def test_is_geographic(tmpdir):
ds = Dataset(str(tmpdir.join('test.nc')), 'w')
ds.createDimension('lat', 1)
ds.createDimension('lon', 1)
ds.createVariable('data', 'S1', dimensions=('lat', 'lon'))
assert is_geographic(ds, 'data') == True
ds.createDimension('foo', 1)
ds.createDimension('bar', 1)
ds.createVariable('data2', 'S1', dimensions=('foo', 'bar'))
assert is_geographic(ds, 'data2') == False
def describe(path_or_dataset):
if isinstance(path_or_dataset, string_types):
dataset = Dataset(path_or_dataset)
else:
dataset = path_or_dataset
description = {
'dimensions': {},
'variables': {},
'attributes': get_ncattrs(dataset)
}
for dimension_name in dataset.dimensions:
dimension = dataset.dimensions[dimension_name]
description['dimensions'][dimension_name] = {'length': len(dimension)}
for variable_name in dataset.variables:
variable = dataset.variables[variable_name]
if not variable.dimensions:
# Do not collect info about dimensionless variables (e.g., CRS variable)
continue
dtype = str(variable.dtype)
if "'" in dtype:
dtype = dtype.split("'")[1]
attributes = get_ncattrs(variable)
variable_info = {
'attributes':
attributes,
'dimensions':
variable.dimensions,
'data_type':
dtype,
'name':
attributes.get('long_name') or attributes.get('standard_name')
or variable_name
}
if dtype not in ('str', ):
if len(variable.shape) > 2:
# Avoid loading the entire array into memory by iterating along the first index (usually time)
variable_info.update({
'min':
min(variable[i, :].min().item()
for i in range(variable.shape[0])),
'max':
max(variable[i, :].max().item()
for i in range(variable.shape[0]))
})
else:
data = variable[:]
variable_info.update({
'min': data.min().item(),
'max': data.max().item()
})
if variable_name in dataset.dimensions and dtype not in ('str', ):
dimension_variable = dataset.variables[variable_name]
if len(dimension_variable.dimensions
) == 1: # range dimensions don't make sense for interval
interval = get_interval(dimension_variable)
if interval:
variable_info['interval'] = interval
else:
# Data variable
proj4 = get_crs(dataset, variable_name)
#extent
if len(variable.dimensions) >= 2:
x_variable_name = None
y_variable_name = None
time_variable_name = None
for dimension_name in (x for x in variable.dimensions
if x in dataset.variables):
attributes = get_ncattrs(dataset.variables[dimension_name])
standard_name = attributes.get('standard_name', None)
if standard_name in X_DIMENSION_STANDARD_NAMES or dimension_name in X_DIMENSION_COMMON_NAMES:
x_variable_name = dimension_name
elif standard_name in Y_DIMENSION_STANDARD_NAMES or dimension_name in Y_DIMENSION_COMMON_NAMES:
y_variable_name = dimension_name
elif standard_name in TIME_DIMENSION_STANDARD_NAMES or dimension_name in TIME_DIMENSION_COMMON_NAMES:
if len(dataset.dimensions[dimension_name]) > 1:
time_variable_name = dimension_name
if x_variable_name and y_variable_name:
if proj4 is None and is_geographic(dataset, variable_name):
# Assume WGS84
proj4 = PROJ4_GEOGRAPHIC
coordinates = SpatialCoordinateVariables(
SpatialCoordinateVariable(
dataset.variables[x_variable_name]),
SpatialCoordinateVariable(
dataset.variables[y_variable_name]),
Proj(str(proj4)) if proj4 else None)
variable_info['spatial_grid'] = {
'extent': coordinates.bbox.as_dict(),
'x_dimension': x_variable_name,
'x_resolution': coordinates.x.pixel_size,
'y_dimension': y_variable_name,
'y_resolution': coordinates.y.pixel_size
}
if time_variable_name:
time_variable = dataset.variables[time_variable_name]
time_info = {
'dimension': time_variable_name,
}
try:
date_variable = DateVariable(time_variable)
values = date_variable.datetimes
time_info['extent'] = [
values.min().isoformat(),
values.max().isoformat()
]
time_info['interval_unit'] = date_variable.unit
interval = get_interval(time_variable)
if interval is not None:
time_info['interval'] = interval
except ValueError:
pass
variable_info['time'] = time_info
if proj4:
variable_info['proj4'] = proj4
description['variables'][variable_name] = variable_info
return description
def map_eems(
eems_file,
# output_directory,
scale,
format,
src_crs,
resampling):
"""
Render a NetCDF EEMS model to a web map.
