Hexgrid Generation
diff --git a/environment.yml b/environment.yml
index 7d4c6e2f..9930b2f0 100644
--- a/environment.yml
+++ b/environment.yml
@@ -4,7 +4,6 @@ channels:
dependencies:
- dask-geopandas
- dask
- - distributed
- jupyterlab
- numpy
- geopandas >=0.13
diff --git a/pyproject.toml b/pyproject.toml
index 51640112..2b06c192 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -64,6 +64,7 @@ tests = [
"pytest",
"pytest-mpl",
"pytest-cov",
+ "pytest-xdist",
"watermark",
"h3",
"astropy"
diff --git a/tobler/_version.py b/tobler/_version.py
deleted file mode 100644
index 5b34becb..00000000
--- a/tobler/_version.py
+++ /dev/null
@@ -1,623 +0,0 @@
-
-# This file helps to compute a version number in source trees obtained from
-# git-archive tarball (such as those provided by githubs download-from-tag
-# feature). Distribution tarballs (built by setup.py sdist) and build
-# directories (produced by setup.py build) will contain a much shorter file
-# that just contains the computed version number.
-
-# This file is released into the public domain. Generated by
-# versioneer-0.20 (https://github.com/python-versioneer/python-versioneer)
-
-"""Git implementation of _version.py."""
-
-import errno
-import os
-import re
-import subprocess
-import sys
-
-
-def get_keywords():
- """Get the keywords needed to look up the version information."""
- # these strings will be replaced by git during git-archive.
- # setup.py/versioneer.py will grep for the variable names, so they must
- # each be defined on a line of their own. _version.py will just call
- # get_keywords().
- git_refnames = "$Format:%d$"
- git_full = "$Format:%H$"
- git_date = "$Format:%ci$"
- keywords = {"refnames": git_refnames, "full": git_full, "date": git_date}
- return keywords
-
-
-class VersioneerConfig: # pylint: disable=too-few-public-methods
- """Container for Versioneer configuration parameters."""
-
-
-def get_config():
- """Create, populate and return the VersioneerConfig() object."""
- # these strings are filled in when 'setup.py versioneer' creates
- # _version.py
- cfg = VersioneerConfig()
- cfg.VCS = "git"
- cfg.style = "pep440"
- cfg.tag_prefix = "v"
- cfg.parentdir_prefix = "tobler-"
- cfg.versionfile_source = "tobler/_version.py"
- cfg.verbose = False
- return cfg
-
-
-class NotThisMethod(Exception):
- """Exception raised if a method is not valid for the current scenario."""
-
-
-LONG_VERSION_PY = {}
-HANDLERS = {}
-
-
-def register_vcs_handler(vcs, method): # decorator
- """Create decorator to mark a method as the handler of a VCS."""
- def decorate(f):
- """Store f in HANDLERS[vcs][method]."""
- if vcs not in HANDLERS:
- HANDLERS[vcs] = {}
- HANDLERS[vcs][method] = f
- return f
- return decorate
-
-
-# pylint:disable=too-many-arguments,consider-using-with # noqa
-def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False,
- env=None):
- """Call the given command(s)."""
- assert isinstance(commands, list)
- process = None
- for command in commands:
- try:
- dispcmd = str([command] + args)
- # remember shell=False, so use git.cmd on windows, not just git
- process = subprocess.Popen([command] + args, cwd=cwd, env=env,
- stdout=subprocess.PIPE,
- stderr=(subprocess.PIPE if hide_stderr
- else None))
- break
- except EnvironmentError:
- e = sys.exc_info()[1]
- if e.errno == errno.ENOENT:
- continue
- if verbose:
- print("unable to run %s" % dispcmd)
- print(e)
- return None, None
- else:
- if verbose:
- print("unable to find command, tried %s" % (commands,))
- return None, None
- stdout = process.communicate()[0].strip().decode()
- if process.returncode != 0:
- if verbose:
- print("unable to run %s (error)" % dispcmd)
- print("stdout was %s" % stdout)
- return None, process.returncode
- return stdout, process.returncode
-
-
-def versions_from_parentdir(parentdir_prefix, root, verbose):
- """Try to determine the version from the parent directory name.
-
- Source tarballs conventionally unpack into a directory that includes both
- the project name and a version string. We will also support searching up
- two directory levels for an appropriately named parent directory
- """
- rootdirs = []
-
- for _ in range(3):
- dirname = os.path.basename(root)
- if dirname.startswith(parentdir_prefix):
- return {"version": dirname[len(parentdir_prefix):],
- "full-revisionid": None,
- "dirty": False, "error": None, "date": None}
- rootdirs.append(root)
- root = os.path.dirname(root) # up a level
-
- if verbose:
- print("Tried directories %s but none started with prefix %s" %
- (str(rootdirs), parentdir_prefix))
- raise NotThisMethod("rootdir doesn't start with parentdir_prefix")
-
-
-@register_vcs_handler("git", "get_keywords")
-def git_get_keywords(versionfile_abs):
- """Extract version information from the given file."""
- # the code embedded in _version.py can just fetch the value of these
- # keywords. When used from setup.py, we don't want to import _version.py,
- # so we do it with a regexp instead. This function is not used from
- # _version.py.
