Merge branch 'main' into blog/ibis-udf-rewriting

.devcontainer/Dockerfile

@@ -1,5 +1,5 @@
 FROM mcr.microsoft.com/vscode/devcontainers/python:3.13
-COPY --from=ghcr.io/astral-sh/uv:0.5.26 /uv /uvx /bin/
+COPY --from=ghcr.io/astral-sh/uv:0.5.29 /uv /uvx /bin/
 ARG USERNAME=vscode
 
 RUN apt-get update && \

.github/workflows/assign.yml

@@ -10,6 +10,6 @@ jobs:
     runs-on: ubuntu-latest
     if: github.event.comment.body == '/take'
     steps:
-      - uses: pozil/auto-assign-issue@v2.1.2
+      - uses: pozil/auto-assign-issue@v2.2.0
         with:
           assignees: ${{ github.event.comment.user.login }}

.github/workflows/create-rotate-key-issue.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Generate a GitHub token
-        uses: actions/[email protected].2
+        uses: actions/[email protected].3
         id: generate_token
         with:
           app-id: ${{ secrets.SQUAWK_BOT_APP_ID }}

.github/workflows/docs-preview.yml

@@ -13,7 +13,7 @@ jobs:
       cancel-in-progress: true
     if: github.event.label.name == 'docs-preview'
     steps:
-      - uses: actions/[email protected].2
+      - uses: actions/[email protected].3
         id: generate_token
         with:
           app-id: ${{ secrets.DOCS_BOT_APP_ID }}

.github/workflows/ibis-backends-cloud.yml

@@ -22,18 +22,20 @@ env:
 
 jobs:
   test_backends:
-    name: ${{ matrix.backend.title }} python-${{ matrix.python-version }}
+    name: ${{ matrix.backend.title }} python-${{ matrix.python-version }}-${{ matrix.os }}
     # only a single bigquery or snowflake run at a time, otherwise test data is
     # clobbered by concurrent runs
     concurrency:
       group: ${{ matrix.backend.title }}-${{ matrix.python-version }}-${{ github.event.label.name || 'ci-run-cloud' }}
       cancel-in-progress: false
 
-    runs-on: ubuntu-latest
+    runs-on: ${{ matrix.os }}
     if: github.event_name == 'push' || github.event.label.name == 'ci-run-cloud'
     strategy:
       fail-fast: false
       matrix:
+        os:
+          - ubuntu-latest
         python-version:
           - "3.10"
           - "3.13"
@@ -51,33 +53,44 @@ jobs:
             extras:
               - --extra athena
         include:
-          - python-version: "3.10"
+          - os: ubuntu-latest
+            python-version: "3.10"
             backend:
               name: bigquery
               title: BigQuery
               extras:
                 - --extra bigquery
-          - python-version: "3.13"
+          - os: ubuntu-latest
+            python-version: "3.13"
             backend:
               name: bigquery
               title: BigQuery
               extras:
                 - --extra bigquery
                 - --extra geospatial
-          - python-version: "3.10"
+          - os: ubuntu-latest
+            python-version: "3.10"
             backend:
               name: snowflake
               title: Snowflake + Snowpark
               key: snowpark
               extras:
                 - --extra snowflake
-          - python-version: "3.11"
+          - os: ubuntu-latest
+            python-version: "3.11"
             backend:
               name: snowflake
               title: Snowflake + Snowpark
               key: snowpark
               extras:
                 - --extra snowflake
+          - os: windows-latest
+            python-version: "3.12"
+            backend:
+              name: snowflake
+              title: Snowflake
+              extras:
+                - --extra snowflake
     # this allows extractions/setup-just to list releases for `just` at a higher
     # rate limit while restricting GITHUB_TOKEN permissions elsewhere
     permissions:
@@ -97,7 +110,7 @@ jobs:
           fetch-depth: 0
           ref: ${{ github.event.pull_request.head.sha }}
 
