online demo of skrub TableReport

skrub-data · Aug 1, 2024 · eb8e1fd · eb8e1fd
commit eb8e1fd
Show file tree

Hide file tree

Showing 17 changed files with 2,021 additions and 0 deletions.
diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
@@ -0,0 +1,34 @@
+name: build
+
+permissions:
+  contents: write
+
+on:
+  push:
+    branches:
+    - main
+
+jobs:
+  build-and-deploy:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+
+    - name: Set up Python 3.11
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.11'
+
+    - name: Install dependencies
+      run: |
+        pip install $(realpath "./skrub.whl")
+
+    - name: Build the site
+      run: |
+        python build.py
+
+    - name: GitHub Pages action
+      uses: peaceiris/[email protected]
+      with:
+        github_token: ${{ secrets.GITHUB_TOKEN }}
+        publish_dir: _build
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1 @@
+_build/
diff --git a/LICENSE b/LICENSE
@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Jérôme Dockès
+
+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.
diff --git a/_includes/example-report.html b/_includes/example-report.html
@@ -0,0 +1,30 @@
+<!DOCTYPE html>
+<html>
+
+<head>
+    <meta charset="utf-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <title>skrub example report</title>
+    <link rel="stylesheet"
+        href="https://cdn.jsdelivr.net/npm/[email protected]/build/pure-min.css"
+        integrity="sha384-X38yfunGUhNzHpBaEBsWLO+A0HDYOQi8ufWDkZ0k9e0eXz/tH3II7uKZ9msv++Ls"
+        crossorigin="anonymous">
+    <style>
+     {% include "skrub-online-report.css" %}
+    </style>
+    <link rel="icon" href="../skrub.svg">
+</head>
+
+<body class="color-links">
+    {% include "nav.html" %}
+
+    {% include "small-banner.html" %}
+
+    <main>
+        <div>
+            {{ report | safe }}
+        </div>
+    </main>
+</body>
+
+</html>
diff --git a/_includes/examples-index.html b/_includes/examples-index.html
@@ -0,0 +1,39 @@
+<!doctype html>
+<html>
+
+<head>
+    <meta charset="utf-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <title>skrub reports</title>
+    <link rel="stylesheet"
+        href="https://cdn.jsdelivr.net/npm/[email protected]/build/pure-min.css"
+        integrity="sha384-X38yfunGUhNzHpBaEBsWLO+A0HDYOQi8ufWDkZ0k9e0eXz/tH3II7uKZ9msv++Ls"
+        crossorigin="anonymous">
+    <style>
+     {% include "skrub-online-report.css" %}
+    </style>
+    <link rel="icon" href="../skrub.svg">
+</head>
+
+<body class="color-links">
+    {% include "nav.html" %}
+
+    {% include "small-banner.html" %}
+
+    <main>
+        <p class="narrow-wrapper">
+            Follow one of the links below to see a report computed with
+            <a href="https://skrub-data.org/dev/reference/generated/skrub.TableReport.html#" class="table-report"><code>skrub.TableReport</code></a>
+            for the corresponding dataset.
+        </p>
+        <ul class="examples-index example-dataset-list">
+            {% for report_name in report_names %}
+            <li>
+                <a href="{{ report_name }}.html">{{ report_name.replace('_', ' ').capitalize() }}</a>
+            </li>
+            {% endfor %}
+        </ul>
+    </main>
+</body>
+
+</html>
diff --git a/_includes/nav.html b/_includes/nav.html
@@ -0,0 +1,14 @@
+<nav>
+    <ul class="nav">
+        {% for name, href in nav_links %}
+        <li>
+            <a
+                href={{ href | relative }}
+                {% if href == current_page %}
+                class="current-page"
+                {% endif %}
+            >{{ name }}</a>
+        </li>
+        {% endfor %}
+    </ul>
+</nav>
diff --git a/_includes/small-banner.html b/_includes/small-banner.html
@@ -0,0 +1,5 @@
+<div class="small-banner flex padding">
+    <a href="https://skrub-data.org/"><img class="skrub" src="../skrub.svg"></a>
+    <a href="https://skrub-data.org/dev/reference/generated/skrub.TableReport.html#"
+       class="table-report"><code>skrub.TableReport</code></a>
+</div>
diff --git a/build.py b/build.py
@@ -0,0 +1,152 @@
+#! /usr/bin/env python
+
+import argparse
+from pathlib import Path
+import shutil
+import re
