fg-data-profiling-wasm 0.1.0__tar.gz

fg_data_profiling_wasm-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 awesome wasm packages
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

fg_data_profiling_wasm-0.1.0/MANIFEST.in

@@ -0,0 +1,9 @@
+# Templates and static resources (applied after materialize)
+recursive-include src/data_profiling/report/presentation/flavours/html/templates *.html *.js *.css
+
+# Configuration
+include src/data_profiling/*.yaml
+
+include LICENSE
+include README.md
+include VERSION

fg_data_profiling_wasm-0.1.0/PKG-INFO

@@ -0,0 +1,195 @@
+Metadata-Version: 2.4
+Name: fg-data-profiling-wasm
+Version: 0.1.0
+Summary: Pyodide-friendly fork of fg-data-profiling (ydata-profiling) for browser WASM
+Author: awesome-wasm-packages
+Maintainer: awesome-wasm-packages
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/awesome-wasm-packages/fg-data-profiling-wasm
+Project-URL: Upstream, https://github.com/Data-Centric-AI-Community/fg-data-profiling
+Keywords: pandas,profiling,pyodide,wasm,eda
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: <3.14,>=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: scipy<1.17,>=1.8
+Requires-Dist: pandas!=1.4.0,<3.0,>1.5
+Requires-Dist: matplotlib<=3.10,>=3.5
+Requires-Dist: pydantic<3,>=2
+Requires-Dist: PyYAML<6.1,>=6.0.3
+Requires-Dist: jinja2<3.2,>=3.1.6
+Requires-Dist: visions[type_image_path]<0.8.2,>=0.7.5
+Requires-Dist: numpy<2.4,>=1.22
+Requires-Dist: filetype>=1.0.0
+Requires-Dist: requests<3,>=2.32.0
+Requires-Dist: tqdm<5,>=4.66.3
+Requires-Dist: seaborn<0.14,>=0.10.1
+Requires-Dist: multimethod<2,>=1.4
+Requires-Dist: statsmodels<1,>=0.13.2
+Requires-Dist: typeguard<5,>=4
+Requires-Dist: imagehash==4.3.2
+Requires-Dist: wordcloud>=1.9.4
+Requires-Dist: dacite<2,>=1.9
+Provides-Extra: native
+Requires-Dist: minify-html>=0.15.0; extra == "native"
+Requires-Dist: phik<0.13,>=0.12.5; extra == "native"
+Requires-Dist: numba<0.63,>=0.60; extra == "native"
+Dynamic: license-file
+
+# fg-data-profiling-wasm
+
+Pyodide-friendly fork of [fg-data-profiling](https://github.com/Data-Centric-AI-Community/fg-data-profiling) (formerly ydata-profiling / pandas-profiling).
+
+**You do not compile this package to WASM.** Upstream already ships as a pure-Python wheel (`py2.py3-none-any`). This fork only does dependency surgery so it can install and run under Pyodide.
+
+## What changed vs upstream
+
+| Change | Why |
+|---|---|
+| Drop hard deps: `numba`, `minify-html`, `phik` | Native / JIT; broken or impractical in browser WASM |
+| Default `html.minify_html = False` | Avoid lazy-importing the Rust `minify-html` extension |
+| Soft-fail if minify is requested but missing | Safer in constrained environments |
+| Keep `phi_k` off (already upstream default) | Avoid needing `phik` |
+| Package name `fg-data-profiling-wasm` | Distinguish the Pyodide wheel from upstream |
+
+Optional native extras remain under `[project.optional-dependencies] native` for desktop use.
+
+## Layout
+
+```
+src/                  # vendored upstream + patches
+patches/              # Pyodide-friendly diffs reapplied on each sync
+scripts/sync-upstream.sh
+upstream.lock.json    # pinned upstream ref + commit
+pyodide/              # install helper + dependency matrix
+pyproject.toml        # Pyodide-friendly dependency set
+```
+
+## Upgrading from upstream
+
+Pinned upstream lives in [`upstream.lock.json`](upstream.lock.json).
+
+```bash
+# Is upstream ahead of our lock?
+make check-upstream
+# or: ./scripts/sync-upstream.sh --check
+
+# Pull latest develop (or whatever ref is in the lock), re-apply patches,
