Update app.py

app.py

@@ -1,469 +1,251 @@
 import marimo
 
-__generated_with = "0.9.2"
+__generated_with = "0.12.8"
 app = marimo.App()
 
 
-@app.cell
-def __():
-    import marimo as mo
-
-    mo.md("# Welcome to marimo! 🌊🍃")
-    return (mo,)
-
-
-@app.cell
-def __(mo):
-    slider = mo.ui.slider(1, 22)
-    return (slider,)
-
-
-@app.cell
-def __(mo, slider):
-    mo.md(
-        f"""
-        marimo is a **reactive** Python notebook.
-
-        This means that unlike traditional notebooks, marimo notebooks **run
-        automatically** when you modify them or
-        interact with UI elements, like this slider: {slider}.
-
-        {"##" + "🍃" * slider.value}
-        """
-    )
-    return
-
-
-@app.cell(hide_code=True)
-def __(mo):
-    mo.accordion(
-        {
-            "Tip: disabling automatic execution": mo.md(
-                rf"""
-            marimo lets you disable automatic execution: just go into the
-            notebook settings and set
-
-            "Runtime > On Cell Change" to "lazy".
-
-            When the runtime is lazy, after running a cell, marimo marks its
-            descendants as stale instead of automatically running them. The
-            lazy runtime puts you in control over when cells are run, while
-            still giving guarantees about the notebook state.
-            """
-            )
-        }
-    )
-    return
-
-
 @app.cell(hide_code=True)
-def __(mo):
+def _(mo):
     mo.md(
-        """
-        Tip: This is a tutorial notebook. You can create your own notebooks
-        by entering `marimo edit` at the command line.
-        """
-    ).callout()
-    return
-
-
-@app.cell(hide_code=True)
-def __(mo):
-    mo.md(
-        """
-        ## 1. Reactive execution
+        r"""
+        ## Face Embeddings of World Leaders
 
-        A marimo notebook is made up of small blocks of Python code called
-        cells.
+        This notebook explores face embeddings using a subset of the **Labeled Faces in the Wild** dataset, focused on public figures. We'll use standard Python and scikit-learn libraries to load the data, embed images, reduce dimensionality, and visualize clustering behavior.
 
-        marimo reads your cells and models the dependencies among them: whenever
-        a cell that defines a global variable  is run, marimo
-        **automatically runs** all cells that reference that variable.
+        This example builds on a demo from the Marimo gallery using the MNIST dataset. Here, we adapt it to work with a facial recognition dataset of public figures. While facial recognition has limited responsible use cases, this curated subset includes only world leaders — a group I feel comfortable experimenting with in a technical context.
 
-        Reactivity keeps your program state and outputs in sync with your code,
-        making for a dynamic programming environment that prevents bugs before they
-        happen.
+        We'll start with our imports:
         """
     )
     return
 
 
-@app.cell(hide_code=True)
-def __(changed, mo):
-    (
-        mo.md(
-            f"""
-            **✨ Nice!** The value of `changed` is now {changed}.
-
-            When you updated the value of the variable `changed`, marimo
-            **reacted** by running this cell automatically, because this cell
-            references the global variable `changed`.
-
-            Reactivity ensures that your notebook state is always
-            consistent, which is crucial for doing good science; it's also what
-            enables marimo notebooks to double as tools and  apps.
-            """
-        )
-        if changed
-        else mo.md(
-            """
-            **🌊 See it in action.** In the next cell, change the value of the
-            variable  `changed` to `True`, then click the run button.
-            """
-        )
-    )
-    return
-
-
 @app.cell
-def __():
-    changed = False
-    return (changed,)
-
-
-@app.cell(hide_code=True)
-def __(mo):
-    mo.accordion(
-        {
-            "Tip: execution order": (
-                """
-                The order of cells on the page has no bearing on
-                the order in which cells are executed: marimo knows that a cell
-                reading a variable must run after the cell that  defines it. This
-                frees you to organize your code in the way that makes the most
-                sense for you.
-                """
-            )
-        }
+def _():
+    from time import time
+
+    import matplotlib.pyplot as plt
+    from scipy.stats import loguniform
+
+    from sklearn.datasets import fetch_lfw_people
+    from sklearn.decomposition import PCA
+    from sklearn.metrics import ConfusionMatrixDisplay, classification_report
+    from sklearn.model_selection import RandomizedSearchCV, train_test_split
+    from sklearn.preprocessing import StandardScaler
+    from sklearn.svm import SVC
+    return (
+        ConfusionMatrixDisplay,
+        PCA,
+        RandomizedSearchCV,
+        SVC,
+        StandardScaler,
+        classification_report,
+        fetch_lfw_people,
+        loguniform,
+        plt,
+        time,
+        train_test_split,
     )
-    return
 