+import secrets
+import time
+
+import jinja2
+import pandas as pd
+from skrub import datasets as skrub_data
+from sklearn import datasets as sklearn_data
+from skrub import TableReport
+
+
+NAV_LINKS = [("Demo", "index.html"), ("Examples", "examples/index.html")]
+
+
+def write(text, path):
+    path.write_text(bust(text), encoding="utf-8")
+
+
+@jinja2.pass_context
+def relative(context, path):
+    current_page = context["current_page"]
+    depth = len(current_page.split("/")) - 1
+    parts = [".."] * depth + path.split("/")
+    return "/".join(parts)
+
+
+def get_jinja_env():
+    env = jinja2.Environment(
+        loader=jinja2.FileSystemLoader(
+            [REPO, REPO / "_includes"],
+            encoding="UTF-8",
+        ),
+        autoescape=True,
+    )
+    env.filters["relative"] = relative
+    env.globals = {
+        "nav_links": NAV_LINKS,
+    }
+    return env
+
+
+def bust(text):
+    return re.sub(r"\?__skrub_[a-zA-Z0-9]+__", f"?__skrub_{VERSION}__", text)
+
+
+def get_datasets():
+    AMES_HOUSING_CSV = (
+        "https://www.openml.org/data/get_csv/20649135/file2ed11cebe25.arff"
+    )
+    datasets = [("AMES Housing", (lambda: pd.read_csv(AMES_HOUSING_CSV)))]
+    skrub_dataset_names = [
+        "employee_salaries",
+        "medical_charge",
+        "traffic_violations",
+        "drug_directory",
+    ]
+    for name in skrub_dataset_names:
+
+        def fetch(name=name):
+            return getattr(skrub_data, f"fetch_{name}")().X
+
+        datasets.append((name, fetch))
+    sklearn_dataset_names = ["titanic"]
+    for name in sklearn_dataset_names:
+
+        def fetch(name=name):
+            return sklearn_data.fetch_openml(
+                name, as_frame=True, parser="auto", version=1
+            ).frame
+
+        datasets.append((name, fetch))
+    return datasets
+
+
+def add_report(name, fetcher):
+    if ARGS.no_reports:
+        html = '<div class="report-placeholder">report</div>'
+        elapsed = 0
+    else:
+        df = fetcher()
+        print(f"making report for {name}")
+        pretty_name = name.replace("_", " ").capitalize()
+        start = time.time()
+        html = TableReport(df, title=pretty_name).html_snippet()
+        elapsed = time.time() - start
+        print(f"{name} took {elapsed:.2f}s")
+    report_template = ENV.get_template("example-report.html")
+    current_page = f"examples/{name}.html"
+    html = report_template.render(
+        nav_links=NAV_LINKS + [(name, current_page)],
+        current_page=current_page,
+        report=html,
+        time=elapsed,
+    )
+    write(html, EXAMPLES_DIR / f"{name}.html")
+
+
+def build_examples():
+    datasets = get_datasets()
+    for name, fetcher in datasets:
+        add_report(name, fetcher)
+
+    examples_index = ENV.get_template("examples-index.html")
+    html = examples_index.render(
+        report_names=[name for name, _ in datasets], current_page="examples/index.html"
+    )
+    write(html, EXAMPLES_DIR / "index.html")
+
+
+def build_pages():
+    all_pages = REPO.glob("*.html")
+    for page in all_pages:
+        template = ENV.get_template(page.name)
+        rendered = template.render(current_page=f"{page.name}")
+        write(rendered, BUILD_DIR / page.name)
+
+    for ext in ["css", "js", "svg"]:
+        for file_path in REPO.glob(f"*.{ext}"):
+            text = file_path.read_text("utf-8")
+            write(text, BUILD_DIR / file_path.name)
+
+    for asset in REPO.glob(f"*.whl"):
+        shutil.copyfile(asset, BUILD_DIR / asset.name)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--no_reports", help="skip building example reports", action="store_true"
+    )
+    ARGS = parser.parse_args()
+
+    REPO = Path(__file__).parent.resolve()
+    BUILD_DIR = REPO / "_build"
+    if BUILD_DIR.is_dir():
+        shutil.rmtree(BUILD_DIR)
+    BUILD_DIR.mkdir()
+
+    EXAMPLES_DIR = BUILD_DIR / "examples"
+    EXAMPLES_DIR.mkdir()
+
+    VERSION = secrets.token_hex()[:4]
+
+    ENV = get_jinja_env()
+
+    build_pages()
+    build_examples()
diff --git a/clevercsv-0.8.2-cp312-cp312-pyodide_2024_0_wasm32.whl b/clevercsv-0.8.2-cp312-cp312-pyodide_2024_0_wasm32.whl