- keywords = {}
- try:
- with open(versionfile_abs, "r") as fobj:
- for line in fobj:
- if line.strip().startswith("git_refnames ="):
- mo = re.search(r'=\s*"(.*)"', line)
- if mo:
- keywords["refnames"] = mo.group(1)
- if line.strip().startswith("git_full ="):
- mo = re.search(r'=\s*"(.*)"', line)
- if mo:
- keywords["full"] = mo.group(1)
- if line.strip().startswith("git_date ="):
- mo = re.search(r'=\s*"(.*)"', line)
- if mo:
- keywords["date"] = mo.group(1)
- except EnvironmentError:
- pass
- return keywords
-
-
-@register_vcs_handler("git", "keywords")
-def git_versions_from_keywords(keywords, tag_prefix, verbose):
- """Get version information from git keywords."""
- if "refnames" not in keywords:
- raise NotThisMethod("Short version file found")
- date = keywords.get("date")
- if date is not None:
- # Use only the last line. Previous lines may contain GPG signature
- # information.
- date = date.splitlines()[-1]
-
- # git-2.2.0 added "%cI", which expands to an ISO-8601 -compliant
- # datestamp. However we prefer "%ci" (which expands to an "ISO-8601
- # -like" string, which we must then edit to make compliant), because
- # it's been around since git-1.5.3, and it's too difficult to
- # discover which version we're using, or to work around using an
- # older one.
- date = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
- refnames = keywords["refnames"].strip()
- if refnames.startswith("$Format"):
- if verbose:
- print("keywords are unexpanded, not using")
- raise NotThisMethod("unexpanded keywords, not a git-archive tarball")
- refs = {r.strip() for r in refnames.strip("()").split(",")}
- # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of
- # just "foo-1.0". If we see a "tag: " prefix, prefer those.
- TAG = "tag: "
- tags = {r[len(TAG):] for r in refs if r.startswith(TAG)}
- if not tags:
- # Either we're using git < 1.8.3, or there really are no tags. We use
- # a heuristic: assume all version tags have a digit. The old git %d
- # expansion behaves like git log --decorate=short and strips out the
- # refs/heads/ and refs/tags/ prefixes that would let us distinguish
- # between branches and tags. By ignoring refnames without digits, we
- # filter out many common branch names like "release" and
- # "stabilization", as well as "HEAD" and "master".
- tags = {r for r in refs if re.search(r'\d', r)}
- if verbose:
- print("discarding '%s', no digits" % ",".join(refs - tags))
- if verbose:
- print("likely tags: %s" % ",".join(sorted(tags)))
- for ref in sorted(tags):
- # sorting will prefer e.g. "2.0" over "2.0rc1"
- if ref.startswith(tag_prefix):
- r = ref[len(tag_prefix):]
- # Filter out refs that exactly match prefix or that don't start
- # with a number once the prefix is stripped (mostly a concern
- # when prefix is '')
- if not re.match(r'\d', r):
- continue
- if verbose:
- print("picking %s" % r)
- return {"version": r,
- "full-revisionid": keywords["full"].strip(),
- "dirty": False, "error": None,
- "date": date}
- # no suitable tags, so version is "0+unknown", but full hex is still there
- if verbose:
- print("no suitable tags, using unknown + full revision id")
- return {"version": "0+unknown",
- "full-revisionid": keywords["full"].strip(),
- "dirty": False, "error": "no suitable tags", "date": None}
-
-
-@register_vcs_handler("git", "pieces_from_vcs")
-def git_pieces_from_vcs(tag_prefix, root, verbose, runner=run_command):
- """Get version from 'git describe' in the root of the source tree.
-
- This only gets called if the git-archive 'subst' keywords were *not*
- expanded, and _version.py hasn't already been rewritten with a short
- version string, meaning we're inside a checked out source tree.
- """
- GITS = ["git"]
- if sys.platform == "win32":
- GITS = ["git.cmd", "git.exe"]
-
- _, rc = runner(GITS, ["rev-parse", "--git-dir"], cwd=root,
- hide_stderr=True)
- if rc != 0:
- if verbose:
- print("Directory %s not under git control" % root)
- raise NotThisMethod("'git rev-parse --git-dir' returned error")
-
- # if there is a tag matching tag_prefix, this yields TAG-NUM-gHEX[-dirty]
- # if there isn't one, this yields HEX[-dirty] (no NUM)
- describe_out, rc = runner(GITS, ["describe", "--tags", "--dirty",
- "--always", "--long",
- "--match", "%s*" % tag_prefix],
- cwd=root)
- # --long was added in git-1.5.5
- if describe_out is None:
- raise NotThisMethod("'git describe' failed")
- describe_out = describe_out.strip()
- full_out, rc = runner(GITS, ["rev-parse", "HEAD"], cwd=root)
- if full_out is None:
- raise NotThisMethod("'git rev-parse' failed")
- full_out = full_out.strip()
-
- pieces = {}
- pieces["long"] = full_out
- pieces["short"] = full_out[:7] # maybe improved later
- pieces["error"] = None
-
- branch_name, rc = runner(GITS, ["rev-parse", "--abbrev-ref", "HEAD"],
- cwd=root)
- # --abbrev-ref was added in git-1.6.3
- if rc != 0 or branch_name is None:
- raise NotThisMethod("'git rev-parse --abbrev-ref' returned error")
- branch_name = branch_name.strip()
-
- if branch_name == "HEAD":
- # If we aren't exactly on a branch, pick a branch which represents
- # the current commit. If all else fails, we are on a branchless
- # commit.
