats is not None: print("Taking zonal statistic: " + zonal_stats) # loop through polys and extract training data for index, row in polygons.iterrows(): print(" Feature {:04}/{:04}\r".format(i + 1, len(polygons)), end='') # set up query based on polygon (convert to WGS84) geom = geometry.Geometry(polygons.geometry.values[0].__geo_interface__, geometry.CRS('epsg:4326')) q = {"geopolygon": geom} # merge polygon query with user supplied query params dc_query.update(q) # Identify the most common projection system in the input query output_crs = mostcommon_crs(dc=dc, product=products, query=dc_query) #load_ard doesn't handle geomedians if 'ga_ls8c_gm_2_annual' in products: ds = dc.load(product='ga_ls8c_gm_2_annual', **dc_query) else: # load data with HiddenPrints(): ds = load_ard(dc=dc, products=products, output_crs=output_crs, **dc_query) # create polygon mask mask = rasterio.features.geometry_mask( [geom.to_crs(ds.geobox.crs) for geoms in [geom]], out_shape=ds.geobox.shape, transform=ds.geobox.affine, all_touched=False, invert=False) mask = xr.DataArray(mask, dims=("y", "x")) ds = ds.where(mask == False) # Check if band indices are wanted if calc_indices is not None: if len(ds.time.values) > 1: if reduce_func == 'geomedian': data = GeoMedian().compute(ds) with HiddenPrints(): data = calculate_indices(data, index=calc_indices, drop=drop, collection=collection) elif reduce_func == 'std': with HiddenPrints(): data = calculate_indices(ds, index=calc_indices, drop=drop, collection=collection) data = data.std('time') elif reduce_func == 'mean': with HiddenPrints(): data = calculate_indices(ds, index=calc_indices, drop=drop, collection=collection) data = data.mean('time') elif reduce_func == 'median': with HiddenPrints(): data = calculate_indices(ds, index=calc_indices, drop=drop, collection=collection) data = data.median('time') else: with HiddenPrints(): data = calculate_indices(ds, index=calc_indices, drop=drop, collection=collection) # when band indices are not required, reduce the # dataset to a 2d array through means or (geo)medians if calc_indices is None: if (len(ds.time.values) > 1) and (reduce_func == None): raise ValueError( "You're dataset has " + str(len(ds.time.values)) + "time-steps, please provide a reduction function, e.g. reduce_func='mean'" ) if len(ds.time.values) > 1: if reduce_func == 'geomedian': data = GeoMedian().compute(ds) if reduce_func == 'mean': data = ds.mean('time') if reduce_func == 'std': data = ds.std('time') if reduce_func == 'median': data = ds.median('time') else: data = ds.squeeze() # compute in case we have dask arrays data = data.compute() if zonal_stats is None: # If no summary stats were requested then extract all pixel values flat_train = sklearn_flatten(data) # Make a labelled array of identical size flat_val = np.repeat(row[field], flat_train.shape[0]) stacked = np.hstack((np.expand_dims(flat_val, axis=1), flat_train)) elif zonal_stats == 'mean': flat_train = data.mean(axis=None, skipna=True) flat_train = flat_train.to_array() stacked = np.hstack((row[field], flat_train)) elif zonal_stats == 'median': flat_train = data.median(axis=None, skipna=True) flat_train = flat_train.to_array() stacked = np.hstack((row[field], flat_train)) # Append training data and label to list out.append(stacked) i += 1 # Return a list of labels for columns in output array return [field] + list(data.data_vars)
def run_filmstrip_app(output_name, time_range, time_step, tide_range=(0.0, 1.0), resolution=(-30, 30), max_cloud=0.5, ls7_slc_off=False, size_limit=10000): ''' An interactive app that allows the user to select a region from a map, then load Digital Earth Africa Landsat data and combine it using the geometric median ("geomedian") statistic to reveal the median or 'typical' appearance of the landscape for a series of time periods. The results for each time period are combined into a 'filmstrip' plot which visualises how the landscape has changed in appearance across time, with a 'change heatmap' panel highlighting potential areas of greatest change. For coastal applications, the analysis can be customised