def crs_to_proj_dict(crs: CRS) -> dict:
warnings.filterwarnings("ignore", module="pyproj", category=UserWarning)
if crs.to_epsg() is not None:
proj_dict = {"EPSG": crs.to_epsg()}
else:
proj_dict = crs.to_dict()
_remove_unnecessary_proj_params(proj_dict)
return proj_dict
def df_coord_transfor(gdf):
# 坐标转换算法
# <location netOffset="-799385.77,-2493897.75" convBoundary="0.00,0.00,18009.61,5593.04" origBoundary="113.832744,22.506539,114.086290,22.692155" projParameter="+proj=utm +zone=49 +ellps=WGS84 +datum=WGS84 +units=m +no_defs"/>
crs = CRS("+proj=utm +zone=49 +ellps=WGS84 +datum=WGS84 +units=m +no_defs")
to_crs = crs.to_epsg()
gdf.to_crs(epsg=to_crs, inplace=True)
gdf.loc[:, "x_"] = gdf.geometry.x - 799385.77
gdf.loc[:, "y_"] = gdf.geometry.y - 2493897.75
return gdf
def records_intersecting(
self,
geometry: BaseGeometry,
crs: CRS = None,
geometry_fields: List[str] = None) -> List[Dict[str, Any]]:
if crs is None:
crs = self.crs
if crs.to_epsg() is None:
raise NotImplementedError(f'no EPSG code found for CRS "{crs}"')
if geometry_fields is None or len(geometry_fields) == 0:
geometry_fields = list(self.geometry_fields)
where_clause = []
where_values = []
for field in geometry_fields:
where_values.extend([geometry.wkt, crs.to_epsg()])
geometry_string = f'ST_GeomFromText(%s, %s)'
if crs != self.crs:
geometry_string = f'ST_Transform({geometry_string}, %s)'
where_values.append(self.crs.to_epsg())
where_clause.append(f'ST_Intersects({field}, {geometry_string})')
where_clause = ' OR '.join(where_clause)
with self.connection as connection:
with connection.cursor() as cursor:
cursor.execute(
f'SELECT * FROM {self.name} WHERE {where_clause};',
where_values)
records = cursor.fetchall()
connection.close()
return [
parse_record_values(dict(zip(self.fields.keys(), record)),
self.fields) for record in records
]
class Projection():
def __init__(self,
name,
output_crs_name=None,
manual_first_axis_direction=None):
self.name = name
try:
self.crs = CRS(name)
except pyproj.exceptions.CRSError:
if name == "CRS:84":
self.crs = CRS("EPSG:4326")
self.manual_first_axis_direction = manual_first_axis_direction
self.from_wgs84_transformer = Transformer.from_crs(
"EPSG:4326", self.crs)
if output_crs_name:
self.output_crs = CRS(output_crs_name)
self.output_transform = Transformer.from_crs(
self.crs, self.output_crs, always_xy=True).transform
else:
self.output_crs = None
self.output_transform = None
def is_projected(self):
return self.crs.is_projected
def get_coordinate_unit(self):
return self.crs.axis_info[0].unit_name
def get_epsg(self):
return self.crs.to_epsg()
def convert_from_wgs84(self, lon, lat):
return self.from_wgs84_transformer.transform(lat, lon)
def is_first_axis_east(self):
dir = self.manual_first_axis_direction if self.manual_first_axis_direction else self.crs.axis_info[
0].direction.lower()
return dir.lower() == 'east'
def georef_by_worker(sv_corr: list,
alt: xr.DataArray,
lon: xr.DataArray,
lat: xr.DataArray,
hdng: xr.DataArray,
heave: xr.DataArray,
wline: float,
vert_ref: str,
input_crs: CRS,
horizontal_crs: CRS,
z_offset: float,
vdatum_directory: str = None):
"""
Use the raw attitude/navigation to transform the vessel relative along/across/down offsets to georeferenced
soundings. Will support transformation to geographic and projected coordinate systems and with a vertical
reference that you select.