+# refresh dependency pins, update the lockfile
+make sync
+# or: ./scripts/sync-upstream.sh
+
+# Sync a release tag / other ref
+make sync-ref REF=v4.9.0
+# or: ./scripts/sync-upstream.sh --ref v4.9.0
+
+# After a successful sync, bump our PyPI version
+./scripts/sync-upstream.sh --bump patch
+
+# If a patch no longer applies: fix src/ by hand, then regenerate the patch series
+./scripts/sync-upstream.sh --regen-patches
+```
+
+Typical release flow after upstream moves:
+
+```bash
+./scripts/sync-upstream.sh --ref develop --bump patch
+python -m build
+# review git diff, commit, push, twine upload dist/*
+```
+
+A weekly GitHub Action (`.github/workflows/upstream-check.yml`) opens/comments on an issue when the lock is behind.
+
+## Build a wheel
+
+```bash
+python -m pip install build
+python -m build    # → dist/fg_data_profiling_wasm-*-py2.py3-none-any.whl
+```
+
+Current artifact:
+
+- `dist/fg_data_profiling_wasm-0.1.0-py2.py3-none-any.whl` (purelib; PyPI-compatible)
+
+## Publish to PyPI (GitHub Actions)
+
+The package is **not on PyPI yet**. Publishing is automated via [Trusted Publishing](https://docs.pypi.org/trusted-publishers/) (OIDC) — no long-lived API token in the repo.
+
+### One-time PyPI setup
+
+1. Sign in at https://pypi.org/
+2. Open **Publishing** → **Add a new pending publisher** (project does not exist yet):
+   - **PyPI project name:** `fg-data-profiling-wasm`
+   - **Owner:** `awesome-wasm-packages`
+   - **Repository:** `fg-data-profiling-wasm`
+   - **Workflow name:** `publish.yml`
+   - **Environment name:** `pypi`
+3. In GitHub → **Settings → Environments** → create environment `pypi` (optional protection rules / required reviewers).
+
+### Publish a version
+
+```bash
+# bump version in VERSION + pyproject.toml (or)
+./scripts/sync-upstream.sh --bump patch
+git add -A && git commit -m "Release $(tr -d '[:space:]' < VERSION)"
+git tag "v$(tr -d '[:space:]' < VERSION)"
+git push && git push --tags
+```
+
+Then create a GitHub Release for that tag (or use the UI). The `Publish to PyPI` workflow builds the wheel and uploads it.
+
+You can also run the workflow manually: **Actions → Publish to PyPI → Run workflow**.
+
+## Use in Pyodide
+
+```python
+import pyodide_js
+await pyodide_js.loadPackage([
+    "numpy", "pandas", "scipy", "matplotlib", "statsmodels",
+    "pillow", "pywavelets", "jinja2", "pyyaml", "pydantic",
+    "tqdm", "requests", "wordcloud", "networkx", "micropip",
+])
+
+import micropip
+await micropip.install([
+    "seaborn", "multimethod==1.12", "dacite", "filetype",
+    "typeguard", "imagehash==4.3.2", "visions==0.7.6", "attrs",
+    "fg-data-profiling-wasm",
+])
+
+import pandas as pd
+from data_profiling import ProfileReport
+
+df = pd.DataFrame({"a": [1, 2, 3], "b": ["x", "y", "x"]})
+report = ProfileReport(
+    df,
+    minimal=True,
+    progress_bar=False,
+    correlations={"phi_k": {"calculate": False}},
+    html={"minify_html": False},
+)
+html = report.to_html()
+```
+
+Helpers live in [`pyodide/install.py`](pyodide/install.py); dependency notes in [`pyodide/DEPS.md`](pyodide/DEPS.md).
+
+## Difficulty (recap)
+
+| Goal | Difficulty |
+|---|---|
+| Install this pure wheel in Pyodide | Easy |
+| Usable `ProfileReport` (core EDA, `minimal=True`) | Medium |
+| Full upstream fidelity (`phik`, minify, numba-shaped features) | Hard / skip |
+
+## Upstream
+
+Based on [Data-Centric-AI-Community/fg-data-profiling](https://github.com/Data-Centric-AI-Community/fg-data-profiling). Tracked commit is in `upstream.lock.json`. MIT-licensed; see `LICENSE`.

