def run_bfast(indice_array):
'''
Runs BFAST algorithm
Input:
indice_array: Array[] sorted 3D array with image arrays for the whole period
Output:
Breaks and mean of timeseries
'''
print("starting Bfast Process")
# set parameters
k = 3
freq = 30
trend = True
hfrac = 0.25
level = 0.05
start_hist = datetime(2013, 8, 1) # set start of history period
start_monitor = datetime(2019, 7, 1) # set start of monitoring perios
end_monitor = datetime(2020, 7, 31) # set end of monitoring period
dates = pd.date_range('2013-08-01', '2020-07-31',
freq='MS') # create data array
dates2 = [pd.to_datetime(date) for date in dates]
nancount = numpy.count_nonzero(numpy.isnan(indice_array))
print(f"Timeseries has {nancount} NANs")
indice_array = numpy.where(numpy.isnan(indice_array), -9999,
indice_array) # supstitute noData values
indice_array = indice_array * 10000
indice_array = indice_array.astype(int)
data, dates = crop_data_dates(indice_array, dates2, start_hist,
end_monitor) # crop array
while len(dates2) > data.shape[0]:
dates2.pop()
if len(dates2) < data.shape[0]:
dates2.insert(0, datetime(2013, 1, 1))
print("First date: {}".format(dates2[0]))
print("Last date: {}".format(dates2[-1]))
print("Shape of data array: {}".format(data.shape))
print(f'Number of dates {len(dates2)}')
# create BFAST model
model = BFASTMonitor(start_monitor,
freq=freq,
k=k,
hfrac=hfrac,
trend=trend,
level=level,
backend='python',
verbose=1)
# data = data[:, 2330:3000, :]
model.fit(data, dates, n_chunks=5,
nan_value=-9999) # fit model to timeseries
# bfastSingle.fit_single(data, dates2, model)
# save results
breaks = model.breaks
means = model.means
return breaks, means # return detected breaks in timeseries and mean values of pixel
def run_bfast(self, block):
'''Runs bfastmonitor over the give timeseries with the parameters set in self.set_parameters
parameters:
-----------
block: numpy array, 3D numpy array to run bfast upon
'''
data, self.cropped_dates = crop_data_dates(block, self.dates,
self.start_hist,
self.end_monitor)
# only apply on a small subset
#data = data[:,:80,:80]
# change nans to a number bfastmonitor-GPU can work with
where_are_NaNs = isnan(data)
data[where_are_NaNs] = -32768
# fit model
self.model.fit(data, self.cropped_dates, nan_value=-32768)
# save breaks and mean magnitudes
breaks = self.model.breaks # index of date that has a break in dates
means = self.model.means # magnitudes of breaks
return (breaks, means)
def apply_datacube(udf_cube: DataCube, context: dict) -> DataCube:
"""
Apply the BFASTmonitor method to detect a break at the end of time-series of the datacube.
This UDF reduce the time dimension of the input datacube.
:param udf_cube: the openEO virtual DataCube object
:return DataCube(breaks_xr):
"""
from datetime import datetime
# convert the openEO datacube into the xarray DataArray structure
my_xarray: xr.DataArray = udf_cube.get_array()
#select single band, removes band dimension
my_xarray = my_xarray.sel(bands='VV')
#
start_hist = datetime(2017, 5, 1)
start_monitor = datetime(2019, 1, 1)
end_monitor = datetime(2019, 12, 29)
# get the dates from the data cube:
dates = [
pd.Timestamp(date).to_pydatetime()
for date in my_xarray.coords['t'].values
]
# pre-processing - crop the input data cube according to the history and monitor periods:
data, dates = crop_data_dates(my_xarray.values, dates, start_hist,
end_monitor)