Parameters
----------
sv_corr
[x, y, z] offsets generated with sv_correct
alt
1d (time) altitude in meters
lon
1d (time) longitude in degrees
lat
1d (time) latitude in degrees
hdng
1d (time) heading in degrees
heave
1d (time) heave in degrees
wline
waterline offset from reference point
vert_ref
vertical reference point, one of ['ellipse', 'vessel', 'waterline']
input_crs
pyproj CRS object, input coordinate reference system information for this run
horizontal_crs
pyproj CRS object, destination coordinate reference system information for this run
z_offset
lever arm from reference point to transmitter
vdatum_directory
if 'NOAA MLLW' 'NOAA MHW' is the vertical reference, a path to the vdatum directory is required here
Returns
-------
list
[xr.DataArray alongtrack offset (time, beam), xr.DataArray acrosstrack offset (time, beam),
xr.DataArray down offset (time, beam), xr.DataArray corrected heave for TX - RP lever arm, all zeros if in 'ellipse' mode (time),
xr.DataArray corrected altitude for TX - RP lever arm, all zeros if in 'vessel' or 'waterline' mode (time)]
"""
g = horizontal_crs.get_geod()
# unpack the sv corrected data output
alongtrack = sv_corr[0]
acrosstrack = sv_corr[1]
depthoffset = sv_corr[2] + z_offset
# generate the corrected depth offset depending on the desired vertical reference
corr_dpth = None
corr_heave = None
corr_altitude = None
if vert_ref in kluster_variables.ellipse_based_vertical_references:
corr_altitude = alt
corr_heave = xr.zeros_like(corr_altitude)
corr_dpth = (depthoffset - corr_altitude.values[:, None]).astype(
np.float32)
elif vert_ref == 'vessel':
corr_heave = heave
corr_altitude = xr.zeros_like(corr_heave)
corr_dpth = (depthoffset + corr_heave.values[:, None]).astype(
np.float32)
elif vert_ref == 'waterline':
corr_heave = heave
corr_altitude = xr.zeros_like(corr_heave)
corr_dpth = (depthoffset + corr_heave.values[:, None] - wline).astype(
np.float32)
# get the sv corrected alongtrack/acrosstrack offsets stacked without the NaNs (arrays have NaNs for beams that do not exist in that sector)
at_idx, alongtrack_stck = stack_nan_array(alongtrack,
stack_dims=('time', 'beam'))
ac_idx, acrosstrack_stck = stack_nan_array(acrosstrack,
stack_dims=('time', 'beam'))
# determine the beam wise offsets
bm_azimuth = np.rad2deg(np.arctan2(acrosstrack_stck,
alongtrack_stck)) + np.float32(
hdng[at_idx[0]].values)
bm_radius = np.sqrt(acrosstrack_stck**2 + alongtrack_stck**2)
pos = g.fwd(lon[at_idx[0]].values, lat[at_idx[0]].values,
bm_azimuth.values, bm_radius.values)
z = np.around(corr_dpth, 3)
if vert_ref == 'NOAA MLLW':
sep, vdatum_unc = transform_vyperdatum(
pos[0],
pos[1],
xr.zeros_like(z),
input_crs.to_epsg(),
'mllw',
vdatum_directory=vdatum_directory)
elif vert_ref == 'NOAA MHW':
sep, vdatum_unc = transform_vyperdatum(
pos[0],
pos[1],
xr.zeros_like(z),
input_crs.to_epsg(),
'mhw',
vdatum_directory=vdatum_directory)
else:
sep = 0
vdatum_unc = xr.zeros_like(z)
z = z - sep
if horizontal_crs.is_projected:
# Transformer.transform input order is based on the CRS, see CRS.geodetic_crs.axis_info
# - lon, lat - this appears to be valid when using CRS from proj4 string
# - lat, lon - this appears to be valid when using CRS from epsg
# use the always_xy option to force the transform to expect lon/lat order
georef_transformer = Transformer.from_crs(input_crs,
horizontal_crs,
always_xy=True)
newpos = georef_transformer.transform(
pos[0], pos[1], errcheck=True) # longitude / latitude order (x/y)
else:
newpos = pos
x = reform_nan_array(np.around(newpos[0], 3), at_idx, alongtrack.shape,
alongtrack.coords, alongtrack.dims)
y = reform_nan_array(np.around(newpos[1], 3), ac_idx, acrosstrack.shape,
acrosstrack.coords, acrosstrack.dims)
return [x, y, z, corr_heave, corr_altitude, vdatum_unc]
def CRS_to_uri(crs: CRS) -> str:
"""Convert CRS to URI."""
