def check_features_block_windows(features, src, bidx):
"""Compare GeoJSON features to a datasource's blocks + windows.
Parameters
----------
features : iter
GeoJSON features
src : a dataset object opened in 'r' mode
Open input datasource
Returns
-------
bool
``True`` if the two block/window streams match and ``False`` otherwise
"""
out = []
iterator = zip_longest(features, src.block_windows(bidx=bidx))
for feat, (block, window) in iterator:
out.append(np.array_equal(
json.loads(feat['properties']['block']),
block))
f_win = feat['properties']['window']
assert f_win['col_off'] == window.col_off
assert f_win['row_off'] == window.row_off
return all(out)
def check_features_block_windows(features, src, bidx):
"""Compare GeoJSON features to a datasource's blocks + windows.
Parameters
----------
features : iter
GeoJSON features.
src : RasterReader
Open input datasource.
Returns
-------
bool
``True`` if the two block/window streams match and ``False`` otherwise.
"""
out = []
iterator = zip_longest(features, src.block_windows(bidx=bidx))
for feat, (block, window) in iterator:
out.append(np.array_equal(
json.loads(feat['properties']['block']),
block))
out.append(np.array_equal(
json.loads(feat['properties']['window']),
window))
return all(out)
def check_features_block_windows(features, src, bidx):
"""Compare GeoJSON features to a datasource's blocks + windows.
Parameters
----------
features : iter
GeoJSON features
src : a dataset object opened in 'r' mode
Open input datasource
Returns
-------
bool
``True`` if the two block/window streams match and ``False`` otherwise
"""
out = []
iterator = zip_longest(features, src.block_windows(bidx=bidx))
for feat, (block, window) in iterator:
out.append(
np.array_equal(json.loads(feat['properties']['block']), block))
f_win = feat['properties']['window']
assert f_win['col_off'] == window.col_off
assert f_win['row_off'] == window.row_off
return all(out)
def stack(ctx, files, output, driver, bidx, photometric, force_overwrite,
creation_options):
"""Stack a number of bands from one or more input files into a
multiband dataset.
Input datasets must be of a kind: same data type, dimensions, etc. The
output is cloned from the first input.
By default, rio-stack will take all bands from each input and write them
in same order to the output. Optionally, bands for each input may be
specified using a simple syntax:
--bidx N takes the Nth band from the input (first band is 1).
--bidx M,N,0 takes bands M, N, and O.
--bidx M..O takes bands M-O, inclusive.
--bidx ..N takes all bands up to and including N.
--bidx N.. takes all bands from N to the end.
Examples, using the Rasterio testing dataset, which produce a copy.
rio stack RGB.byte.tif -o stacked.tif
rio stack RGB.byte.tif --bidx 1,2,3 -o stacked.tif
rio stack RGB.byte.tif --bidx 1..3 -o stacked.tif
rio stack RGB.byte.tif --bidx ..2 RGB.byte.tif --bidx 3.. -o stacked.tif
"""
verbosity = (ctx.obj and ctx.obj.get('verbosity')) or 2
logger = logging.getLogger('rio')
try:
with rasterio.Env(CPL_DEBUG=verbosity > 2):
output, files = resolve_inout(files=files,
output=output,
force_overwrite=force_overwrite)
output_count = 0
indexes = []
for path, item in zip_longest(files, bidx, fillvalue=None):
with rasterio.open(path) as src:
src_indexes = src.indexes
if item is None:
indexes.append(src_indexes)
output_count += len(src_indexes)
elif '..' in item:
start, stop = map(lambda x: int(x) if x else None,
item.split('..'))
if start is None:
start = 1
indexes.append(src_indexes[slice(start - 1, stop)])
output_count += len(src_indexes[slice(start - 1, stop)])
else:
parts = list(map(int, item.split(',')))
if len(parts) == 1:
indexes.append(parts[0])
output_count += 1
else:
parts = list(parts)
indexes.append(parts)
output_count += len(parts)
with rasterio.open(files[0]) as first:
kwargs = first.meta
kwargs.update(**creation_options)
kwargs['transform'] = kwargs.pop('affine')
kwargs.update(driver=driver, count=output_count)
if photometric:
kwargs['photometric'] = photometric
with rasterio.open(output, 'w', **kwargs) as dst:
dst_idx = 1
for path, index in zip(files, indexes):
with rasterio.open(path) as src:
if isinstance(index, int):
data = src.read(index)
dst.write(data, dst_idx)
dst_idx += 1
elif isinstance(index, collections.Iterable):
data = src.read(index)
dst.write(data, range(dst_idx,
dst_idx + len(index)))
dst_idx += len(index)
except Exception:
logger.exception("Exception caught during processing")
raise click.Abort()
def show_hist(source, bins=10, masked=True, title='Histogram'):
"""Easily display a histogram with matplotlib.
Parameters
----------
bins : int, optional
Compute histogram across N bins.
data : np.array or rasterio.Band or tuple(dataset, bidx)
Input data to display. The first three arrays in multi-dimensional
arrays are plotted as red, green, and blue.
masked : bool, optional
When working with a `rasterio.Band()` object, specifies if the data
should be masked on read.
title : str, optional
Title for the figure.