"""
from EEMSBasePackage import EEMSCmd, EEMSProgram
model = EEMSProgram(eems_file)
# For each data producing command, store the netcdf file that contains it
file_vars = dict()
raw_variables = set()
for cmd in model.orderedCmds: # This is bottom up, may want to invert
filename = None
variable = None
if cmd.HasResultName():
filename = cmd.GetParam('OutFileName')
variable = cmd.GetResultName()
elif cmd.IsReadCmd():
filename = cmd.GetParam('OutFileName')
variable = cmd.GetParam('NewFieldName')
raw_variables.add(variable)
if filename and variable:
if not filename in file_vars:
file_vars[filename] = []
file_vars[filename].append(variable)
filenames = file_vars.keys()
for filename in filenames:
if not os.path.exists(filename):
raise click.ClickException(
'Could not find data file from EEMS model: {0}'.format(
filename))
dst_crs = 'EPSG:3857'
output_directory = tempfile.mkdtemp()
click.echo('Using temp directory: {0}'.format(output_directory))
# if not os.path.exists(output_directory):
# os.makedirs(output_directory)
# Since fuzzy renderer is hardcoded, we can output it now
fuzzy_renderer = palette_to_stretched_renderer(DEFAULT_PALETTES['fuzzy'],
'1,-1')
fuzzy_renderer.get_legend(image_height=150)[0].to_image().save(
os.path.join(output_directory, 'fuzzy_legend.png'))
template_filename = filenames[0]
template_var = file_vars[template_filename][0]
with Dataset(template_filename) as ds:
var_obj = ds.variables[template_var]
dimensions = var_obj.dimensions
shape = var_obj.shape
num_dimensions = len(shape)
if num_dimensions != 2:
raise click.ClickException(
'Only 2 dimensions are allowed on data variables for now')
ds_crs = get_crs(ds, template_var)
if not ds_crs and is_geographic(ds, template_var):
ds_crs = 'EPSG:4326' # Assume all geographic data is WGS84
src_crs = CRS.from_string(ds_crs) if ds_crs else CRS(
{'init': src_crs}) if src_crs else None
# get transforms, assume last 2 dimensions on variable are spatial in row, col order
y_dim, x_dim = dimensions[-2:]
coords = SpatialCoordinateVariables.from_dataset(
ds, x_dim, y_dim, projection=Proj(src_crs) if src_crs else None)
#
# if mask is not None and not mask.shape == shape[-2:]:
# # Will likely break before this if collecting statistics
# raise click.BadParameter(
# 'mask variable shape does not match shape of input spatial dimensions',
# param='--mask', param_hint='--mask'
# )
#
if not src_crs:
raise click.BadParameter('must provide src_crs to reproject',
param='--src-crs',
param_hint='--src-crs')
dst_crs = CRS.from_string(dst_crs)
src_height, src_width = coords.shape
dst_transform, dst_width, dst_height = calculate_default_transform(
src_crs, dst_crs, src_width, src_height, *coords.bbox.as_list())
reproject_kwargs = {
'src_crs': src_crs,
'src_transform': coords.affine,
'dst_crs': dst_crs,
'dst_transform': dst_transform,
'resampling': getattr(RESAMPLING, resampling),
'dst_shape': (dst_height, dst_width)
}
if not (dst_crs or src_crs):
raise click.BadParameter(
'must provide valid src_crs to get interactive map',
param='--src-crs',
param_hint='--src-crs')
leaflet_anchors = get_leaflet_anchors(
BBox.from_affine(dst_transform,
dst_width,
dst_height,
projection=Proj(dst_crs) if dst_crs else None))
layers = {}
for filename in filenames:
with Dataset(filename) as ds:
click.echo('Processing dataset {0}'.format(filename))
for variable in file_vars[filename]:
click.echo('Processing variable {0}'.format(variable))
if not variable in ds.variables:
raise click.ClickException(
'variable {0} was not found in file: {1}'.format(
variable, filename))
var_obj = ds.variables[variable]
if not var_obj.dimensions == dimensions:
raise click.ClickException(
'All datasets must have the same dimensions for {0}'.