epsg_code = crs.to_epsg()
return f"http://www.opengis.net/def/crs/EPSG/0/{epsg_code}"
def records_intersecting(
self,
geometry: BaseGeometry,
crs: CRS = None,
geometry_fields: List[str] = None) -> List[Dict[str, Any]]:
if crs is None:
crs = self.crs
if crs.to_epsg() is None:
raise NotImplementedError(f'no EPSG code found for CRS "{crs}"')
if geometry_fields is None or len(geometry_fields) == 0:
geometry_fields = list(self.geometry_fields)
where_clause = []
where_values = []
for field in geometry_fields:
where_values.extend([geometry.wkt, crs.to_epsg()])
geometry_string = f'GeomFromText(?, ?)'
if crs != self.crs:
geometry_string = f'Transform({geometry_string}, ?)'
where_values.append(self.crs.to_epsg())
where_clause.append(f'Intersects({field}, {geometry_string})')
where_clause = ' OR '.join(where_clause)
non_geometry_fields = {
field: field_type
for field, field_type in self.fields.items()
if field_type.__name__ not in GEOMETRY_TYPES
}
with self.connection:
cursor = self.connection.cursor()
cursor.execute(
f'SELECT {", ".join(non_geometry_fields)} '
f'FROM {self.name} WHERE {where_clause};',
where_values,
)
non_geometry_records = cursor.fetchall()
non_geometry_records = [
parse_record_values(
dict(zip(non_geometry_fields.keys(), record)),
non_geometry_fields) for record in non_geometry_records
]
geometry_field_string = ', '.join(
f'asbinary({geometry_field})'
for geometry_field in self.geometry_fields)
cursor.execute(
f'SELECT {geometry_field_string} '
f'FROM {self.name} WHERE {where_clause};',
where_values,
)
geometry_records = cursor.fetchall()
geometry_records = [
parse_record_values(
dict(zip(self.geometry_fields.keys(), record)),
self.geometry_fields) for record in geometry_records
]
records = [{
**non_geometry_records[index],
**geometry_records[index]
} for index in range(len(non_geometry_records))]
return [{field: record[field]
for field in self.fields} for record in records]
def get(
datasets: dict = GISCO_DATASETS,
crs: CRS = CRS.from_epsg(3035)
) -> gpd.GeoDataFrame:
"""
Retrieve NUTS, LAU and countries from GISCO API and make a single, consistent GDF.
Parameters
----------
datasets : dict
dict with API URLs.
crs : str, optional
Spatial Reference System. The default is "EPSG:4326".
Returns
-------
admin_units : GeoDataFrame
Table with all administrative units.
"""
source_crs_code = crs.to_epsg()
logging.info("Downloading countries...")
countries = gpd.read_file(datasets["countries"].format(source_crs_code),
crs=crs.to_string())
logging.info("Downloading NUTS...")
nuts = gpd.read_file(datasets["nuts"].format(source_crs_code),
crs=crs.to_string())
logging.info("Downloading LAU...")
lau = gpd.read_file(datasets["lau"].format(source_crs_code),
crs=crs.to_string())
logging.info("Done.")
# Convert to lower case
countries.columns = countries.columns.str.lower()
nuts.columns = nuts.columns.str.lower()
lau.columns = lau.columns.str.lower()
# Create consistent columns across ds
lau = lau.rename({"lau_name": "name"}, axis=1)
lau["levl_code"] = 4
nuts = nuts.rename({"name_latn": "name"}, axis=1)
countries = countries.rename({"cntr_name": "name"}, axis=1)
countries = countries.rename({"cntr_id": "cntr_code"}, axis=1)
countries["levl_code"] = 0
# EU+ countries are included both in NUTS (level 0) and in "countries"
# Discard then NUTS level 0
nuts_noEU = nuts.loc[~nuts.id.isin(countries.id), :]
admin_units = pd.concat([countries, nuts_noEU, lau],
axis=0,
ignore_index=True)
admin_units = gpd.GeoDataFrame(
admin_units.