- branches, rc = runner(GITS, ["branch", "--contains"], cwd=root)
- # --contains was added in git-1.5.4
- if rc != 0 or branches is None:
- raise NotThisMethod("'git branch --contains' returned error")
- branches = branches.split("\n")
-
- # Remove the first line if we're running detached
- if "(" in branches[0]:
- branches.pop(0)
-
- # Strip off the leading "* " from the list of branches.
- branches = [branch[2:] for branch in branches]
- if "master" in branches:
- branch_name = "master"
- elif not branches:
- branch_name = None
- else:
- # Pick the first branch that is returned. Good or bad.
- branch_name = branches[0]
-
- pieces["branch"] = branch_name
-
- # parse describe_out. It will be like TAG-NUM-gHEX[-dirty] or HEX[-dirty]
- # TAG might have hyphens.
- git_describe = describe_out
-
- # look for -dirty suffix
- dirty = git_describe.endswith("-dirty")
- pieces["dirty"] = dirty
- if dirty:
- git_describe = git_describe[:git_describe.rindex("-dirty")]
-
- # now we have TAG-NUM-gHEX or HEX
-
- if "-" in git_describe:
- # TAG-NUM-gHEX
- mo = re.search(r'^(.+)-(\d+)-g([0-9a-f]+)$', git_describe)
- if not mo:
- # unparseable. Maybe git-describe is misbehaving?
- pieces["error"] = ("unable to parse git-describe output: '%s'"
- % describe_out)
- return pieces
-
- # tag
- full_tag = mo.group(1)
- if not full_tag.startswith(tag_prefix):
- if verbose:
- fmt = "tag '%s' doesn't start with prefix '%s'"
- print(fmt % (full_tag, tag_prefix))
- pieces["error"] = ("tag '%s' doesn't start with prefix '%s'"
- % (full_tag, tag_prefix))
- return pieces
- pieces["closest-tag"] = full_tag[len(tag_prefix):]
-
- # distance: number of commits since tag
- pieces["distance"] = int(mo.group(2))
-
- # commit: short hex revision ID
- pieces["short"] = mo.group(3)
-
- else:
- # HEX: no tags
- pieces["closest-tag"] = None
- count_out, rc = runner(GITS, ["rev-list", "HEAD", "--count"], cwd=root)
- pieces["distance"] = int(count_out) # total number of commits
-
- # commit date: see ISO-8601 comment in git_versions_from_keywords()
- date = runner(GITS, ["show", "-s", "--format=%ci", "HEAD"], cwd=root)[0].strip()
- # Use only the last line. Previous lines may contain GPG signature
- # information.
- date = date.splitlines()[-1]
- pieces["date"] = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
-
- return pieces
-
-
-def plus_or_dot(pieces):
- """Return a + if we don't already have one, else return a ."""
- if "+" in pieces.get("closest-tag", ""):
- return "."
- return "+"
-
-
-def render_pep440(pieces):
- """Build up version string, with post-release "local version identifier".
-
- Our goal: TAG[+DISTANCE.gHEX[.dirty]] . Note that if you
- get a tagged build and then dirty it, you'll get TAG+0.gHEX.dirty
-
- Exceptions:
- 1: no tags. git_describe was just HEX. 0+untagged.DISTANCE.gHEX[.dirty]
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"] or pieces["dirty"]:
- rendered += plus_or_dot(pieces)
- rendered += "%d.g%s" % (pieces["distance"], pieces["short"])
- if pieces["dirty"]:
- rendered += ".dirty"
- else:
- # exception #1
- rendered = "0+untagged.%d.g%s" % (pieces["distance"],
- pieces["short"])
- if pieces["dirty"]:
- rendered += ".dirty"
- return rendered
-
-
-def render_pep440_branch(pieces):
- """TAG[[.dev0]+DISTANCE.gHEX[.dirty]] .
-
- The ".dev0" means not master branch. Note that .dev0 sorts backwards
- (a feature branch will appear "older" than the master branch).
-
- Exceptions:
- 1: no tags. 0[.dev0]+untagged.DISTANCE.gHEX[.dirty]
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"] or pieces["dirty"]:
- if pieces["branch"] != "master":
- rendered += ".dev0"
- rendered += plus_or_dot(pieces)
- rendered += "%d.g%s" % (pieces["distance"], pieces["short"])
- if pieces["dirty"]:
- rendered += ".dirty"
- else:
- # exception #1
- rendered = "0"
- if pieces["branch"] != "master":
- rendered += ".dev0"
- rendered += "+untagged.%d.g%s" % (pieces["distance"],
- pieces["short"])
- if pieces["dirty"]:
- rendered += ".dirty"
- return rendered
-
-
-def render_pep440_pre(pieces):
- """TAG[.post0.devDISTANCE] -- No -dirty.
-
- Exceptions:
- 1: no tags. 0.post0.devDISTANCE
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"]:
- rendered += ".post0.dev%d" % pieces["distance"]
- else:
- # exception #1
- rendered = "0.post0.dev%d" % pieces["distance"]
- return rendered
-
-
-def render_pep440_post(pieces):
- """TAG[.postDISTANCE[.dev0]+gHEX] .
-
- The ".dev0" means dirty. Note that .dev0 sorts backwards
- (a dirty tree will appear "older" than the corresponding clean one),
- but you shouldn't be releasing software with -dirty anyways.