fg_data_profiling_wasm-0.1.0/README.md

@@ -0,0 +1,148 @@
+# fg-data-profiling-wasm
+
+Pyodide-friendly fork of [fg-data-profiling](https://github.com/Data-Centric-AI-Community/fg-data-profiling) (formerly ydata-profiling / pandas-profiling).
+
+**You do not compile this package to WASM.** Upstream already ships as a pure-Python wheel (`py2.py3-none-any`). This fork only does dependency surgery so it can install and run under Pyodide.
+
+## What changed vs upstream
+
+| Change | Why |
+|---|---|
+| Drop hard deps: `numba`, `minify-html`, `phik` | Native / JIT; broken or impractical in browser WASM |
+| Default `html.minify_html = False` | Avoid lazy-importing the Rust `minify-html` extension |
+| Soft-fail if minify is requested but missing | Safer in constrained environments |
+| Keep `phi_k` off (already upstream default) | Avoid needing `phik` |
+| Package name `fg-data-profiling-wasm` | Distinguish the Pyodide wheel from upstream |
+
+Optional native extras remain under `[project.optional-dependencies] native` for desktop use.
+
+## Layout
+
+```
+src/                  # vendored upstream + patches
+patches/              # Pyodide-friendly diffs reapplied on each sync
+scripts/sync-upstream.sh
+upstream.lock.json    # pinned upstream ref + commit
+pyodide/              # install helper + dependency matrix
+pyproject.toml        # Pyodide-friendly dependency set
+```
+
+## Upgrading from upstream
+
+Pinned upstream lives in [`upstream.lock.json`](upstream.lock.json).
+
+```bash
+# Is upstream ahead of our lock?
+make check-upstream
+# or: ./scripts/sync-upstream.sh --check
+
+# Pull latest develop (or whatever ref is in the lock), re-apply patches,
+# refresh dependency pins, update the lockfile
+make sync
+# or: ./scripts/sync-upstream.sh
+
+# Sync a release tag / other ref
+make sync-ref REF=v4.9.0
+# or: ./scripts/sync-upstream.sh --ref v4.9.0
+
+# After a successful sync, bump our PyPI version
+./scripts/sync-upstream.sh --bump patch
+
+# If a patch no longer applies: fix src/ by hand, then regenerate the patch series
+./scripts/sync-upstream.sh --regen-patches
+```
+
+Typical release flow after upstream moves:
+
+```bash
+./scripts/sync-upstream.sh --ref develop --bump patch
+python -m build
+# review git diff, commit, push, twine upload dist/*
+```
+
+A weekly GitHub Action (`.github/workflows/upstream-check.yml`) opens/comments on an issue when the lock is behind.
+
+## Build a wheel
+
+```bash
+python -m pip install build
+python -m build    # → dist/fg_data_profiling_wasm-*-py2.py3-none-any.whl
+```
+
+Current artifact:
+
+- `dist/fg_data_profiling_wasm-0.1.0-py2.py3-none-any.whl` (purelib; PyPI-compatible)
+
+## Publish to PyPI (GitHub Actions)
+
+The package is **not on PyPI yet**. Publishing is automated via [Trusted Publishing](https://docs.pypi.org/trusted-publishers/) (OIDC) — no long-lived API token in the repo.
+
+### One-time PyPI setup
+
+1. Sign in at https://pypi.org/
+2. Open **Publishing** → **Add a new pending publisher** (project does not exist yet):
+   - **PyPI project name:** `fg-data-profiling-wasm`
+   - **Owner:** `awesome-wasm-packages`
+   - **Repository:** `fg-data-profiling-wasm`
+   - **Workflow name:** `publish.yml`
+   - **Environment name:** `pypi`
+3. In GitHub → **Settings → Environments** → create environment `pypi` (optional protection rules / required reviewers).
+
+### Publish a version
+
+```bash
+# bump version in VERSION + pyproject.toml (or)
+./scripts/sync-upstream.sh --bump patch
+git add -A && git commit -m "Release $(tr -d '[:space:]' < VERSION)"
+git tag "v$(tr -d '[:space:]' < VERSION)"
+git push && git push --tags
+```
+
+Then create a GitHub Release for that tag (or use the UI). The `Publish to PyPI` workflow builds the wheel and uploads it.
+
+You can also run the workflow manually: **Actions → Publish to PyPI → Run workflow**.
+
+## Use in Pyodide
+
+```python
+import pyodide_js
+await pyodide_js.loadPackage([
+    "numpy", "pandas", "scipy", "matplotlib", "statsmodels",
+    "pillow", "pywavelets", "jinja2", "pyyaml", "pydantic",
+    "tqdm", "requests", "wordcloud", "networkx", "micropip",
+])
+
+import micropip
+await micropip.install([
+    "seaborn", "multimethod==1.12", "dacite", "filetype",
+    "typeguard", "imagehash==4.3.2", "visions==0.7.6", "attrs",
+    "fg-data-profiling-wasm",
+])
+
+import pandas as pd
+from data_profiling import ProfileReport
+
+df = pd.DataFrame({"a": [1, 2, 3], "b": ["x", "y", "x"]})
+report = ProfileReport(
+    df,
+    minimal=True,
+    progress_bar=False,
+    correlations={"phi_k": {"calculate": False}},
+    html={"minify_html": False},
+)
+html = report.to_html()
+```
+
+Helpers live in [`pyodide/install.py`](pyodide/install.py); dependency notes in [`pyodide/DEPS.md`](pyodide/DEPS.md).
+
+## Difficulty (recap)
+
+| Goal | Difficulty |
+|---|---|
+| Install this pure wheel in Pyodide | Easy |
+| Usable `ProfileReport` (core EDA, `minimal=True`) | Medium |
+| Full upstream fidelity (`phik`, minify, numba-shaped features) | Hard / skip |
+
+## Upstream
+
+Based on [Data-Centric-AI-Community/fg-data-profiling](https://github.com/Data-Centric-AI-Community/fg-data-profiling). Tracked commit is in `upstream.lock.json`. MIT-licensed; see `LICENSE`.

