def snap_to_flowlines(df, to_snap):
"""Snap to nearest flowline, within tolerance
Updates df with snapping results, and returns to_snap as set of dams still
needing to be snapped after this operation.
Parameters
----------
df : GeoDataFrame
master dataset, this is where all snapping gets recorded
to_snap : DataFrame
data frame containing pygeos geometries to snap ("geometry")
and snapping tolerance ("snap_tolerance")
Returns
-------
tuple of (GeoDataFrame, DataFrame)
(df, to_snap)
"""
for region, HUC2s in list(REGION_GROUPS.items()):
region_start = time()
print("\n----- {} ------\n".format(region))
print("Reading flowlines...")
flowlines = from_geofeather(
nhd_dir / "clean" / region / "flowlines.feather"
).set_index("lineID")
in_region = to_snap.loc[to_snap.HUC2.isin(HUC2s)]
print(
"Selected {:,} barriers in region to snap against {:,} flowlines".format(
len(in_region), len(flowlines)
)
)
if len(in_region) == 0:
print("No barriers in region to snap")
continue
print("Finding nearest flowlines...")
# TODO: can use near instead of nearest, and persist list of near lineIDs per barrier
# so that we can construct subnetworks with just those
lines = nearest(
in_region.geometry, flowlines.geometry, in_region.snap_tolerance
)
lines = lines.join(in_region.geometry).join(
flowlines.geometry.rename("line"), on="lineID",
)
# project the point to the line,
# find out its distance on the line,
# then interpolate its new coordinates
lines["geometry"] = pg.line_interpolate_point(
lines.line, pg.line_locate_point(lines.line, lines.geometry)
)
ix = lines.index
df.loc[ix, "snapped"] = True
df.loc[ix, "geometry"] = lines.geometry
df.loc[ix, "snap_dist"] = lines.distance
df.loc[ix, "snap_ref_id"] = lines.lineID
df.loc[ix, "lineID"] = lines.lineID
df.loc[ix, "snap_log"] = ndarray_append_strings(
"snapped: within ",
to_snap.loc[ix].snap_tolerance,
"m tolerance of flowline",
)
to_snap = to_snap.loc[~to_snap.index.isin(ix)].copy()
print(
"{:,} barriers snapped in region in {:.2f}s".format(
len(ix), time() - region_start
)
)
# TODO: flag those that joined to loops
return df, to_snap
from analysis.constants import (
REGIONS,
REGION_GROUPS,
CRS,
WATERBODY_EXCLUDE_FTYPES,
WATERBODY_MIN_SIZE,
)
from analysis.util import append
src_dir = Path("data/nhd/source/huc4")
out_dir = Path("data/nhd/raw")
start = time()
# useful slices are [:2], [2:4], [4:]
for region, HUC2s in list(REGION_GROUPS.items())[4:]:
print("\n----- {} ------\n".format(region))
region_dir = out_dir / region
if not os.path.exists(region_dir):
os.makedirs(region_dir)
# if os.path.exists(region_dir / "flowline.feather"):
# print("Skipping existing region {}".format(region))
# continue
region_start = time()
merged_flowlines = None
merged_joins = None
merged_waterbodies = None
# Dam, Gate, Lock Chamber, Waterfall
KEEP_FTYPES = [343, 369, 398, 487]
src_dir = Path("data/nhd/source/huc4")
nhd_dir = Path("data/nhd")
out_dir = nhd_dir / "extra"
if not os.path.exists(out_dir):
os.makedirs(out_dir)
start = time()
merged = None
for region, HUC2s in REGION_GROUPS.items():
print("\n----- {} ------\n".format(region))
for HUC2 in HUC2s:
for i in REGIONS[HUC2]:
HUC4 = "{0}{1:02d}".format(HUC2, i)
read_start = time()
print("\n\n------------------- Reading {} -------------------".
format(HUC4))
gdb = src_dir / HUC4 / "NHDPLUS_H_{HUC4}_HU4_GDB.gdb".format(
HUC4=HUC4)
df = gp.read_file(gdb, layer="NHDLine")
df.NHDPlusID = df.NHDPlusID.astype("uint64")