-
- Exceptions:
- 1: no tags. 0.postDISTANCE[.dev0]
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"] or pieces["dirty"]:
- rendered += ".post%d" % pieces["distance"]
- if pieces["dirty"]:
- rendered += ".dev0"
- rendered += plus_or_dot(pieces)
- rendered += "g%s" % pieces["short"]
- else:
- # exception #1
- rendered = "0.post%d" % pieces["distance"]
- if pieces["dirty"]:
- rendered += ".dev0"
- rendered += "+g%s" % pieces["short"]
- return rendered
-
-
-def render_pep440_post_branch(pieces):
- """TAG[.postDISTANCE[.dev0]+gHEX[.dirty]] .
-
- The ".dev0" means not master branch.
-
- Exceptions:
- 1: no tags. 0.postDISTANCE[.dev0]+gHEX[.dirty]
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"] or pieces["dirty"]:
- rendered += ".post%d" % pieces["distance"]
- if pieces["branch"] != "master":
- rendered += ".dev0"
- rendered += plus_or_dot(pieces)
- rendered += "g%s" % pieces["short"]
- if pieces["dirty"]:
- rendered += ".dirty"
- else:
- # exception #1
- rendered = "0.post%d" % pieces["distance"]
- if pieces["branch"] != "master":
- rendered += ".dev0"
- rendered += "+g%s" % pieces["short"]
- if pieces["dirty"]:
- rendered += ".dirty"
- return rendered
-
-
-def render_pep440_old(pieces):
- """TAG[.postDISTANCE[.dev0]] .
-
- The ".dev0" means dirty.
-
- Exceptions:
- 1: no tags. 0.postDISTANCE[.dev0]
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"] or pieces["dirty"]:
- rendered += ".post%d" % pieces["distance"]
- if pieces["dirty"]:
- rendered += ".dev0"
- else:
- # exception #1
- rendered = "0.post%d" % pieces["distance"]
- if pieces["dirty"]:
- rendered += ".dev0"
- return rendered
-
-
-def render_git_describe(pieces):
- """TAG[-DISTANCE-gHEX][-dirty].
-
- Like 'git describe --tags --dirty --always'.
-
- Exceptions:
- 1: no tags. HEX[-dirty] (note: no 'g' prefix)
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"]:
- rendered += "-%d-g%s" % (pieces["distance"], pieces["short"])
- else:
- # exception #1
- rendered = pieces["short"]
- if pieces["dirty"]:
- rendered += "-dirty"
- return rendered
-
-
-def render_git_describe_long(pieces):
- """TAG-DISTANCE-gHEX[-dirty].
-
- Like 'git describe --tags --dirty --always -long'.
- The distance/hash is unconditional.
-
- Exceptions:
- 1: no tags. HEX[-dirty] (note: no 'g' prefix)
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- rendered += "-%d-g%s" % (pieces["distance"], pieces["short"])
- else:
- # exception #1
- rendered = pieces["short"]
- if pieces["dirty"]:
- rendered += "-dirty"
- return rendered
-
-
-def render(pieces, style):
- """Render the given version pieces into the requested style."""
- if pieces["error"]:
- return {"version": "unknown",
- "full-revisionid": pieces.get("long"),
- "dirty": None,
- "error": pieces["error"],
- "date": None}
-
- if not style or style == "default":
- style = "pep440" # the default
-
- if style == "pep440":
- rendered = render_pep440(pieces)
- elif style == "pep440-branch":
- rendered = render_pep440_branch(pieces)
- elif style == "pep440-pre":
- rendered = render_pep440_pre(pieces)
- elif style == "pep440-post":
- rendered = render_pep440_post(pieces)
- elif style == "pep440-post-branch":
- rendered = render_pep440_post_branch(pieces)
- elif style == "pep440-old":
- rendered = render_pep440_old(pieces)
- elif style == "git-describe":
- rendered = render_git_describe(pieces)
- elif style == "git-describe-long":
- rendered = render_git_describe_long(pieces)
- else:
- raise ValueError("unknown style '%s'" % style)
-
- return {"version": rendered, "full-revisionid": pieces["long"],
- "dirty": pieces["dirty"], "error": None,
- "date": pieces.get("date")}
-
-
-def get_versions():
- """Get version information or return default if unable to do so."""
- # I am in _version.py, which lives at ROOT/VERSIONFILE_SOURCE. If we have
- # __file__, we can work backwards from there to the root. Some
- # py2exe/bbfreeze/non-CPython implementations don't do __file__, in which
- # case we can only use expanded keywords.
-
- cfg = get_config()
- verbose = cfg.verbose
-
- try:
- return git_versions_from_keywords(get_keywords(), cfg.tag_prefix,
- verbose)
- except NotThisMethod:
- pass
-
- try:
- root = os.path.realpath(__file__)
- # versionfile_source is the relative path from the top of the source
- # tree (where the .git directory might live) to this file. Invert
- # this to find the root from __file__.