fg_data_profiling_wasm-0.1.0/VERSION

@@ -0,0 +1 @@
+0.1.0

fg_data_profiling_wasm-0.1.0/pyproject.toml

@@ -0,0 +1,93 @@
+[build-system]
+build-backend = "setuptools.build_meta"
+requires = [
+    "setuptools>=72.0.0,<81.0.0",
+    "wheel>=0.38.4,<1.0.0",
+]
+
+[project]
+name = "fg-data-profiling-wasm"
+version = "0.1.0"
+requires-python = ">=3.10,<3.14"
+authors = [
+    { name = "awesome-wasm-packages" },
+]
+maintainers = [
+    { name = "awesome-wasm-packages" },
+]
+description = "Pyodide-friendly fork of fg-data-profiling (ydata-profiling) for browser WASM"
+keywords = ["pandas", "profiling", "pyodide", "wasm", "eda"]
+readme = "README.md"
+license = "MIT"
+license-files = ["LICENSE"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering",
+]
+
+# Core deps synced from upstream via ./scripts/sync-upstream.sh
+# (drops numba / minify-html / phik — see native extra).
+# >>> upstream-deps:start
+dependencies = [
+    "scipy>=1.8, <1.17",
+    "pandas>1.5, <3.0, !=1.4.0",
+    "matplotlib>=3.5, <=3.10",
+    "pydantic>=2, <3",
+    "PyYAML>=6.0.3, <6.1",
+    "jinja2>=3.1.6, <3.2",
+    "visions[type_image_path]>=0.7.5, <0.8.2",
+    "numpy>=1.22,<2.4",
+    "filetype>=1.0.0",
+    "requests>=2.32.0, <3",
+    "tqdm>=4.66.3, <5",
+    "seaborn>=0.10.1, <0.14",
+    "multimethod>=1.4, <2",
+    "statsmodels>=0.13.2, <1",
+    "typeguard>=4, <5",
+    "imagehash==4.3.2",
+    "wordcloud>=1.9.4",
+    "dacite>=1.9, <2",
+]
+# <<< upstream-deps:end
+
+[project.optional-dependencies]
+# Native extras — not expected to work in the browser
+# >>> upstream-native:start
+native = [
+    "minify-html>=0.15.0",
+    "phik>=0.12.5, <0.13",
+    "numba>=0.60,<0.63",
+]
+# <<< upstream-native:end
+
+[project.urls]
+Homepage = "https://github.com/awesome-wasm-packages/fg-data-profiling-wasm"
+Upstream = "https://github.com/Data-Centric-AI-Community/fg-data-profiling"
+
+[project.scripts]
+data_profiling = "data_profiling.controller.console:main"
+pandas_profiling = "data_profiling.controller.console:main"
+
+[tool.setuptools]
+include-package-data = true
+
+[tool.setuptools.package-data]
+data_profiling = ["py.typed", "*.yaml"]
+
+[tool.distutils.bdist_wheel]
+universal = true
+
+[tool.setuptools.package-dir]
+"" = "src"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+include = ["data_profiling*", "ydata_profiling*"]

fg_data_profiling_wasm-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

fg_data_profiling_wasm-0.1.0/setup.py

@@ -0,0 +1,4 @@
+from setuptools import setup
+
+# Metadata lives in pyproject.toml; this file keeps editable/legacy install paths working.
+setup()

fg_data_profiling_wasm-0.1.0/src/data_profiling/__init__.py

@@ -0,0 +1,34 @@
+"""Main module of data-profiling.
+
+.. include:: ../../README.md
+"""
+# ignore numba warnings
+import warnings  # isort:skip # noqa
+
+import importlib.util  # isort:skip # noqa
+from warnings import warn
+
+from data_profiling.compare_reports import compare  # isort:skip # noqa
+from data_profiling.controller import pandas_decorator  # isort:skip # noqa
+from data_profiling.profile_report import ProfileReport  # isort:skip # noqa
+from data_profiling.version import __version__  # isort:skip # noqa
+
+# backend
+import data_profiling.model.pandas  # isort:skip  # noqa
+
+spec = importlib.util.find_spec("pyspark")
+if spec is not None:
+    import data_profiling.model.spark  # isort:skip  # noqa
+
+spec_numba = importlib.util.find_spec("numba")
+if spec_numba is not None:
+    from numba.core.errors import NumbaDeprecationWarning  # isort:skip # noqa
+
+    warnings.simplefilter("ignore", category=NumbaDeprecationWarning)
+
+__all__ = [
+    "pandas_decorator",
+    "ProfileReport",
+    "__version__",
+    "compare",
+]