loc[:,
["fid", "name", "name_engl", "cntr_code", "levl_code", "geometry"]]
)
# New level codes
admin_units.levl_code = admin_units.levl_code.replace({
0: "country",
1: "NUTS1",
2: "NUTS2",
3: "NUTS3",
4: "LAU"
})
# Convert to ISO 3166-1 alpha-2
transl = {"UK": "GB", "EL": "GR"}
admin_units["fid"] = admin_units["fid"].replace(transl)
admin_units["cntr_code"] = admin_units["cntr_code"].replace(transl)
admin_units.crs = crs.to_string()
return admin_units
def prepareRaster(
df: pd.DataFrame,
crs: CRS = CRS.from_epsg(3035),
variable: str = "",
delete_orig: bool = False,
):
"""
Convert original raster or NetCDF into EnerMaps rasters (single band, GeoTiff, EPSG:3035).
Parameters
----------
df : DataFrame.
Results of API extraction.
crs : pyproj.crs.CRS.
coordinate reference system.
variable : str, optional.
Variable of NETCDF.
delete_orig : bool, optional.
Set to True to delete original downloaded file (e.g. NetCDF).
Returns
-------
df : DataFrame
Results with schema for EnerMaps data table
"""
dicts = []
for i, row in df.iterrows():
filename = row["value"]
if filename.startswith("http"):
filename = "/vsicurl/" + filename
if filename[-2:] == "nc":
src_ds = gdal.Open("NETCDF:{0}:{1}".format(filename, variable))
else:
src_ds = gdal.Open(filename)
# Override function parameter
if "variable" in row.index:
variable = row["variable"]
if "crs" in df.columns:
source_wkt = osr.SpatialReference()
source_wkt.ImportFromEPSG(row.crs.to_epsg())
source_wkt = source_wkt.ExportToPrettyWkt()
source_crs = CRS.from_wkt(source_wkt)
else:
prj = src_ds.GetProjection()
srs = osr.SpatialReference(wkt=prj)
source_crs = CRS.from_epsg(srs.GetAttrValue("authority", 1))
dest_wkt = osr.SpatialReference()
dest_wkt.ImportFromEPSG(crs.to_epsg())
dest_wkt = dest_wkt.ExportToPrettyWkt()
for b in range(src_ds.RasterCount):
my_dict = {}
b += 1
dest_filename = Path(filename).stem
dest_filename += "_band" + str(b)
# Translating to make sure that the raster settings are consistent for each band
logging.info("Translating band {}".format(b))
os.system(
"gdal_translate {filename} {dest_filename}.tif -b {b} -of GTIFF --config GDAL_PAM_ENABLED NO -co COMPRESS=DEFLATE -co BIGTIFF=YES".format(
filename=filename, dest_filename=dest_filename, b=b
)
)
# Reprojecting if needed
if source_crs.to_epsg() != crs.to_epsg():
logging.info(
"Warping from {} to {}".format(source_crs.to_epsg(), crs.to_epsg())
)
intermediate_filename = dest_filename + ".tif" # from previous step
dest_filename += "_{}".format(crs.to_epsg())
os.system(
"gdalwarp {intermediate_filename} {dest_filename}.tif -of GTIFF -s_srs {sourceSRS} -t_srs {outputSRS} --config GDAL_PAM_ENABLED NO -co COMPRESS=DEFLATE -co BIGTIFF=YES".format(
intermediate_filename=intermediate_filename,
dest_filename=dest_filename,
outputSRS=crs.to_string(),
sourceSRS=source_crs.to_string(),
)
)
os.remove(intermediate_filename)
dest_filename += ".tif"
logging.info(dest_filename)
my_dict["start_at"] = row["start_at"] + pd.Timedelta(hours=row["dt"]) * (
b - 1
)
my_dict["z"] = row["z"]
my_dict["dt"] = row["dt"]
my_dict["unit"] = row["unit"]
my_dict["variable"] = variable
my_dict["fid"] = dest_filename
my_dict["israster"] = True
dicts.append(my_dict)
data = pd.DataFrame(
dicts,
columns=[
"start_at",
"fields",
"variable",
"value",
"ds_id",
"fid",
"dt",
"z",
"unit",
"israster",
],
)
if delete_orig:
os.remove(filename)
return data