- for _ in cfg.versionfile_source.split('/'):
- root = os.path.dirname(root)
- except NameError:
- return {"version": "0+unknown", "full-revisionid": None,
- "dirty": None,
- "error": "unable to find root of source tree",
- "date": None}
-
- try:
- pieces = git_pieces_from_vcs(cfg.tag_prefix, root, verbose)
- return render(pieces, cfg.style)
- except NotThisMethod:
- pass
-
- try:
- if cfg.parentdir_prefix:
- return versions_from_parentdir(cfg.parentdir_prefix, root, verbose)
- except NotThisMethod:
- pass
-
- return {"version": "0+unknown", "full-revisionid": None,
- "dirty": None,
- "error": "unable to compute version", "date": None}
diff --git a/tobler/area_weighted/area_interpolate.py b/tobler/area_weighted/area_interpolate.py
index 07618f31..24dcffc5 100644
--- a/tobler/area_weighted/area_interpolate.py
+++ b/tobler/area_weighted/area_interpolate.py
@@ -260,7 +260,7 @@ def _area_interpolate_binning(
Returns
-------
estimates : geopandas.GeoDataFrame
- new geodaraframe with interpolated variables as columns and target_df geometry
+ new geodataframe with interpolated variables as columns and target_df geometry
as output geometry
Notes
diff --git a/tobler/area_weighted/area_interpolate_dask.py b/tobler/area_weighted/area_interpolate_dask.py
index faf5e02b..5e2164be 100755
--- a/tobler/area_weighted/area_interpolate_dask.py
+++ b/tobler/area_weighted/area_interpolate_dask.py
@@ -54,7 +54,7 @@ def area_interpolate_dask(
Returns
-------
estimates : dask_geopandas.GeoDataFrame
- new dask-geopandas geodaraframe with interpolated variables and `id_col` as
+ new dask-geopandas geodataframe with interpolated variables and `id_col` as
columns and target_df geometry as output geometry
"""
diff --git a/tobler/dasymetric/masked_area_interpolate.py b/tobler/dasymetric/masked_area_interpolate.py
index fe6c53bc..74f10ff4 100644
--- a/tobler/dasymetric/masked_area_interpolate.py
+++ b/tobler/dasymetric/masked_area_interpolate.py
@@ -1,8 +1,9 @@
+from warnings import warn
+
import geopandas as gpd
from ..area_weighted import area_interpolate
from .raster_tools import extract_raster_features
-from warnings import warn
def masked_area_interpolate(
diff --git a/tobler/dasymetric/raster_tools.py b/tobler/dasymetric/raster_tools.py
index b2ce5962..3038870c 100644
--- a/tobler/dasymetric/raster_tools.py
+++ b/tobler/dasymetric/raster_tools.py
@@ -2,18 +2,22 @@
import ast
import multiprocessing
+import warnings
import geopandas as gpd
import numpy as np
import pandas as pd
import rasterio as rio
+import rasterstats as rs
from joblib import Parallel, delayed
+from packaging.version import Version
from rasterio import features
-from shapely.geometry import shape
from rasterio.mask import mask
-import warnings
+from shapely.geometry import shape
+
from ..util.util import _check_presence_of_crs
-import rasterstats as rs
+
+GPD_10 = Version(gpd.__version__) >= Version("1.0.0dev")
def _chunk_dfs(geoms_to_chunk, n_jobs):
@@ -104,10 +108,12 @@ def extract_raster_features(
if n_jobs == -1:
n_jobs = multiprocessing.cpu_count()
with rio.open(raster_path) as src:
-
- raster_crs = src.crs.data
+ raster_crs = src.crs.to_dict()
gdf = gdf.to_crs(raster_crs)
- geomask = [gdf.unary_union.__geo_interface__]
+ if GPD_10:
+ geomask = [gdf.union_all().__geo_interface__]
+ else:
+ geomask = [gdf.unary_union.__geo_interface__]
out_image, out_transform = mask(
src, geomask, nodata=nodata, crop=True
diff --git a/tobler/pycno/pycno.py b/tobler/pycno/pycno.py
index 19ed692e..b39c0bcd 100644
--- a/tobler/pycno/pycno.py
+++ b/tobler/pycno/pycno.py
@@ -274,7 +274,7 @@ def pycno_interpolate(
Returns
-------
geopandas.GeoDataFrame
- new geodaraframe with interpolated variables as columns and target_df geometry
+ new geodataframe with interpolated variables as columns and target_df geometry
as output geometry
Notes
diff --git a/tobler/tests/test_area_interpolators.py b/tobler/tests/test_area_interpolators.py
index bc8791b9..11d05c64 100644
--- a/tobler/tests/test_area_interpolators.py
+++ b/tobler/tests/test_area_interpolators.py
@@ -1,4 +1,5 @@
"""test interpolation functions."""