# !!! Note !!! that data has the shape 91, and not 92 for our dataset. The reason is the definition in
# the bfast utils.py script where the start_hist is set < than dates, and not <= than dates.
# -------------------------------------
# specify the BFASTmonitor parameters:
model = BFASTMonitor(start_monitor,
freq=31,
k=3,
verbose=1,
hfrac=0.25,
trend=True,
level=0.05,
backend='python')
# run the monitoring:
# model.fit(data, dates, nan_value=udf_data.nodatavals[0])
model.fit(data, dates)
# get the detected breaks as an xarray Data Array:
breaks_xr = xr.DataArray(
model.breaks,
coords=[my_xarray.coords['x'].values, my_xarray.coords['y'].values],
dims=['x', 'y'])
# return the breaks as openEO DataCube:
return DataCube(breaks_xr)
def run_bfast(indice_array):
# parameters
k = 3
freq = 30
trend = True
hfrac = 0.25
level = 0.05
start_hist = datetime(2013, 4,
1) # no data for the first three months of 2013
start_monitor = datetime(2016, 7, 1)
end_monitor = datetime(2018, 12, 31)
dates = pd.date_range('2013-04-01', '2018-7-31', freq='MS')
dates2 = [pd.to_datetime(date) for date in dates]
indice_array = numpy.where(numpy.isnan(indice_array), -9999, indice_array)
data, dates2 = crop_data_dates(indice_array, dates2, start_hist,
end_monitor)
# data = data * 10000
data = data.astype(int)
while len(dates2) > data.shape[0]:
dates2.pop()
if len(dates2) < data.shape[0]:
dates2.insert(0, datetime(2013, 1, 1))
print("First date: {}".format(dates2[0]))
print("Last date: {}".format(dates2[-1]))
print("Shape of data array: {}".format(data.shape))
print(f'Number of dates {len(dates2)}')
model = BFASTMonitor(start_monitor,
freq=freq,
k=k,
hfrac=hfrac,
trend=trend,
level=level,
backend='python',
verbose=1)
# data = data[:, 2330:3000, :]
model.fit(data, dates2, nan_value=-9999)
# bfastSingle.fit_single(data, dates2, model)
# visualize results
breaks = model.breaks
means = model.means
return breaks, means
def bfast4openeo(udf_data):
#
from bfast import BFASTMonitor
from bfast.utils import crop_data_dates
from datetime import datetime
import xarray as xr
import pandas as pd
import numpy as np
#
start_hist = datetime(2016, 12, 31)
start_monitor = datetime(2019, 1, 1)
end_monitor = datetime(2019, 12, 29)
# get the dates from the data cube:
dates = [
pd.Timestamp(date).to_pydatetime()
for date in udf_data.coords['time'].values
]
# pre-processing - crop the input data cube according to the history and monitor periods:
data, dates = crop_data_dates(udf_data.values, dates, start_hist,
end_monitor)
# !!! Note !!! that data has the shape 91, and not 92 for our dataset. The reason is the definition in
# the bfast utils.py script where the start_hist is set < than dates, and not <= than dates.
# -------------------------------------
# specify the BFASTmonitor parameters:
model = BFASTMonitor(start_monitor,
freq=31,
k=3,
verbose=1,
hfrac=0.25,
trend=True,
level=0.05,
backend='python')
# run the monitoring:
# model.fit(data, dates, nan_value=udf_data.nodatavals[0])
model.fit(data, dates)
# get the detected breaks as an xarray Data Array:
# !!! question !!! are those breaks identical to the breaks we get from R script?
breaks_xr = xr.DataArray(
model.breaks,
coords=[udf_data.coords['y'].values, udf_data.coords['x'].values],
dims=['y', 'x'])
return breaks_xr
if not os.path.isdir("data/peru_small"):
os.makedirs("data/peru_small")
if not os.path.exists(ifile_meta):
url = 'https://sid.erda.dk/share_redirect/fcwjD77gUY/dates.txt'
wget.download(url, ifile_meta)
if not os.path.exists(ifile_data):
url = 'https://sid.erda.dk/share_redirect/fcwjD77gUY/data.npy'
wget.download(url, ifile_data)
data_orig = numpy.load(ifile_data)
with open(ifile_meta) as f:
dates = f.read().split('\n')
dates = [datetime.strptime(d, '%Y-%m-%d') for d in dates if len(d) > 0]
data, dates = crop_data_dates(data_orig, dates, start_hist, end_monitor)
print("First date: {}".format(dates[0]))
print("Last date: {}".format(dates[-1]))
print("Shape of data array: {}".format(data.shape))
# fit BFASTMontiro model
model = BFASTMonitor(
start_monitor,
freq=freq,
k=k,
hfrac=hfrac,
trend=trend,
level=level,
backend='opencl',
verbose=1,
device_id=0,
def run_bfast_(backend,
k=3,
freq=365,
trend=False,
hfrac=0.25,
level=0.05,
start_hist=datetime(2002, 1, 1),
start_monitor=datetime(2010, 1, 1),
end_monitor=datetime(2018, 1, 1)):
print("Running the {} backend".format(backend))
# download and parse input data
ifile_meta = "data/peru_small/dates.txt"
ifile_data = "data/peru_small/data.npy"
if not os.path.isdir("data/peru_small"):
os.makedirs("data/peru_small")
if not os.path.exists(ifile_meta):
url = 'https://sid.erda.dk/share_redirect/fcwjD77gUY/dates.txt'
wget.download(url, ifile_meta)
if not os.path.exists(ifile_data):
url = 'https://sid.erda.dk/share_redirect/fcwjD77gUY/data.npy'
wget.download(url, ifile_data)
data_orig = np.load(ifile_data)
with open(ifile_meta) as f:
dates = f.read().split('\n')
dates = [datetime.strptime(d, '%Y-%m-%d') for d in dates if len(d) > 0]
data, dates = crop_data_dates(data_orig, dates, start_hist, end_monitor)
# fit BFASTMontiro model
model = BFASTMonitor(
start_monitor,
freq=freq,
k=k,
hfrac=hfrac,
trend=trend,
level=level,
backend=backend,
verbose=1,
device_id=0,
)
#data = data[:,:50,:50]
start_time = time.time()
if backend == "opencl":
model.fit(data, dates, n_chunks=5, nan_value=-32768)
else:
model.fit(data, dates, nan_value=-32768)
end_time = time.time()
print("All computations have taken {} seconds.".format(end_time -
start_time))
# visualize results
breaks = model.breaks
means = model.means
magnitudes = model.magnitudes
return breaks, means, magnitudes