format(variable))
data = var_obj[:]
# if mask is not None:
# data = numpy.ma.masked_array(data, mask=mask)
if variable in raw_variables:
palette = DEFAULT_PALETTES['raw']
palette_stretch = '{0},{1}'.format(data.max(), data.min())
renderer = palette_to_stretched_renderer(
palette, palette_stretch)
renderer.get_legend(
image_height=150, max_precision=2)[0].to_image().save(
os.path.join(output_directory,
'{0}_legend.png'.format(variable)))
else:
renderer = fuzzy_renderer
image_filename = os.path.join(
output_directory, '{0}.{1}'.format(variable, format))
data = warp_array(data, **reproject_kwargs)
render_image(renderer,
data,
image_filename,
scale=scale,
format=format)
local_filename = os.path.split(image_filename)[1]
layers[variable] = local_filename
index_html = os.path.join(output_directory, 'index.html')
with open(index_html, 'w') as out:
template = Environment(
loader=PackageLoader('clover.cli')).get_template('eems_map.html')
out.write(
template.render(layers=json.dumps(layers),
bounds=str(leaflet_anchors),
tree=[[cmd, depth]
for (cmd, depth) in model.GetCmdTree()],
raw_variables=list(raw_variables)))
webbrowser.open(index_html)
def render_netcdf(filename_pattern, variable, output_directory, renderer_file,
save_file, renderer_type, colormap, fill, colorspace,
palette, palette_stretch, scale, id_variable, lh,
legend_breaks, legend_ticks, legend_precision, format,
src_crs, dst_crs, res, resampling, anchors, interactive_map,
mask_path):
"""
Render netcdf files to images.
colormap is ignored if renderer_file is provided
--dst-crs is ignored if using --map option (always uses EPSG:3857
If no colormap or palette is provided, a default palette may be chosen based on the name of the variable.
If provided, mask must be 1 for areas to be masked out, and 0 otherwise. It
must be in the same CRS as the input datasets, and have the same spatial
dimensions.
"""
# Parameter overrides
if interactive_map:
dst_crs = 'EPSG:3857'
filenames = glob.glob(filename_pattern)
if not filenames:
raise click.BadParameter('No files found matching that pattern',
param='filename_pattern',
param_hint='FILENAME_PATTERN')
if not os.path.exists(output_directory):
os.makedirs(output_directory)
mask = get_mask(mask_path) if mask_path is not None else None
if renderer_file is not None and not save_file:
if not os.path.exists(renderer_file):
raise click.BadParameter('does not exist',
param='renderer_file',
param_hint='renderer_file')
# see https://bitbucket.org/databasin/ncdjango/wiki/Home for format
renderer_dict = json.loads(open(renderer_file).read())
if variable in renderer_dict and not 'colors' in renderer_dict:
renderer_dict = renderer_dict[variable]
renderer_type = renderer_dict['type']
if renderer_type == 'stretched':
colors = ','.join([str(c[0]) for c in renderer_dict['colors']])
if 'min' in colors or 'max' in colors or 'mean' in colors:
statistics = collect_statistics(filenames, (variable, ),
mask=mask)[variable]
for entry in renderer_dict['colors']:
if isinstance(entry[0], basestring):
if entry[0] in ('min', 'max', 'mean'):
entry[0] = statistics[entry[0]]
elif '*' in entry[0]:
rel_value, statistic = entry[0].split('*')
entry[0] = float(rel_value) * statistics[statistic]
renderer = renderer_from_dict(renderer_dict)
else:
if renderer_type == 'stretched':
if palette is not None:
renderer = palette_to_stretched_renderer(palette,
palette_stretch,
filenames,
variable,
fill_value=fill,
mask=mask)
elif colormap is None and variable in DEFAULT_PALETTES:
palette, palette_stretch = DEFAULT_PALETTES[variable]
renderer = palette_to_stretched_renderer(palette,
palette_stretch,
filenames,
variable,
fill_value=fill,
mask=mask)
else:
if colormap is None:
colormap = 'min:#000000,max:#FFFFFF'
renderer = colormap_to_stretched_renderer(colormap,
colorspace,
filenames,
variable,
fill_value=fill,
mask=mask)
elif renderer_type == 'classified':
if not palette:
raise click.BadParameter(
'palette required for classified (for now)',
param='--palette',
param_hint='--palette')
renderer = palette_to_classified_renderer(
palette,
filenames,
variable,
method='equal',
fill_value=fill,
mask=mask) # TODO: other methods
if save_file:
if os.path.exists(save_file):
with open(save_file, 'r+') as output_file:
data = json.loads(output_file.read())
output_file.seek(0)
output_file.truncate()
data[variable] = renderer.serialize()
output_file.write(json.dumps(data, indent=4))
else:
with open(save_file, 'w') as output_file:
output_file.write(json.dumps({variable: renderer.serialize()}))
if renderer_type == 'stretched':
if legend_ticks is not None and not legend_breaks:
legend_ticks = [float(v) for v in legend_ticks.split(',')]
legend = renderer.get_legend(
image_height=lh,
breaks=legend_breaks,
ticks=legend_ticks,
max_precision=legend_precision)[0].to_image()
elif renderer_type == 'classified':
legend = composite_elements(renderer.get_legend())
legend.save(
os.path.join(output_directory, '{0}_legend.png'.format(variable)))
with Dataset(filenames[0]) as ds:
var_obj = ds.variables[variable]
dimensions = var_obj.dimensions
shape = var_obj.shape
num_dimensions = len(shape)
if num_dimensions == 3:
if id_variable:
if shape[0] != ds.variables[id_variable][:].shape[0]:
raise click.BadParameter(
'must be same dimensionality as 3rd dimension of {0}'.