 
 @app.cell(hide_code=True)
-def __(mo):
-    mo.md(
-        """
-        **Global names must be unique.** To enable reactivity, marimo imposes a
-        constraint on how names appear in cells: no two cells may define the same
-        variable.
-        """
-    )
+def _(mo):
+    mo.md(r"""We're using `fetch_lfw_people` from `sklearn.datasets` to load a curated subset of the LFW dataset — restricted to individuals with at least 70 images, resulting in 7 distinct people and just over 1,200 samples. These happen to be mostly world leaders, which makes the demo both manageable and fun to explore.""")
     return
 
 
-@app.cell(hide_code=True)
-def __(mo):
-    mo.accordion(
-        {
-            "Tip: encapsulation": (
-                """
-                By encapsulating logic in functions, classes, or Python modules,
-                you can minimize the number of global variables in your notebook.
-                """
-            )
-        }
+@app.cell
+def _(fetch_lfw_people):
+    lfw_people = fetch_lfw_people(min_faces_per_person=70, resize=0.4)
+
+    # introspect the images arrays to find the shapes (for plotting)
+    n_samples, h, w = lfw_people.images.shape
+
+    # for machine learning we use the 2 data directly (as relative pixel
+    # positions info is ignored by this model)
+    X = lfw_people.data
+    n_features = X.shape[1]
+
+    # the label to predict is the id of the person
+    Y = lfw_people.target
+    target_names = lfw_people.target_names
+    n_classes = target_names.shape[0]
+
+    print("Total dataset size:")
+    print("n_samples: %d" % n_samples)
+    print("n_features: %d" % n_features)
+    print("n_classes: %d" % n_classes)
+    return (
+        X,
+        Y,
+        h,
+        lfw_people,
+        n_classes,
+        n_features,
+        n_samples,
+        target_names,
+        w,
     )
-    return
 
 
 @app.cell(hide_code=True)
-def __(mo):
-    mo.accordion(
-        {
-            "Tip: private variables": (
-                """
-                Variables prefixed with an underscore are "private" to a cell, so
-                they can be defined by multiple cells.
-                """
-            )
-        }
-    )
+def _(mo):
+    mo.md(r"""Next, we embed each face image using a pre-trained FaceNet model (`InceptionResnetV1` trained on `vggface2`). This converts each image into a 512-dimensional vector. Since the original data is grayscale and flattened, we reshape, normalize, and convert it to RGB before feeding it through the model.""")
     return
 