-      - uses: actions/[email protected].2
+      - uses: actions/[email protected].3
         id: generate_token
         with:
           app-id: ${{ secrets.DOCS_BOT_APP_ID }}
@@ -138,6 +151,7 @@ jobs:
 
       - name: setup databricks credentials
         if: matrix.backend.name == 'databricks'
+        shell: bash
         run: |
           {
             echo "DATABRICKS_HTTP_PATH=${DATABRICKS_HTTP_PATH}"
@@ -151,6 +165,7 @@ jobs:
 
       - name: setup snowflake credentials
         if: matrix.backend.name == 'snowflake'
+        shell: bash
         run: |
           pyversion="${{ matrix.python-version }}"
           {
@@ -160,6 +175,9 @@ jobs:
             echo "SNOWFLAKE_DATABASE=${SNOWFLAKE_DATABASE}"
             echo "SNOWFLAKE_SCHEMA=${SNOWFLAKE_SCHEMA}_python${pyversion//./}_${{ matrix.backend.key }}"
             echo "SNOWFLAKE_WAREHOUSE=${SNOWFLAKE_WAREHOUSE}"
+            if ${{ matrix.backend.key == 'snowpark' }}; then
+              echo "SNOWFLAKE_SNOWPARK=1" >> "$GITHUB_ENV"
+            fi
           } >> "$GITHUB_ENV"
         env:
           SNOWFLAKE_USER: ${{ secrets.SNOWFLAKE_USER }}
@@ -176,10 +194,6 @@ jobs:
           aws-region: us-east-2
           role-to-assume: arn:aws:iam::070284473168:role/ibis-project-athena
 
-      - name: enable snowpark testing
-        if: matrix.backend.key == 'snowpark'
-        run: echo "SNOWFLAKE_SNOWPARK=1" >> "$GITHUB_ENV"
-
       - name: "run parallel tests: ${{ matrix.backend.name }}"
         run: just ci-check "${{ join(matrix.backend.extras, ' ') }} --extra examples" -m ${{ matrix.backend.name }} --numprocesses auto --dist loadgroup
 

.github/workflows/release.yml

@@ -14,7 +14,7 @@ jobs:
   release:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/[email protected].2
+      - uses: actions/[email protected].3
         id: generate_token
         with:
           app-id: ${{ secrets.APP_ID }}

.github/workflows/update-nix-flakes.yml

@@ -13,7 +13,7 @@ jobs:
       - name: install nix
         uses: DeterminateSystems/nix-installer-action@v16
 
-      - uses: actions/[email protected].2
+      - uses: actions/[email protected].3
         id: generate-token
         with:
           app-id: ${{ secrets.SQUAWK_BOT_APP_ID }}

ci/release/dry_run.sh

@@ -35,14 +35,14 @@ nix develop '.#release' -c git commit -m 'test: semantic-release dry run' --no-v
 unset GITHUB_ACTIONS
 
 nix develop '.#release' -c npx --yes \
-  -p "semantic-release@24.0.0" \
+  -p "semantic-release" \
   -p "@semantic-release/commit-analyzer" \
   -p "@semantic-release/release-notes-generator" \
   -p "@semantic-release/changelog" \
   -p "@semantic-release/exec" \
   -p "@semantic-release/git" \
-  -p "semantic-release-replace-plugin@1.2.0" \
-  -p "conventional-changelog-conventionalcommits@8.0.0" \
+  -p "semantic-release-replace-plugin" \
+  -p "conventional-changelog-conventionalcommits" \
   semantic-release \
   --ci \
   --dry-run \

ci/release/run.sh

@@ -3,13 +3,13 @@
 set -euo pipefail
 
 nix develop '.#release' -c npx --yes \
-  -p "semantic-release@24.0.0" \
+  -p "semantic-release" \
   -p "@semantic-release/commit-analyzer" \
   -p "@semantic-release/release-notes-generator" \
   -p "@semantic-release/changelog" \
   -p "@semantic-release/github" \
   -p "@semantic-release/exec" \
   -p "@semantic-release/git" \
-  -p "semantic-release-replace-plugin@1.2.0" \
-  -p "conventional-changelog-conventionalcommits@8.0.0" \
+  -p "semantic-release-replace-plugin" \
+  -p "conventional-changelog-conventionalcommits" \
   semantic-release --ci