format(variable),
param='--id_variable',
param_hint='--id_variable')
else:
# Guess from the 3rd dimension
guess = dimensions[0]
if guess in ds.variables and ds.variables[guess][:].shape[
0] == shape[0]:
id_variable = guess
ds_crs = get_crs(ds, variable)
if not ds_crs and is_geographic(ds, variable):
ds_crs = 'EPSG:4326' # Assume all geographic data is WGS84
src_crs = CRS.from_string(ds_crs) if ds_crs else CRS(
{'init': src_crs}) if src_crs else None
# get transforms, assume last 2 dimensions on variable are spatial in row, col order
y_dim, x_dim = dimensions[-2:]
coords = SpatialCoordinateVariables.from_dataset(
ds,
x_dim,
y_dim,
projection=Proj(src_crs.to_dict()) if src_crs else None)
if mask is not None and not mask.shape == shape[-2:]:
# Will likely break before this if collecting statistics
raise click.BadParameter(
'mask variable shape does not match shape of input spatial dimensions',
param='--mask',
param_hint='--mask')
flip_y = False
reproject_kwargs = None
if dst_crs is not None:
if not src_crs:
raise click.BadParameter('must provide src_crs to reproject',
param='--src-crs',
param_hint='--src-crs')
dst_crs = CRS.from_string(dst_crs)
src_height, src_width = coords.shape
dst_transform, dst_width, dst_height = calculate_default_transform(
src_crs,
dst_crs,
src_width,
src_height,
*coords.bbox.as_list(),
resolution=res)
reproject_kwargs = {
'src_crs': src_crs,
'src_transform': coords.affine,
'dst_crs': dst_crs,
'dst_transform': dst_transform,
'resampling': getattr(RESAMPLING, resampling),
'dst_shape': (dst_height, dst_width)
}
else:
dst_transform = coords.affine
dst_height, dst_width = coords.shape
dst_crs = src_crs
if coords.y.is_ascending_order():
# Only needed if we are not already reprojecting the data, since that will flip it automatically
flip_y = True
if anchors or interactive_map:
if not (dst_crs or src_crs):
raise click.BadParameter(
'must provide at least src_crs to get Leaflet anchors or interactive map',
param='--src-crs',
param_hint='--src-crs')
leaflet_anchors = get_leaflet_anchors(
BBox.from_affine(
dst_transform,
dst_width,
dst_height,
projection=Proj(dst_crs) if dst_crs else None))
if anchors:
click.echo('Anchors: {0}'.format(leaflet_anchors))
layers = {}
for filename in filenames:
with Dataset(filename) as ds:
click.echo('Processing {0}'.format(filename))
filename_root = os.path.split(filename)[1].replace('.nc', '')
if not variable in ds.variables:
raise click.BadParameter(
'variable {0} was not found in file: {1}'.format(
variable, filename),
param='variable',
param_hint='VARIABLE')
var_obj = ds.variables[variable]
if not var_obj.dimensions == dimensions:
raise click.ClickException(
'All datasets must have the same dimensions for {0}'.