+
import geopandas
import dask_geopandas
@@ -15,7 +16,9 @@ def datasets():
sac1 = load_example("Sacramento1")
sac2 = load_example("Sacramento2")
sac1 = geopandas.read_file(sac1.get_path("sacramentot2.shp"))
+ sac1 = sac1.to_crs(sac1.estimate_utm_crs())
sac2 = geopandas.read_file(sac2.get_path("SacramentoMSA2.shp"))
+ sac2 = sac2.to_crs(sac1.crs)
sac1["pct_poverty"] = sac1.POV_POP / sac1.POV_TOT
categories = ["cat", "dog", "donkey", "wombat", "capybara"]
sac1["animal"] = (categories * ((len(sac1) // len(categories)) + 1))[: len(sac1)]
@@ -45,8 +48,8 @@ def test_area_interpolate_singlecore():
def test_area_interpolate_extensive():
sac1, sac2 = datasets()
area = area_interpolate(
- source_df=sac1,
- target_df=sac2,
+ source_df=sac1.to_crs(4326), # trigger warning once
+ target_df=sac2.to_crs(4326),
extensive_variables=["TOT_POP"],
n_jobs=1,
)
@@ -81,21 +84,20 @@ def test_area_interpolate_categorical():
assert_almost_equal(area.animal_capybara.sum(), 20, decimal=0)
+@pytest.mark.xfail(reason="dask_geopandas is broken with dask-expr backend")
def test_area_interpolate_categorical_dask():
sac1, sac2 = datasets()
- sac1['animal'] = sac1['animal'].astype('category')
- dsac1 = (
- dask_geopandas.from_geopandas(sac1, npartitions=2)
- .spatial_shuffle(by='hilbert', shuffle='tasks')
+ sac1["animal"] = sac1["animal"].astype("category")
+ dsac1 = dask_geopandas.from_geopandas(sac1, npartitions=2).spatial_shuffle(
+ by="hilbert", shuffle="tasks"
)
- dsac2 = (
- dask_geopandas.from_geopandas(sac2, npartitions=2)
- .spatial_shuffle(by='hilbert', shuffle='tasks')
+ dsac2 = dask_geopandas.from_geopandas(sac2, npartitions=2).spatial_shuffle(
+ by="hilbert", shuffle="tasks"
)
area = area_interpolate_dask(
source_dgdf=dsac1,
target_dgdf=dsac2,
- id_col='ZIP',
+ id_col="ZIP",
categorical_variables=["animal"],
).compute()
assert_almost_equal(area.animal_cat.sum(), 32, decimal=0)
@@ -177,8 +179,12 @@ def test_area_interpolate_parallel():
def test_area_tables_binning():
sac1, sac2 = datasets()
+ sac1 = sac1.to_crs(4326)
+ sac2 = sac2.to_crs(4326)
- auto = _area_tables_binning(source_df=sac1, target_df=sac2, spatial_index="auto")
+ auto = _area_tables_binning(
+ source_df=sac1, target_df=sac2, spatial_index="auto"
+ )
source = _area_tables_binning(
source_df=sac1, target_df=sac2, spatial_index="source"
)
diff --git a/tobler/tests/test_dasymetric.py b/tobler/tests/test_dasymetric.py
index ea4122ce..0cacef70 100644
--- a/tobler/tests/test_dasymetric.py
+++ b/tobler/tests/test_dasymetric.py
@@ -1,45 +1,25 @@
"""test interpolation functions."""
-import sys
-import pandas as pd
import geopandas
-import pytest
-try:
- import quilt3
-
- QUILTMISSING = False
-except ImportError:
- QUILTMISSING = True
-
-import os
from libpysal.examples import load_example
from tobler.dasymetric import masked_area_interpolate
def datasets():
- if not QUILTMISSING:
-
- if not os.path.exists("nlcd_2011.tif"):
- p = quilt3.Package.browse("rasters/nlcd", "s3://spatial-ucr")
- p["nlcd_2011.tif"].fetch()
- sac1 = load_example("Sacramento1")
- sac2 = load_example("Sacramento2")
- sac1 = geopandas.read_file(sac1.get_path("sacramentot2.shp"))
- sac1 = sac1.to_crs(sac1.estimate_utm_crs())
- sac2 = geopandas.read_file(sac2.get_path("SacramentoMSA2.shp"))
- sac2 = sac2.to_crs(sac2.estimate_utm_crs())
- sac1["pct_poverty"] = sac1.POV_POP / sac1.POV_TOT
- categories = ["cat", "dog", "donkey", "wombat", "capybara"]
- sac1["animal"] = (categories * ((len(sac1) // len(categories)) + 1))[
- : len(sac1)
- ]
-
- return sac1, sac2
- else:
- pass
+ sac1 = load_example("Sacramento1")
+ sac2 = load_example("Sacramento2")
+ sac1 = geopandas.read_file(sac1.get_path("sacramentot2.shp"))
+ sac1 = sac1.to_crs(sac1.estimate_utm_crs())
+ sac2 = geopandas.read_file(sac2.get_path("SacramentoMSA2.shp"))
+ sac2 = sac2.to_crs(sac2.estimate_utm_crs())
+ sac1["pct_poverty"] = sac1.POV_POP / sac1.POV_TOT
+ categories = ["cat", "dog", "donkey", "wombat", "capybara"]
+ sac1["animal"] = (categories * ((len(sac1) // len(categories)) + 1))[
+ : len(sac1)
+ ]
+ return sac1, sac2
-@pytest.mark.skipif(QUILTMISSING, reason="quilt3 not available.")
def test_masked_area_interpolate():
sac1, sac2 = datasets()
masked = masked_area_interpolate(
@@ -47,7 +27,7 @@ def test_masked_area_interpolate():
target_df=sac2,
extensive_variables=["TOT_POP"],
intensive_variables=["pct_poverty"],
- raster="nlcd_2011.tif",
+ raster="https://spatial-ucr.s3.amazonaws.com/nlcd/landcover/nlcd_landcover_2011.tif",
pixel_values=[21, 22, 23, 24],
)
assert masked.TOT_POP.sum().round(0) == sac1.TOT_POP.sum()
diff --git a/tobler/tests/test_model.py b/tobler/tests/test_model.py
index 79466699..c0e0ae3c 100644
--- a/tobler/tests/test_model.py
+++ b/tobler/tests/test_model.py
@@ -1,47 +1,30 @@
"""test interpolation functions."""