to select only satellite images obtained during a specific tidal range (e.g. low, average or high tide). Last modified: April 2020 Parameters ---------- output_name : str A name that will be used to name the output filmstrip plot file. time_range : tuple A tuple giving the date range to analyse (e.g. `time_range = ('1988-01-01', '2017-12-31')`). time_step : dict This parameter sets the length of the time periods to compare (e.g. `time_step = {'years': 5}` will generate one filmstrip plot for every five years of data; `time_step = {'months': 18}` will generate one plot for each 18 month period etc. Time periods are counted from the first value given in `time_range`. tide_range : tuple, optional An optional parameter that can be used to generate filmstrip plots based on specific ocean tide conditions. This can be valuable for analysing change consistently along the coast. For example, `tide_range = (0.0, 0.2)` will select only satellite images acquired at the lowest 20% of tides; `tide_range = (0.8, 1.0)` will select images from the highest 20% of tides. The default is `tide_range = (0.0, 1.0)` which will select all images regardless of tide. resolution : tuple, optional The spatial resolution to load data. The default is `resolution = (-30, 30)`, which will load data at 30 m pixel resolution. Increasing this (e.g. to `resolution = (-100, 100)`) can be useful for loading large spatial extents. max_cloud : float, optional This parameter can be used to exclude satellite images with excessive cloud. The default is `0.5`, which will keep all images with less than 50% cloud. ls7_slc_off : bool, optional An optional boolean indicating whether to include data from after the Landsat 7 SLC failure (i.e. SLC-off). Defaults to False, which removes all Landsat 7 observations > May 31 2003. size_limit : int, optional An optional integer (in hectares) specifying the size limit for the data query. Queries larger than this size will receive a warning that he data query is too large (and may therefore result in memory errors). Returns ------- ds_geomedian : xarray Dataset An xarray dataset containing geomedian composites for each timestep in the analysis. ''' ######################## # Select and load data # ######################## # Define centre_coords as a global variable global centre_coords # Test if centre_coords is in the global namespace; # use default value if it isn't if 'centre_coords' not in globals(): centre_coords = (6.587292, 1.532833) # Plot interactive map to select area basemap = basemap_to_tiles(basemaps.Esri.WorldImagery) geopolygon = select_on_a_map(height='600px', layers=(basemap, ), center=centre_coords, zoom=14) # Set centre coords based on most recent selection to re-focus # subsequent data selections centre_coords = geopolygon.centroid.points[0][::-1] # Test size of selected area msq_per_hectare = 10000 area = (geopolygon.to_crs(crs=CRS('epsg:6933')).area / msq_per_hectare) radius = np.round(np.sqrt(size_limit), 1) if area > size_limit: print(f'Warning: Your selected area is {area:.00f} hectares. ' f'Please select an area of less than {size_limit} hectares.' f'\nTo select a smaller area, re-run the cell ' f'above and draw a new polygon.') else: print('Starting analysis...') # Connect to datacube database dc = datacube.Datacube(app='Change_filmstrips') # Configure local dask cluster create_local_dask_cluster() # Obtain native CRS crs = mostcommon_crs(dc=dc, product='ls5_usgs_sr_scene', query={ 'time': '1990', 'geopolygon': geopolygon }) # Create query based on time range, area selected, custom params query = { 'time': time_range, 'geopolygon': geopolygon, 'output_crs': crs, 'resolution': resolution, 'dask_chunks': { 'x': 3000, 'y': 3000 }, 'align': (resolution[1] / 2.0, resolution[1] / 2.0) } # Load data from all three Landsats warnings.filterwarnings("ignore") ds = load_ard(dc=dc, measurements=['red', 'green', 'blue'], products=[ 'ls5_usgs_sr_scene', 'ls7_usgs_sr_scene', 'ls8_usgs_sr_scene' ], min_gooddata=max_cloud, ls7_slc_off=ls7_slc_off, **query) # Optionally calculate tides for each timestep in the satellite # dataset and drop any observations out side this range if tide_range != (0.0, 1.0): ds = tidal_tag(ds=ds, tidepost_lat=None, tidepost_lon=None) min_tide, max_tide = ds.tide_height.quantile(tide_range).values ds = ds.sel(time=(ds.tide_height >= min_tide) & (ds.tide_height <= max_tide)) ds = ds.drop('tide_height') print(f' Keeping {len(ds.time)} observations with tides ' f'between {min_tide:.2f} and {max_tide:.2f} m') # Create time step ranges to generate filmstrips from bins_dt = pd.date_range(start=time_range[0], end=time_range[1], freq=pd.DateOffset(**time_step)) # Bin all satellite observations by timestep. If some observations # fall outside the upper bin, label these with the highest bin labels = bins_dt.astype('str') time_steps = (pd.cut(ds.time.values, bins_dt, labels=labels[:-1]).add_categories( labels[-1]).fillna(labels[-1])) time_steps_var = xr.DataArray(time_steps, [('time', ds.time)], name='timestep') # Resample data temporally into time steps, and compute geomedians ds_geomedian = ( ds.groupby(time_steps_var).apply(lambda ds_subset: xr_geomedian( ds_subset, num_threads= 1, # disable internal threading, dask will run several concurrently eps=0.2 * (1 / 10_000), # 1/5 pixel value resolution nocheck=True)) ) # disable some checks inside geomedian library that use too much ram
def load_crophealth_data(lat, lon, buffer): """ Loads Landsat 8 analysis-ready data (ARD) product for the crop health case-study area over the last two years. Last modified: April 2020 Parameters ---------- lat: float The central latitude to analyse lon: float The central longitude to analyse buffer: The number of square degrees to load around the central latitude and longitude. For reasonable loading times, set this as `0.1` or lower. Returns ---------- ds: xarray.Dataset data set containing combined, masked data Masked values are set to 'nan' """ # Suppress warnings warnings.filterwarnings('ignore') # Initialise the data cube. 'app' argument is used to identify this app dc = datacube.Datacube(app='Crophealth-app') # Define area to load latitude = (lat - buffer, lat + buffer) longitude = (lon - buffer, lon + buffer) # Specify the date range # Calculated as today's date, subtract 730 days to collect two years of data # Dates are converted to strings as required by loading function below end_date = dt.date.today() start_date = end_date - dt.timedelta(days=730) time = (start_date.strftime("%Y-%m-%d"), end_date.strftime("%Y-%m-%d")) # Construct the data cube query products = ["ls8_usgs_sr_scene"] query = { 'x': longitude, 'y': latitude, 'time': time, 'measurements': [ 'red', 'green', 'blue', 'nir', 'swir2' ], 'output_crs': 'EPSG:6933', 'resolution': (-30, 30) } # Load the data and mask out bad quality pixels ds = load_ard(dc, products=products, min_gooddata=0.5, **query) # Calculate the normalised difference vegetation index (NDVI) across # all pixels for each image. # This is stored as an attribute of the data ds = calculate_indices(ds, index='NDVI', collection='s2') # Return the data return(ds)
def WIT_drill(gdf_poly, time, min_gooddata=0.80, TCW_threshold=-6000, export_csv=None, dask_chunks=None): """ The Wetlands Insight Tool. This function loads FC, WOfS, Landsat-ARD, and calculate tasseled cap wetness, in order to determine the dominant land cover class within a polygon at each satellite observation. The output is a pandas dataframe containing a timeseries of the relative fractions of each class at each time-step. This forms the input to produce a stacked line-plot. Last modified: Feb 2020 Parameters ---------- gdf_poly : geopandas.GeoDataFrame The dataframe must only contain a single row, containing the polygon you wish to interrograte. time : tuple a tuple containing the time range over which to run the WIT. e.g. ('2015-01' , '2019-12') min_gooddata : Float, optional A number between 0 and 1 (e.g 0.8) indicating the minimum percentage of good quality pixels required for a satellite observation to be loaded and therefore included in the WIT plot. Defaults to 0.8, which should be considered a minimum percentage. TCW_threshold : Int, optional The tasseled cap wetness threshold, beyond which a pixel will be considered 'wet'. Defaults to -6000. Consider the surface reflectance scaling of the Landsat product when adjusting this (C2 = 1-65,535) export_csv : str, optional To export the returned pandas dataframe provide a location string (e.g. 