compose.yaml

@@ -1,15 +1,18 @@
 services:
   clickhouse:
-    image: clickhouse/clickhouse-server:25.1.2.3-alpine
+    image: clickhouse/clickhouse-server:25.1.3.23-alpine
     ports:
       - 8123:8123 # http port
       - 9000:9000 # native protocol port
+    environment:
+      CLICKHOUSE_USER: ibis
+      CLICKHOUSE_PASSWORD: ""
     healthcheck:
       interval: 1s
       retries: 10
       test:
         - CMD-SHELL
-        - wget -qO- 'http://127.0.0.1:8123/?query=SELECT%201' # SELECT 1
+        - wget -qO- 'http://ibis@clickhouse:8123/?query=SELECT%201' # SELECT 1
     volumes:
       - clickhouse:/var/lib/clickhouse/user_files/ibis
     networks:
@@ -98,7 +101,7 @@ services:
       - trino
 
   minio:
-    image: bitnami/minio:2025.1.20
+    image: bitnami/minio:2025.2.3
     environment:
       MINIO_ROOT_USER: accesskey
       MINIO_ROOT_PASSWORD: secretkey
@@ -554,7 +557,7 @@ services:
       - impala
 
   risingwave:
-    image: ghcr.io/risingwavelabs/risingwave:v2.1.2
+    image: ghcr.io/risingwavelabs/risingwave:v2.1.3
     command: "standalone --meta-opts=\" \
       --advertise-addr 0.0.0.0:5690 \
       --backend mem \

docs/posts/campaign-finance/index.qmd

@@ -73,7 +73,7 @@ raw
 ```
 
 ```{python}
-# For a more comprehesive description of the columns and their meaning, see
+# For a more comprehensive description of the columns and their meaning, see
 # https://www.fec.gov/campaign-finance-data/contributions-individuals-file-description/
 columns = {
     "CMTE_ID": "keep",  # Committee ID
@@ -101,9 +101,9 @@ columns = {
     "SUB_ID": "drop",  # Submission ID. Unique number assigned to each transaction.
 }
 
-renaming = {old: new for old, new in zip(raw.columns, columns.keys())}
+renaming = dict(zip(columns.keys(), raw.columns))
 to_keep = [k for k, v in columns.items() if v == "keep"]
-kept = raw.relabel(renaming)[to_keep]
+kept = raw.rename(renaming)[to_keep]
 kept
 ```
 
@@ -214,7 +214,7 @@ from ibis.expr.types import StringValue, DateValue
 
 
 def mmddyyyy_to_date(val: StringValue) -> DateValue:
-    return val.cast(str).lpad(8, "0").to_timestamp("%m%d%Y").date()
+    return val.cast(str).lpad(8, "0").nullif("").to_timestamp("%m%d%Y").date()
 
 
 cleaned = cleaned.mutate(date=mmddyyyy_to_date(_.TRANSACTION_DT)).drop("TRANSACTION_DT")

docs/posts/ibis-duckdb-geospatial/index.qmd

@@ -140,7 +140,7 @@ streets
 Using the deferred API, we can check which streets are within `d=10` meters of distance.
 
 ```{python}
-sts_near_broad = streets.filter(_.geom.d_within(broad_station_subquery, 10))
+sts_near_broad = streets.filter(_.geom.d_within(broad_station_subquery, distance=10))
 sts_near_broad
 ```
 
@@ -227,7 +227,9 @@ data we can't tell the street near which it happened. However, we can check if t
 distance of a street.
 
 ```{python}
-h_street = streets.filter(_.geom.d_within(h_near_broad.select(_.geom).as_scalar(), 2))
+h_street = streets.filter(
+    _.geom.d_within(h_near_broad.select(_.geom).as_scalar(), distance=2)
+)
 h_street
 ```