import geopandas
-try:
- import quilt3
-
- QUILTMISSING = False
-except ImportError:
- QUILTMISSING = True
-
-import os
-
-import pytest
from libpysal.examples import load_example
from tobler.model import glm
def datasets():
- if not QUILTMISSING:
+ sac1 = load_example("Sacramento1")
+ sac2 = load_example("Sacramento2")
+ sac1 = geopandas.read_file(sac1.get_path("sacramentot2.shp"))
+ sac1 = sac1.to_crs(sac1.estimate_utm_crs())
+ sac2 = geopandas.read_file(sac2.get_path("SacramentoMSA2.shp"))
+ sac2 = sac2.to_crs(sac2.estimate_utm_crs())
+ sac1["pct_poverty"] = sac1.POV_POP / sac1.POV_TOT
+ categories = ["cat", "dog", "donkey", "wombat", "capybara"]
+ sac1["animal"] = (categories * ((len(sac1) // len(categories)) + 1))[
+ : len(sac1)
+ ]
- if not os.path.exists("nlcd_2011.tif"):
- p = quilt3.Package.browse("rasters/nlcd", "s3://spatial-ucr")
- p["nlcd_2011.tif"].fetch()
- sac1 = load_example("Sacramento1")
- sac2 = load_example("Sacramento2")
- sac1 = geopandas.read_file(sac1.get_path("sacramentot2.shp"))
- sac1 = sac1.to_crs(sac1.estimate_utm_crs())
- sac2 = geopandas.read_file(sac2.get_path("SacramentoMSA2.shp"))
- sac2 = sac2.to_crs(sac2.estimate_utm_crs())
- sac1["pct_poverty"] = sac1.POV_POP / sac1.POV_TOT
- categories = ["cat", "dog", "donkey", "wombat", "capybara"]
- sac1["animal"] = (categories * ((len(sac1) // len(categories)) + 1))[
- : len(sac1)
- ]
+ return sac1, sac2
- return sac1, sac2
- else:
- pass
-@pytest.mark.skipif(QUILTMISSING, reason="quilt3 not available.")
def test_glm_poisson():
sac1, sac2 = datasets()
glm_poisson = glm(
- source_df=sac2, target_df=sac1, variable="POP2001", raster="nlcd_2011.tif",
+ source_df=sac2, target_df=sac1, variable="POP2001", raster="https://spatial-ucr.s3.amazonaws.com/nlcd/landcover/nlcd_landcover_2011.tif",
)
assert glm_poisson.POP2001.sum() > 1469000
diff --git a/tobler/tests/test_utils.py b/tobler/tests/test_utils.py
index c7cb202e..b5dca26e 100644
--- a/tobler/tests/test_utils.py
+++ b/tobler/tests/test_utils.py
@@ -9,16 +9,17 @@
from tobler.util import h3fy
-sac1 = load_example("Sacramento1")
-sac1 = geopandas.read_file(sac1.get_path("sacramentot2.shp"))
-
def test_h3fy():
+ sac1 = load_example("Sacramento1")
+ sac1 = geopandas.read_file(sac1.get_path("sacramentot2.shp"))
sac_hex = h3fy(sac1, return_geoms=True)
assert sac_hex.shape == (364, 1)
def test_h3fy_nogeoms():
+ sac1 = load_example("Sacramento1")
+ sac1 = geopandas.read_file(sac1.get_path("sacramentot2.shp"))
sac_hex = h3fy(sac1, return_geoms=False)
assert len(sac_hex) == 364
@@ -43,14 +44,19 @@ def test_h3fy_diff_crs():
def test_h3fy_clip():
+ sac1 = load_example("Sacramento1")
+ sac1 = geopandas.read_file(sac1.get_path("sacramentot2.shp"))
sac_hex = h3fy(sac1, clip=True)
+ sac_hex = sac_hex.to_crs(sac_hex.estimate_utm_crs())
assert_almost_equal(
- sac_hex.to_crs(32710).unary_union.area, 13131736346.537416, decimal=4
+ sac_hex.area.sum(), 13131736346.537422, decimal=0
)
@pytest.mark.skipif(platform.system() == "Windows", reason='Unknown precision error on Windows. See #174 for details')
def test_h3_multipoly():
va = geopandas.read_file(load_example("virginia").get_path("virginia.shp"))
+ va = va.to_crs(va.estimate_utm_crs())
+
va = h3fy(va)
- assert_almost_equal(va.to_crs(2284).unary_union.area, 1106844905155.1118, decimal=0)
+ assert_almost_equal(va.area.sum(), 102888497504.47836, decimal=0)
diff --git a/tobler/util/util.py b/tobler/util/util.py
index dce6586b..5a7bbccf 100644
--- a/tobler/util/util.py
+++ b/tobler/util/util.py
@@ -5,8 +5,12 @@
import geopandas
import numpy as np
import pandas
+import shapely
+from packaging.version import Version
from shapely.geometry import Polygon
+GPD_10 = Version(geopandas.__version__) >= Version("1.0.0dev")
+
def circumradius(resolution):
"""Find the circumradius of an h3 hexagon at given resolution.
