Merge pull request #372 from knaaptime/lodesupdate

.ci/310.yml

@@ -6,7 +6,6 @@ dependencies:
   - pandas
   - giddy >=2.2.1
   - libpysal
-  - cenpy
   - geopandas  >=0.9
   - hdbscan
   - matplotlib 

.ci/311.yml

@@ -6,7 +6,6 @@ dependencies:
   - pandas
   - giddy >=2.2.1
   - libpysal
-  - cenpy
   - geopandas >=0.9
   - hdbscan
   - matplotlib 

.ci/39.yml

@@ -6,7 +6,6 @@ dependencies:
   - pandas
   - giddy >=2.2.1
   - libpysal
-  - cenpy
   - geopandas  >=0.9
   - matplotlib 
   - scikit-learn

.github/release.yml

@@ -11,6 +11,9 @@ changelog:
     - title: Enhancements
       labels:
         - enhancement
+    - title: Maintenance
+      labels:
+        - maintenance
     - title: Other Changes
       labels:
         - "*"

.github/workflows/unittests.yml

@@ -1,91 +1,61 @@
- name: Continuous Integration
-
- on:
-   push:
-     branches:
-       - '*'
-   pull_request:
-     branches:
-       - '*'
-   schedule:
-       - cron: '59 23 * * *'
+name: Tests
 
- jobs:
-   unittests:
-     name: CI (${{ matrix.os }}-${{ matrix.environment-file }})
-     runs-on: ${{ matrix.os }}
-     continue-on-error: true
-     timeout-minutes: 90 
-     strategy:
-       matrix:
-         os: ['ubuntu-latest', 'macos-latest', 'windows-latest']
-         environment-file: [.ci/39.yml, .ci/310.yml, .ci/311.yml]
-
-     steps:
-       - name: checkout repo
-         uses: actions/checkout@v2
-
-       - name: setup micromamba
-         uses: mamba-org/provision-with-micromamba@main
-         with:
-           environment-file: ${{ matrix.environment-file }}
-           micromamba-version: 'latest'
-           mamba-version: "*"
-           channels: conda-forge
-           channel-priority: true
-
-
-       - name: install geosnap - bash
-         shell: bash -l {0}
-         run: pip install -e . --no-deps --force-reinstall
-         if: matrix.os != 'windows-latest'
-
-       - name: install geosnap - powershell
-         shell: powershell
-         run: pip install -e . --no-deps --force-reinstall
-         if: matrix.os == 'windows-latest'
-
-
-       - name: download data - bash
-         shell: bash -l {0}
-         run: python geosnap/tests/_dl_data.py
-         env:
-           COMBO_DATA: ${{ secrets.COMBO_DATA }}
-         if: matrix.os != 'windows-latest'
-
-       - name: download data - powershell
-         shell: powershell
-         run: python geosnap/tests/_dl_data.py
-         env:
-           COMBO_DATA: ${{ secrets.COMBO_DATA }}
-         if: matrix.os == 'windows-latest'
-
-
-       - name: run tests - bash
-         shell: bash -l {0}
-         run: pytest -v geosnap --cov=geosnap --cov-report=xml
-         env:
-           LTDB_SAMPLE: ${{ secrets.COMBO_DATA }} # check whether we can pull secrets
-           LTDB_FULL: ${{ secrets.COMBO_DATA }}
-           NCDB: ${{ secrets.COMBO_DATA }}
-         if: matrix.os != 'windows-latest'
-
-       - name: run tests - powershell
-         shell: powershell
-         run: pytest -v geosnap
-         env:
-           LTDB_SAMPLE: ${{ secrets.COMBO_DATA }} # check whether we can pull secrets
-           LTDB_FULL: ${{ secrets.COMBO_DATA }}
-           NCDB: ${{ secrets.COMBO_DATA }}
-         if: matrix.os == 'windows-latest'
-
-
-       - name: codecov
-         uses: codecov/codecov-action@v2
-         with:
-           token: ${{ secrets.CODECOV_TOKEN }}
-           file: ./coverage.xml
-           flags: unittests # optional
-           name: geosnap-codecov
-           verbose: true 
-         if: matrix.os != 'windows-latest'
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches:
+      - "*"
+  schedule:
+    - cron: "0 0 * * 1,4"
+
+jobs:
+  Test:
+    name: ${{ matrix.os }}, ${{ matrix.environment-file }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest]
+        environment-file:
+          - .ci/39.yml
+          - .ci/310.yml
+          - .ci/311.yml
+        include:
+          - environment-file: .ci/310.yml
+            os: macos-latest
+          - environment-file: .ci/310.yml
+            os: windows-latest
+    defaults:
+      run:
+        shell: bash -l {0}
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: setup micromamba
+        uses: mamba-org/provision-with-micromamba@main
+        with:
+          environment-file: ${{ matrix.environment-file }}
+          micromamba-version: "latest"
+
+      - name: Install geosnap
+        run: pip install . ;python geosnap/tests/_dl_data.py;
+        env:
+          COMBO_DATA: ${{ secrets.COMBO_DATA }}
+
+      - name: Test geosnap
+        run: |
+          pytest -v --color yes --cov geosnap --cov-append --cov-report term-missing --cov-report xml .
+
+      - uses: codecov/codecov-action@v3
+
+      - name: Generate and publish the report
+        if: |
+          failure()
+          && steps.status.outcome == 'failure'
+          && github.event_name == 'schedule'
+          && github.repository_owner == 'pysal'
+        uses: xarray-contrib/issue-from-pytest-log@v1
+        with:
+          log-path: pytest-log.jsonl