format(variable))
if num_dimensions == 2:
data = var_obj[:]
if mask is not None:
data = numpy.ma.masked_array(data, mask=mask)
image_filename = os.path.join(
output_directory,
'{0}_{1}.{2}'.format(filename_root, variable, format))
if reproject_kwargs:
data = warp_array(data, **reproject_kwargs)
render_image(renderer,
data,
image_filename,
scale,
flip_y=flip_y,
format=format)
local_filename = os.path.split(image_filename)[1]
layers[os.path.splitext(local_filename)[0]] = local_filename
elif num_dimensions == 3:
for index in range(shape[0]):
id = ds.variables[id_variable][
index] if id_variable is not None else index
image_filename = os.path.join(
output_directory,
'{0}_{1}__{2}.{3}'.format(filename_root, variable, id,
format))
data = var_obj[index]
if mask is not None:
data = numpy.ma.masked_array(data, mask=mask)
if reproject_kwargs:
data = warp_array(data, **reproject_kwargs)
render_image(renderer,
data,
image_filename,
scale,
flip_y=flip_y,
format=format)
local_filename = os.path.split(image_filename)[1]
layers[os.path.splitext(local_filename)
[0]] = local_filename
# TODO: not tested recently. Make sure still correct
# else:
# # Assume last 2 components of shape are lat & lon, rest are iterated over
# id_variables = None
# if id_variable is not None:
# id_variables = id_variable.split(',')
# for index, name in enumerate(id_variables):
# if name:
# assert data.shape[index] == ds.variables[name][:].shape[0]
#
# ranges = []
# for dim in data.shape[:-2]:
# ranges.append(range(0, dim))
# for combined_index in product(*ranges):
# id_parts = []
# for index, dim_index in enumerate(combined_index):
# if id_variables is not None and index < len(id_variables) and id_variables[index]:
# id = ds.variables[id_variables[index]][dim_index]
#
# if not isinstance(id, basestring):
# if isinstance(id, Iterable):
# id = '_'.join((str(i) for i in id))
# else:
# id = str(id)
#
# id_parts.append(id)
#
# else:
# id_parts.append(str(dim_index))
#
# combined_id = '_'.join(id_parts)
# image_filename = os.path.join(output_directory, '{0}__{1}.{2}'.format(filename_root, combined_id, format))
# if reproject_kwargs:
# data = warp_array(data, **reproject_kwargs) # NOTE: lack of index will break this
# render_image(renderer, data[combined_index], image_filename, scale, flip_y=flip_y, format=format)
#
# local_filename = os.path.split(image_filename)[1]
# layers[os.path.splitext(local_filename)[0]] = local_filename
if interactive_map:
index_html = os.path.join(output_directory, 'index.html')
with open(index_html, 'w') as out:
template = Environment(
loader=PackageLoader('clover.cli')).get_template('map.html')
out.write(
template.render(layers=json.dumps(layers),
bounds=str(leaflet_anchors),
variable=variable))
webbrowser.open(index_html)
def mask(
input,
output,
variable,
like,
netcdf3,
all_touched,
invert,
zip):
"""
Create a NetCDF mask from a shapefile.
Values are equivalent to a numpy mask: 0 for unmasked areas, and 1 for masked areas.
Template NetCDF dataset must have a valid projection defined or be inferred from dimensions (e.g., lat / long)
"""
with Dataset(like) as template_ds:
template_varname = data_variables(template_ds).keys()[0]
template_variable = template_ds.variables[template_varname]
template_crs = get_crs(template_ds, template_varname)
if template_crs:
template_crs = CRS.from_string(template_crs)
elif is_geographic(template_ds, template_varname):
template_crs = CRS({'init': 'EPSG:4326'})
else:
raise click.UsageError('template dataset must have a valid projection defined')
spatial_dimensions = template_variable.dimensions[-2:]
mask_shape = template_variable.shape[-2:]
template_y_name, template_x_name = spatial_dimensions
coords = SpatialCoordinateVariables.from_dataset(
template_ds,
x_name=template_x_name,
y_name=template_y_name,
projection=Proj(**template_crs.to_dict())
)
with fiona.open(input, 'r') as shp:
transform_required = CRS(shp.crs) != template_crs
# Project bbox for filtering
bbox = coords.bbox
if transform_required:
bbox = bbox.project(Proj(**shp.crs), edge_points=21)
geometries = []
for f in shp.filter(bbox=bbox.as_list()):
geom = f['geometry']
if transform_required:
geom = transform_geom(shp.crs, template_crs, geom)
geometries.append(geom)
click.echo('Converting {0} features to mask'.format(len(geometries)))
if invert:
fill_value = 0
default_value = 1
else:
fill_value = 1
default_value = 0
with rasterio.drivers():
# Rasterize features to 0, leaving background as 1
mask = rasterize(
geometries,
out_shape=mask_shape,
transform=coords.affine,
all_touched=all_touched,
fill=fill_value,
default_value=default_value,
dtype=numpy.uint8
)
format = 'NETCDF3_CLASSIC' if netcdf3 else 'NETCDF4'
dtype = 'int8' if netcdf3 else 'uint8'
with Dataset(output, 'w', format=format) as out:
coords.add_to_dataset(out, template_x_name, template_y_name)
out_var = out.createVariable(variable, dtype, dimensions=spatial_dimensions, zlib=zip,
fill_value=get_fill_value(dtype))
out_var[:] = mask