 
-@app.cell(hide_code=True)
-def __(mo):
-    mo.md(
-        """
-        ## 2. UI elements
-
-        Cells can output interactive UI elements. Interacting with a UI
-        element **automatically triggers notebook execution**: when
-        you interact with a UI element, its value is sent back to Python, and
-        every cell that references that element is re-run.
-
-        marimo provides a library of UI elements to choose from under
-        `marimo.ui`.
-        """
+@app.cell
+def _(X, h, w):
+    from facenet_pytorch import InceptionResnetV1
+    from torchvision import transforms
+    from PIL import Image
+    import torch
+    import numpy as np
+
+    # Load FaceNet model
+    model = InceptionResnetV1(pretrained='vggface2').eval()
+
+    # Transform pipeline: grayscale → RGB → resize → normalize
+    transform = transforms.Compose([
+        transforms.Resize((160, 160)),
+        transforms.ToTensor(),
+        transforms.Lambda(lambda x: x.repeat(3, 1, 1) if x.shape[0] == 1 else x),
+        transforms.Normalize([0.5], [0.5])
+    ])
+
+    # Embed a single flattened row from X
+    def embed_flat_row(flat):
+        img = flat.reshape(h, w)
+        img = (img * 255).astype(np.uint8)
+        pil = Image.fromarray(img).convert("L")  # grayscale
+        tensor = transform(pil).unsqueeze(0)
+        with torch.no_grad():
+            return model(tensor).squeeze().numpy()  # 512-dim
+
+    # Generate embeddings for all samples
+    embeddings = np.array([embed_flat_row(row) for row in X])
+    return (
+        Image,
+        InceptionResnetV1,
+        embed_flat_row,
+        embeddings,
+        model,
+        np,
+        torch,
+        transform,
+        transforms,
     )
-    return
 
 
 @app.cell
-def __(mo):
-    mo.md("""**🌊 Some UI elements.** Try interacting with the below elements.""")
+def _(mo):
+    mo.md(r"""Now that we have 512-dimensional embeddings, we reduce them to 2D for visualization. Both t-SNE and UMAP are available here — UMAP is active by default, but you can switch to t-SNE by uncommenting the alternate line. This step lets us inspect the structure of the embedding space:""")
     return
 
 
 @app.cell
-def __(mo):
-    icon = mo.ui.dropdown(["🍃", "🌊", "✨"], value="🍃")
-    return (icon,)
-
+def _(embeddings):
+    from sklearn.manifold import TSNE
+    import umap.umap_ as umap
 
-@app.cell
-def __(icon, mo):
-    repetitions = mo.ui.slider(1, 16, label=f"number of {icon.value}: ")
-    return (repetitions,)
+    # X_embedded = TSNE(n_components=2, perplexity=30, random_state=42).fit_transform(embeddings)
+    X_embedded = umap.UMAP(n_components=2, random_state=42).fit_transform(embeddings)
+    return TSNE, X_embedded, umap
 
 
 @app.cell
-def __(icon, repetitions):
-    icon, repetitions
+def _(mo):
+    mo.md(r"""We wrap the 2D embeddings into a Pandas DataFrame for easier manipulation and plotting. Each row includes x/y coordinates and the associated person ID, which we map to names. We then define a simple Altair scatterplot function to visualize the clustered embeddings by identity.""")
     return
 
 
 @app.cell
-def __(icon, mo, repetitions):
-    mo.md("# " + icon.value * repetitions.value)
-    return
-
-
-@app.cell(hide_code=True)
-def __(mo):
-    mo.md(
-        """
-        ## 3. marimo is just Python
+def _(X_embedded, Y, target_names):
+    import pandas as pd
 
-        marimo cells parse Python (and only Python), and marimo notebooks are
-        stored as pure Python files — outputs are _not_ included. There's no
-        magical syntax.
+    embedding_df = pd.DataFrame({
+        "x": X_embedded[:, 0],
+        "y": X_embedded[:, 1],
+        "person": Y
+    }).reset_index()
+    embedding_df["name"] = embedding_df["person"].map(lambda i: target_names[i])
+    return embedding_df, pd
 
-        The Python files generated by marimo are:
 
-        - easily versioned with git, yielding minimal diffs
-        - legible for both humans and machines
-        - formattable using your tool of choice,
-        - usable as Python  scripts, with UI  elements taking their default
-        values, and
-        - importable by other modules (more on that in the future).
-        """
-    )
-    return
+@app.cell
+def _():
+    import altair as alt
+    def scatter(df):
+        return (alt.Chart(df)
+        .mark_circle()
+        .encode(
+            x=alt.X("x:Q"),
+            y=alt.Y("y:Q"),
+            color=alt.Color("name:N"),
+        ).properties(width=500, height=300))
+    return alt, scatter
 