@@ -138,7 +142,10 @@ def h3fy(source, resolution=6, clip=False, buffer=False, return_geoms=True):
else:
source = source.to_crs(4326)
- source_unary = source.unary_union
+ if GPD_10:
+ source_unary = shapely.force_2d(source.union_all())
+ else:
+ source_unary = shapely.force_2d(source.unary_union)
if type(source_unary) == Polygon:
hexagons = _to_hex(
@@ -207,6 +214,8 @@ def _to_hex(source, resolution=6, return_geoms=True, buffer=True):
lambda hex_id: Polygon(h3.h3_to_geo_boundary(hex_id, geo_json=True)),
)
- hexs = geopandas.GeoDataFrame(hexids, geometry=polys, crs=4326).set_index("hex_id")
+ hexs = geopandas.GeoDataFrame(hexids, geometry=polys.values, crs=4326).set_index(
+ "hex_id"
+ )
return hexs
-
+[](https://github.com/pysal/tobler/actions/workflows/unittests.yml)
[](https://codecov.io/gh/pysal/tobler)
diff --git a/.ci/310.yml b/ci/310.yml
similarity index 92%
rename from .ci/310.yml
rename to ci/310.yml
index e666b7af..ff7f9a53 100644
--- a/.ci/310.yml
+++ b/ci/310.yml
@@ -5,7 +5,6 @@ dependencies:
- python=3.10
- dask
- dask-geopandas
- - distributed
- jupyterlab
- numpy
- geopandas
@@ -19,10 +18,11 @@ dependencies:
- libpysal
- tqdm
- codecov
- - quilt3
- pytest
- pytest-mpl
- pytest-cov
+ - pytest-xdist
+ - coverage
- twine
- pip
- h3-py
diff --git a/.ci/311.yml b/ci/311.yml
similarity index 67%
rename from .ci/311.yml
rename to ci/311.yml
index a533e59e..53c87042 100644
--- a/.ci/311.yml
+++ b/ci/311.yml
@@ -6,7 +6,6 @@ dependencies:
- jupyterlab
- dask
- dask-geopandas
- - distributed
- numpy
- geopandas
- pandas
@@ -20,11 +19,20 @@ dependencies:
- tqdm
- codecov
- pytest
- - quilt3
- pytest-mpl
- pytest-cov
+ - pytest-xdist
+ - coverage
- twine
- pip
- h3-py
- joblib
- astropy
+ - mapclassify
+ - sphinx>=1.4.3
+ - sphinxcontrib-bibtex==1.0.0
+ - sphinx_bootstrap_theme
+ - numpydoc
+ - nbsphinx
+ - joblib
+ - astropy
\ No newline at end of file
diff --git a/ci/312-dev.yml b/ci/312-dev.yml
new file mode 100644
index 00000000..b5f1e90f
--- /dev/null
+++ b/ci/312-dev.yml
@@ -0,0 +1,39 @@
+name: test
+channels:
+ - conda-forge
+dependencies:
+ - python=3.12
+ - dask
+ - dask-geopandas
+ - numpy
+ - pandas
+ - rasterio
+ - rasterstats
+ - statsmodels
+ - scipy
+ - libpysal
+ - tqdm
+ - codecov
+ - pytest-xdist
+ - coverage
+ - pytest
+ - pytest-mpl
+ - pytest-cov
+ - twine
+ - h3-py
+ - mapclassify
+ - sphinx>=1.4.3
+ - sphinxcontrib-bibtex==1.0.0
+ - sphinx_bootstrap_theme
+ - numpydoc
+ - nbsphinx
+ - joblib
+ - astropy
+ - pip
+ - pip:
+ # dev versions of packages
+ - --pre --index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple --extra-index-url https://pypi.org/simple
+ - scikit-learn
+ - scipy
+ - git+https://github.com/geopandas/geopandas.git@main
+ - shapely
diff --git a/.ci/39.yml b/ci/312.yml
similarity index 88%
rename from .ci/39.yml
rename to ci/312.yml
index d029839f..2782f0b2 100644
--- a/.ci/39.yml
+++ b/ci/312.yml
@@ -2,10 +2,9 @@ name: test
channels:
- conda-forge
dependencies:
- - python=3.9
+ - python=3.12
- dask
- dask-geopandas
- - distributed
- numpy
- geopandas
- pandas
@@ -17,15 +16,15 @@ dependencies:
- libpysal
- tqdm
- codecov
+ - pytest-xdist
+ - coverage
- pytest
- - quilt3
- pytest-mpl
- pytest-cov
- twine
- pip
- h3-py
- mapclassify
- - descartes
- sphinx>=1.4.3
- sphinxcontrib-bibtex==1.0.0
- sphinx_bootstrap_theme
diff --git a/codecov.yml b/codecov.yml
new file mode 100644
index 00000000..82613e08
--- /dev/null
+++ b/codecov.yml
@@ -0,0 +1,20 @@
+codecov:
+ notify:
+ after_n_builds: 7
+coverage:
+ range: 50..95
+ round: nearest
+ precision: 1
+ status:
+ project:
+ default:
+ threshold: 15%
+ patch:
+ default:
+ threshold: 20%
+ target: 60%
+comment:
+ layout: "reach, diff, files"
+ behavior: once
+ after_n_builds: 7
+ require_changes: true
diff --git a/docs/index.rst b/docs/index.rst
index f996711b..92144c55 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -10,7 +10,7 @@