"""
if plt is None: # pragma: no cover
raise ImportError("Could not import matplotlib")
if isinstance(source, (tuple, rasterio.Band)):
arr = source[0].read(source[1], masked=masked)
else:
arr = source
# The histogram is computed individually for each 'band' in the array
# so we need the overall min/max to constrain the plot
rng = arr.min(), arr.max()
if len(arr.shape) is 2:
arr = [arr]
colors = ['gold']
else:
colors = ('red', 'green', 'blue', 'violet', 'gold', 'saddlebrown')
# If a rasterio.Band() is given make sure the proper index is displayed
# in the legend.
if isinstance(source, (tuple, rasterio.Band)):
labels = [str(source[1])]
else:
labels = (str(i + 1) for i in range(len(arr)))
# This loop should add a single plot each band in the input array,
# regardless of if the number of bands exceeds the number of colors.
# The colors slicing ensures that the number of iterations always
# matches the number of bands.
# The goal is to provide a curated set of colors for working with
# smaller datasets and let matplotlib define additional colors when
# working with larger datasets.
for bnd, color, label in zip_longest(arr, colors[:len(arr)], labels):
plt.hist(bnd.flatten(),
bins=bins,
alpha=0.5,
color=color,
label=label,
range=rng)
plt.legend(loc="upper right")
plt.title(title, fontweight='bold')
plt.grid(True)
plt.xlabel('DN')
plt.ylabel('Frequency')
fig = plt.gcf()
fig.show()
def stack(ctx, files, output, driver, bidx, photometric, force_overwrite,
creation_options):
"""Stack a number of bands from one or more input files into a
multiband dataset.
Input datasets must be of a kind: same data type, dimensions, etc. The
output is cloned from the first input.
By default, rio-stack will take all bands from each input and write them
in same order to the output. Optionally, bands for each input may be
specified using a simple syntax:
--bidx N takes the Nth band from the input (first band is 1).
--bidx M,N,0 takes bands M, N, and O.
--bidx M..O takes bands M-O, inclusive.
--bidx ..N takes all bands up to and including N.
--bidx N.. takes all bands from N to the end.
Examples, using the Rasterio testing dataset, which produce a copy.
rio stack RGB.byte.tif -o stacked.tif
rio stack RGB.byte.tif --bidx 1,2,3 -o stacked.tif
rio stack RGB.byte.tif --bidx 1..3 -o stacked.tif
rio stack RGB.byte.tif --bidx ..2 RGB.byte.tif --bidx 3.. -o stacked.tif
"""
logger = logging.getLogger('rio')
try:
with ctx.obj['env']:
output, files = resolve_inout(files=files, output=output,
force_overwrite=force_overwrite)
output_count = 0
indexes = []
for path, item in zip_longest(files, bidx, fillvalue=None):
with rasterio.open(path) as src:
src_indexes = src.indexes
if item is None:
indexes.append(src_indexes)
output_count += len(src_indexes)
elif '..' in item:
start, stop = map(
lambda x: int(x) if x else None, item.split('..'))
if start is None:
start = 1
indexes.append(src_indexes[slice(start - 1, stop)])
output_count += len(src_indexes[slice(start - 1, stop)])
else:
parts = list(map(int, item.split(',')))
if len(parts) == 1:
indexes.append(parts[0])
output_count += 1
else:
parts = list(parts)
indexes.append(parts)
output_count += len(parts)
with rasterio.open(files[0]) as first:
kwargs = first.meta
kwargs.update(**creation_options)
kwargs.update(
driver=driver,
count=output_count)
if photometric:
kwargs['photometric'] = photometric
with rasterio.open(output, 'w', **kwargs) as dst:
dst_idx = 1
for path, index in zip(files, indexes):
with rasterio.open(path) as src:
if isinstance(index, int):
data = src.read(index)
dst.write(data, dst_idx)
dst_idx += 1
elif isinstance(index, collections.Iterable):
data = src.read(index)
dst.write(data, range(dst_idx, dst_idx + len(index)))
dst_idx += len(index)
except Exception:
logger.exception("Exception caught during processing")
raise click.Abort()
def show_hist(source, bins=10, masked=True, title='Histogram'):
"""Easily display a histogram with matplotlib.
Parameters
----------
bins : int, optional
Compute histogram across N bins.
data : np.array or rasterio.Band or tuple(dataset, bidx)
Input data to display. The first three arrays in multi-dimensional
arrays are plotted as red, green, and blue.
masked : bool, optional
When working with a `rasterio.Band()` object, specifies if the data
should be masked on read.
title : str, optional
Title for the figure.
"""
if plt is None: # pragma: no cover
raise ImportError("Could not import matplotlib")
if isinstance(source, (tuple, rasterio.Band)):
arr = source[0].read(source[1], masked=masked)
else:
arr = source
# The histogram is computed individually for each 'band' in the array
# so we need the overall min/max to constrain the plot
rng = arr.min(), arr.max()
if len(arr.shape) is 2:
arr = [arr]
colors = ['gold']
else:
colors = ('red', 'green', 'blue', 'violet', 'gold', 'saddlebrown')
# If a rasterio.Band() is given make sure the proper index is displayed
# in the legend.
if isinstance(source, (tuple, rasterio.Band)):
labels = [str(source[1])]
else:
labels = (str(i + 1) for i in range(len(arr)))
# This loop should add a single plot each band in the input array,
# regardless of if the number of bands exceeds the number of colors.
# The colors slicing ensures that the number of iterations always
# matches the number of bands.
# The goal is to provide a curated set of colors for working with
# smaller datasets and let matplotlib define additional colors when
# working with larger datasets.
for bnd, color, label in zip_longest(arr, colors[:len(arr)], labels):
plt.hist(
bnd.flatten(),
bins=bins,
alpha=0.5,
color=color,
label=label,
range=rng
)
plt.legend(loc="upper right")
plt.title(title, fontweight='bold')
plt.grid(True)
plt.xlabel('DN')
plt.ylabel('Frequency')
fig = plt.gcf()
fig.show()