Merge pull request #10 from deepnote/fpyrek/grn-4947-support-python-313

feat: python 3.13 support

Author: FilipPyrek

.cursorrules

@@ -137,6 +137,7 @@ Supported versions:
 - Python 3.10
 - Python 3.11
 - Python 3.12
+- Python 3.13
 
 ## Code Examples
 

.github/workflows/cd.yml

@@ -35,7 +35,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python_version: ["3.9", "3.10", "3.11", "3.12"]
+        python_version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
     permissions:
       id-token: write
       contents: read
@@ -413,7 +413,7 @@ jobs:
     needs: build-and-push-artifacts-status
     if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
     env:
-      PYTHON_VERSIONS: "3.9,3.10,3.11,3.12"
+      PYTHON_VERSIONS: "3.9,3.10,3.11,3.12,3.13"
     steps:
       - name: Checkout code
         uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4

.github/workflows/ci.yml

@@ -158,7 +158,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
 
     steps:
     - name: Checkout code
@@ -277,7 +277,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
     steps:
       - name: Checkout code
         uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4
@@ -293,11 +293,11 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
 
-      - name: Set up Java 11
+      - name: Set up Java 17
         uses: actions/setup-java@c5195efecf7bdfc987ee8bae7a71cb8b11521c00 # v4
         with:
           distribution: 'temurin'
-          java-version: '11'
+          java-version: '17'
 
       - name: Load cached Poetry installation
         id: cached-poetry
@@ -322,6 +322,10 @@ jobs:
           path: .venv
           key: venv-v2-${{ github.event.pull_request.head.repo.full_name || github.repository }}-py${{ matrix.python-version }}-${{ hashFiles('poetry.lock') }}
 
+      - name: Add venv to PATH
+        if: steps.cache-deps.outputs.cache-hit == 'true'
+        run: echo "${{ github.workspace }}/.venv/bin" >> $GITHUB_PATH
+
       - name: Install dependencies
         if: steps.cache-deps.outputs.cache-hit != 'true'
         run: poetry install --no-interaction --no-root --with dev
@@ -363,6 +367,14 @@ jobs:
             echo "Warning: No coverage file generated"
           fi
 
+      - name: Per-version coverage summary
+        if: steps.test-unit.outputs.coverage_generated == 'true'
+        env:
+          PYTHON_VERSION: ${{ matrix.python-version }}
+        run: |
+          echo "## Python ${PYTHON_VERSION} Coverage" >> $GITHUB_STEP_SUMMARY
+          poetry run coverage report --data-file=coverage/.coverage.${PYTHON_VERSION} --format=markdown >> $GITHUB_STEP_SUMMARY
+
       - name: Upload test results to Codecov (these are results not coverage reports)
         if: ${{ !cancelled() }}
         uses: codecov/test-results-action@47f89e9acb64b76debcd5ea40642d25a4adced9f # v1
@@ -378,13 +390,6 @@ jobs:
           files: ./coverage/coverage-${{ matrix.python-version }}.xml
           fail_ci_if_error: ${{ github.event.pull_request.head.repo.full_name == github.repository || github.event_name == 'push' }}
 
-      - name: Per-version coverage summary
-        if: steps.test-unit.outputs.coverage_generated == 'true'
-        env:
-          PYTHON_VERSION: ${{ matrix.python-version }}
-        run: |
-          echo "## Python ${PYTHON_VERSION} Coverage" >> $GITHUB_STEP_SUMMARY
-          poetry run coverage report --data-file=coverage/.coverage.${PYTHON_VERSION} --format=markdown >> $GITHUB_STEP_SUMMARY
   audit-prod:
     name: Audit - Production
     runs-on: ubuntu-latest

.mise.toml

@@ -3,8 +3,8 @@
 # Then run: mise install
 
 [tools]
-python = "3.12"
-java = "temurin-11"
+python = "3.13"
+java = "temurin-17"
 poetry = "2.2.0"
 
 [tasks.setup]

.pre-commit-config.yaml

@@ -11,13 +11,13 @@ repos:
     hooks:
       - id: flake8
         name: flake8
-        entry: poetry run flake8 -j auto
+        entry: mise exec -- poetry run flake8 -j auto
         language: system
         types: [python]
 
       - id: isort
         name: isort
-        entry: poetry run isort
+        entry: mise exec -- poetry run isort
         language: system
         types: [python]
         args: ["--filter-files"]

CLAUDE.md

@@ -52,7 +52,7 @@
 
 ## Python Version Support
 
-- Python 3.9, 3.10, 3.11, 3.12
+- Python 3.9, 3.10, 3.11, 3.12, 3.13
 
 ## Dependencies
 

CONTRIBUTING.md

@@ -1,6 +1,6 @@
 # Contributing
 
-All contributions are highly appreciated! 
+All contributions are highly appreciated!
 Start by [forking the repository](https://github.com/deepnote/deepnote-toolkit/fork) on GitHub and setting up Deepnote Toolkit for local development.
 