'output/results.csv') dask_chunks : dict, optional To lazily load the datasets using dask, pass a dictionary containing the dimensions over which to chunk e.g. {'time':-1, 'x':250, 'y':250}. The function is not currently set up to handle dask arrays very well, so memory efficieny using dask will be of limited use here. Returns ------- PolyDrill_df : Pandas.Dataframe A pandas dataframe containing the timeseries of relative fractions of each land cover class (WOfs, FC, TCW) """ print("working on polygon: " + str(gdf_poly.drop('geometry', axis=1).values) + ". ") # make quaery from polygon geom = geometry.Geometry(gdf_poly.geometry.values[0].__geo_interface__, geometry.CRS("epsg:4326")) query = {"geopolygon": geom, "time": time} # set Sandbox configs to load COG's faster datacube.utils.rio.set_default_rio_config(aws="auto", cloud_defaults=True) # Create a datacube instance dc = datacube.Datacube(app="wetlands insight tool") # find UTM crs for location crs = deafrica_datahandling.mostcommon_crs(dc=dc, product="usgs_ls8c_level2_2", query=query) # load landsat 5,7,8 data ls578_ds = deafrica_datahandling.load_ard( dc=dc, products=["usgs_ls8c_level2_2"], output_crs=crs, min_gooddata=min_gooddata, measurements=["red", "green", "blue", "nir", "swir_1", "swir_2"], align=(15, 15), dask_chunks=dask_chunks, group_by='solar_day', resolution=(-30, 30), **query, ) # mask the data with our original polygon to remove extra data data = ls578_ds mask = rasterio.features.geometry_mask( [geom.to_crs(data.geobox.crs) for geoms in [geom]], out_shape=data.geobox.shape, transform=data.geobox.affine, all_touched=False, invert=False, ) # mask the data with the polygon mask_xr = xr.DataArray(mask, dims=("y", "x")) ls578_ds = data.where(mask_xr == False) print("size of wetlands array: " + str(ls578_ds.isel(time=1).red.values.shape)) ls578_ds = ls578_ds.compute() # calculate tasselled cap wetness within masked AOI print("calculating tasseled cap index ") tci = thresholded_tasseled_cap(ls578_ds, wetness_threshold=TCW_threshold, drop=True, drop_tc_bands=True) # select only finite values (over threshold values) tcw = xr.ufuncs.isfinite(tci.wetness_thresholded) # #reapply the polygon mask tcw = tcw.where(mask_xr == False) print("Loading WOfS layers ") wofls = dc.load( product="ga_ls8c_wofs_2", like=ls578_ds, fuse_func=wofs_fuser, dask_chunks=dask_chunks, ) wofls = wofls.where(wofls.time == tcw.time) # #reapply the polygon mask wofls = wofls.where(mask_xr == False) wofls = wofls.compute() wet_wofs = wofls.where(wofls.water == 128) # use bit values for wet (128) and terrain/low-angle (8) shadow_wofs = wofls.where(wofls.water == 136) # bit values for wet (128) and sea (4) sea_wofs = wofls.where(wofls.water == 132) # bit values for wet (128) and sea (4) and terrain/low-angle (8) sea_shadow_wofs = wofls.where(wofls.water == 140) # load Fractional cover print("Loading fractional Cover") # load fractional cover fc_ds = dc.load( product="ga_ls8c_fractional_cover_2", dask_chunks=dask_chunks, like=ls578_ds, measurements=["pv", "npv", "bs"], ) # use landsat data set to cloud mask FC fc_ds = fc_ds.where(ls578_ds.red) # mask with polygon fc_ds = fc_ds.where(mask_xr == False) fc_ds = fc_ds.compute() fc_ds_noTCW = fc_ds.where(tcw == False) print("Generating classification") # match timesteps fc_ds_noTCW = fc_ds_noTCW.where(fc_ds_noTCW.time == tcw.time) # following robbi's advice, cast the dataset to a dataarray maxFC = fc_ds_noTCW.to_array(dim="variable", name="maxFC") # turn FC array into integer only as nanargmax doesn't seem to handle floats the way we want it to FC_int = maxFC.astype("int8") # use numpy.nanargmax to get the index of the maximum value along the variable dimension # BSPVNPV=np.nanargmax(FC_int, axis=0) BSPVNPV = FC_int.argmax(dim="variable") FC_mask = xr.ufuncs.isfinite(maxFC).all(dim="variable") # #re-mask with nans to remove no-data BSPVNPV = BSPVNPV.where(FC_mask) # restack the Fractional cover dataset all together # CAUTION:ARGMAX DEPENDS ON ORDER OF VARIABALES IN # DATASET, THESE WILL BE DIFFERENT FOR DIFFERENT COLLECTIONS. # NEED TO ADJUST 0,1,2 BELOW DEPENDING ON ORDER OF FC VARIABLES # IN THE DATASET. FC_dominant = xr.Dataset({ "BS": (BSPVNPV == 2).where(FC_mask), "PV": (BSPVNPV == 0).where(FC_mask), "NPV": (BSPVNPV == 1).where(FC_mask), }) # count number of Fractional Cover pixels for each cover type in area of interest FC_count = FC_dominant.sum(dim=["x", "y"]) # number of pixels in area of interest pixels = (mask_xr == 0).sum(dim=["x", "y"]) # count number of tcw pixels tcw_pixel_count = tcw.sum(dim=["x", "y"]) # return FC_dominant, FC_mask, BSPVNPV, fc_ds, ls578_ds # number of pixels in area of interest pixels = (mask_xr == 0).sum(dim=["x", "y"]) wofs_pixels = (wet_wofs.water.count(dim=["x", "y"]) + shadow_wofs.water.count(dim=["x", "y"]) + sea_wofs.water.count(dim=["x", "y"]) + sea_shadow_wofs.water.count(dim=["x", "y"])) # count percentage of area of wofs wofs_area_percent = (wofs_pixels / pixels) * 100 # count number of tcw pixels tcw_pixel_count = tcw.sum(dim=["x", "y"]) # calculate percentage area wet tcw_area_percent = (tcw_pixel_count / pixels) * 100 # calculate wet not wofs tcw_less_wofs = tcw_area_percent - wofs_area_percent # Fractional cover pixel count method # Get number of FC pixels, divide by total number of pixels per polygon # Work out the number of nodata pixels in the data, so that we can graph the variables by number of observed pixels. Bare_soil_percent = (FC_count.BS / pixels) * 100 Photosynthetic_veg_percent = (FC_count.PV / pixels) * 100 NonPhotosynthetic_veg_percent = (FC_count.NPV / pixels) * 100 NoData = (100 - wofs_area_percent - tcw_less_wofs - Photosynthetic_veg_percent - NonPhotosynthetic_veg_percent - Bare_soil_percent) NoDataPixels = (NoData / 100) * pixels # Fractional cover pixel count method # Get number of FC pixels, divide by total number of pixels per polygon Bare_soil_percent2 = (FC_count.BS / (pixels - NoDataPixels)) * 100 Photosynthetic_veg_percent2 = (FC_count.PV / (pixels - NoDataPixels)) * 100 NonPhotosynthetic_veg_percent2 = (FC_count.NPV / (pixels - NoDataPixels)) * 100 # count percentage of area of wofs wofs_area_percent2 = (wofs_pixels / (pixels - NoDataPixels)) * 100 # wofs_area_percent wofs_area_percent = (wofs_pixels / pixels) * 100 # count number of tcw pixels tcw_pixel_count2 = tcw.sum(dim=["x", "y"]) # calculate percentage area wet tcw_area_percent2 = (tcw_pixel_count2 / (pixels - NoDataPixels)) * 100 # calculate wet not wofs tcw_less_wofs2 = tcw_area_percent2 - wofs_area_percent2 # last check for timestep matching before we plot wofs_area_percent2 = wofs_area_percent2.where( wofs_area_percent2.time == Bare_soil_percent2.time) Bare_soil_percent2 = Bare_soil_percent2.where( Bare_soil_percent2.time == wofs_area_percent2.time) Photosynthetic_veg_percent2 = Photosynthetic_veg_percent2.where( Photosynthetic_veg_percent2.time == wofs_area_percent2.time) NonPhotosynthetic_veg_percent2 = NonPhotosynthetic_veg_percent2.where( NonPhotosynthetic_veg_percent2.time == wofs_area_percent2.time) # start setup of dataframe by adding only one dataset WOFS_df = pd.DataFrame( data=wofs_area_percent2.data, index=wofs_area_percent2.time.values, columns=["wofs_area_percent"], ) # add data into pandas dataframe for export WOFS_df["wet_percent"] = tcw_less_wofs2.data WOFS_df["green_veg_percent"] = Photosynthetic_veg_percent2.data WOFS_df["dry_veg_percent"] = NonPhotosynthetic_veg_percent2.data WOFS_df["bare_soil_percent"] = Bare_soil_percent2.data # call the composite dataframe something sensible, like PolyDrill PolyDrill_df = WOFS_df.round(2) # save the csv of the output data used to create the stacked plot for the polygon drill if export_csv: print('exporting csv: ' + export_csv) PolyDrill_df.to_csv(export_csv, index_label="Datetime") ls578_ds = None data = None fc_ds = None wofls = None tci = None return PolyDrill_df