docs/api.rst

@@ -27,6 +27,7 @@ available quickly with no configuration by accessing methods on the class.
     DataStore.acs
     DataStore.blocks_2000
     DataStore.blocks_2010
+    DataStore.blocks_2020
     DataStore.codebook
     DataStore.counties
     DataStore.ejscreen
@@ -59,6 +60,7 @@ files instead of streaming over the web.
     io.store_census
     io.store_blocks_2000
     io.store_blocks_2010
+    io.store_blocks_2020
     io.store_ejscreen
     io.store_ltdb
     io.store_ncdb
@@ -108,9 +110,9 @@ Model neighborhood change using optimal-matching algorithms or spatial discrete
 .. autosummary::
    :toctree: generated/
 
+   analyze.draw_sequence_from_gdf
    analyze.linc
    analyze.lincs_from_gdf
-   analyze.predict_markov_labels
    analyze.sequence
    analyze.transition
 
@@ -141,7 +143,7 @@ Compute shortest path distance along a network using pandana, and visualize trav
 
    analyze.compute_travel_cost_adjlist
    analyze.isochrone
-   analyze.isocrones
+   analyze.isochrones
 
 The ModelResults Class
 '''''''''''''''''''''''''''''''''''''''''''''

docs/data.rst

@@ -41,6 +41,9 @@ Geo Data
 | Blocks  | https://www2.census.gov/geo/tiger/TIGER2018/TABBLOCK/      |
 | 2010    |                                                            |
 +---------+------------------------------------------------------------+
+| Blocks  | https://www2.census.gov/geo/tiger/TIGER2021/TABBLOCK/      |
+| 2020    |                                                            |
++---------+------------------------------------------------------------+
 | Tracts  | https://github.co                                          |
 | 1990    | m/loganpowell/census-geojson/tree/master/GeoJSON/500k/1990 |
 +---------+------------------------------------------------------------+

geosnap/__init__.py

@@ -1,4 +1,3 @@
-
 r"""
 
 geosnap: Geospatial Neighborhood Analysis Package.
@@ -25,12 +24,8 @@
 import contextlib
 from importlib.metadata import PackageNotFoundError, version
 
-from . import analyze
-from . import io
-from . import util
-from . import visualize
-from . import harmonize
-from ._data import _Map, DataStore
+from . import analyze, harmonize, io, util, visualize
+from ._data import DataStore, _Map
 
 with contextlib.suppress(PackageNotFoundError):
-    __version__ = version("geosnap")
+    __version__ = version("geosnap")

geosnap/_data.py

@@ -358,6 +358,44 @@ def blocks_2010(self, states=None, fips=None):
 
         return blocks
 
+    def blocks_2020(self, states=None, fips=None):
+        """Census blocks for 2020.
+
+        Parameters
+        ----------
+        states : list-like
+            list of state fips codes to return as a datafrrame.
+
+        Returns
+        -------
+        type
+        pandas.DataFrame or geopandas.GeoDataFrame
+            2010 blocks as a geodataframe or as a dataframe with geometry
+            stored as well-known binary on the 'wkb' column.
+
+        """
+        msg = (
+            "Unable to locate local census 2020 block data. Streaming instead.\n"
+            "If you plan to use census data repeatedly you can store it locally "
+            "with the io.store_blocks_2010 function for better performance"
+        )
+        if isinstance(states, (str, int)):
+            states = [states]
+        blks = {}
+        for state in states:
+            local = pathlib.Path(self.data_dir, "blocks_2020", f"{state}.parquet")
+            remote = f"s3://spatial-ucr/census/blocks_2020/{state}.parquet"
+            blks[state] = _fetcher(local, remote, msg)
+
+            if fips:
+                blks[state] = blks[state][blks[state]["geoid"].str.startswith(fips)]
+
+            blks[state]["year"] = 2020
+        blocks = list(blks.values())
+        blocks = gpd.GeoDataFrame(pd.concat(blocks, sort=True))
+
+        return blocks
+
     def tracts_1990(self, states=None):
         """Nationwide Census Tracts as drawn in 1990 (cartographic 500k).