 ## Local development setup
@@ -13,17 +13,17 @@ Start by [forking the repository](https://github.com/deepnote/deepnote-toolkit/f
 2. Run setup:
 
     ```bash
-    mise install        # Installs Python 3.12 and Java 11
+    mise install        # Installs Python 3.12 and Java 17
     mise run setup      # Installs dependencies and pre-commit hooks
     ```
 
 #### Option 2: Manual setup
 
 1. Install poetry: [Installation](https://python-poetry.org/docs/#installation)
-2. Install Java 11 (required for PySpark tests):
-    - macOS: `brew install openjdk@11`
-    - Ubuntu/Debian: `sudo apt-get install openjdk-11-jdk`
-    - RHEL/Fedora: `sudo dnf install java-11-openjdk-devel`
+2. Install Java 17 (required for PySpark tests):
+    - macOS: `brew install openjdk@17`
+    - Ubuntu/Debian: `sudo apt-get install openjdk-17-jdk`
+    - RHEL/Fedora: `sudo dnf install java-17-openjdk-devel`
 3. Set up venv for development package:
 
     ```bash

deepnote_toolkit/ocelots/pandas/analyze.py

@@ -78,13 +78,25 @@ def _get_histogram(pd_series):
             # let's drop infinite values because they break histograms
             np_array = np.array(pd_series.replace([np.inf, -np.inf], np.nan).dropna())
 
+        # Check if array is empty after dropping NaN/NaT values
+        if len(np_array) == 0:
+            return None
+
         y, bins = np.histogram(np_array, bins=10)
         return [
             {"bin_start": bins[i], "bin_end": bins[i + 1], "count": count.item()}
             for i, count in enumerate(y)
         ]
-    except IndexError:
-        # numpy bug https://github.com/numpy/numpy/issues/8627
+    except (ValueError, IndexError) as e:
+        # NumPy 2.2+ raises "Too many bins for data range" when:
+        # - Data range is zero (all values identical), or
+        # - For integer data, bin width would be < 1.0, or
+        # - Floating point precision prevents creating finite-sized bins at large scales
+        # Numpy implementation: https://github.com/numpy/numpy/blob/e7a123b2d3eca9897843791dd698c1803d9a39c2/numpy/lib/_histograms_impl.py#L454
+        # IndexError can occur in NumPy 2.x with edge cases involving large integers or datetime conversions
+        if isinstance(e, ValueError) and "Too many bins for data range" in str(e):
+            return None
+        # For IndexError or other ValueError cases, return None to gracefully handle edge cases
         return None
 
 

deepnote_toolkit/variable_explorer.py

@@ -407,6 +407,27 @@ def _to_int(x):
     return int(x) if x else None
 
 
+def _get_type_name(v):
+    """
+    Get the normalized type name for a variable with backwards compatibility.
+
+    In Python 3.13, NumPy's bool_ type may report as 'bool' instead of 'bool_'.
+    This function ensures we always return 'bool_' for NumPy bool types to maintain
+    compatibility with older Python versions.
+    """
+    # Check for NumPy bool_ type first (most reliable check)
+    # This handles the case where Python 3.13 reports np.bool_ as 'bool'
+    try:
+        if np is not None and isinstance(v, np.bool_):
+            return "bool_"
+    except (AttributeError, TypeError):
+        # If numpy types change or there's an issue with the comparison
+        pass
+
+    # Fall back to standard type name
+    return type(v).__name__
+
+
 def _get_variable_dict_entry(var_name, v):
     try:
         shape = _get_shape(v)
@@ -415,7 +436,7 @@ def _get_variable_dict_entry(var_name, v):
         underlying_data_type = _get_underlying_data_type(v)
         var_result = {
             "varName": var_name,
-            "varType": type(v).__name__,
+            "varType": _get_type_name(v),
             "varSize": _to_int(_get_size(v)),
             "varShape": shape,
             "varContent": _get_content(v),

dockerfiles/test.Dockerfile

@@ -2,7 +2,7 @@ FROM quay.io/pypa/manylinux_2_28_x86_64:2025.05.28-1
 RUN pipx install nox poetry==2.2.0
 
 RUN dnf -y update && \
-    dnf -y install java-11-openjdk-devel \
+    dnf -y install java-17-openjdk-devel \
     # Required for pymssql - provides sqlfront.h header file
     freetds-devel \
     # Required for database connectivity through ODBC