 
 @app.cell(hide_code=True)
-def __(mo):
-    mo.md(
-        """
-        ## 4. Running notebooks as apps
-
-        marimo notebooks can double as apps. Click the app window icon in the
-        bottom-right to see this notebook in "app view."
-
-        Serve a notebook as an app with `marimo run` at the command-line.
-        Of course, you can use marimo just to level-up your
-        notebooking, without ever making apps.
-        """
-    )
+def _(mo):
+    mo.md(r"""Here's our 2D embedding space of world leader faces! Each point is a facial embedding projected with UMAP and colored by identity. Try selecting a cluster — the notebook will automatically reveal the associated images so you can explore what the model “thinks” belongs together.""")
     return
 
 
-@app.cell(hide_code=True)
-def __(mo):
-    mo.md(
-        """
-        ## 5. The `marimo` command-line tool
-
-        **Creating and editing notebooks.** Use
-
-        ```
-        marimo edit
-        ```
-
-        in a terminal to start the marimo notebook server. From here
-        you can create a new notebook or edit existing ones.
-
-
-        **Running as apps.** Use
-
-        ```
-        marimo run notebook.py
-        ```
-
-        to start a webserver that serves your notebook as an app in read-only mode,
-        with code cells hidden.
-
-        **Convert a Jupyter notebook.** Convert a Jupyter notebook to a marimo
-        notebook using `marimo convert`:
-
-        ```
-        marimo convert your_notebook.ipynb > your_app.py
-        ```
-
-        **Tutorials.** marimo comes packaged with tutorials:
-
-        - `dataflow`: more on marimo's automatic execution
-        - `ui`: how to use UI elements
-        - `markdown`: how to write markdown, with interpolated values and
-           LaTeX
-        - `plots`: how plotting works in marimo
-        - `sql`: how to use SQL
-        - `layout`: layout elements in marimo
-        - `fileformat`: how marimo's file format works
-        - `markdown-format`: for using `.md` files in marimo
-        - `for-jupyter-users`: if you are coming from Jupyter
-
-        Start a tutorial with `marimo tutorial`; for example,
-
-        ```
-        marimo tutorial dataflow
-        ```
-
-        In addition to tutorials, we have examples in our
-        [our GitHub repo](https://www.github.com/marimo-team/marimo/tree/main/examples).
-        """
-    )
-    return
+@app.cell
+def _(embedding_df, scatter):
+    import marimo as mo
+    chart = mo.ui.altair_chart(scatter(embedding_df))
+    return chart, mo
 
 
 @app.cell(hide_code=True)
-def __(mo):
-    mo.md(
-        """
-        ## 6. The marimo editor
-
-        Here are some tips to help you get started with the marimo editor.
-        """
-    )
+def _(mo):
+    mo.md(r"""When you select points in the scatterplot, Marimo automatically passes those indices into this cell. Here, we render a preview of the corresponding face images using `matplotlib`, along with a table of all selected metadata — making it easy to inspect clustering quality or outliers at a glance.""")
     return
 
 
 @app.cell
-def __(mo, tips):
-    mo.accordion(tips)
-    return
+def _(chart, mo):
+    table = mo.ui.table(chart.value)
+    return (table,)
 
 
-@app.cell(hide_code=True)
-def __(mo):
-    mo.md("""## Finally, a fun fact""")
-    return
-
+@app.cell
+def _(X, chart, h, mo, table, w):
+    def show_images(indices, max_images=6):
+        import matplotlib.pyplot as plt
+
+        indices = indices[:max_images]
+        images = X.reshape((-1, h, w))[indices]
+        fig, axes = plt.subplots(1, len(indices))
+        fig.set_size_inches(12.5, 1.5)
+        if len(indices) > 1:
+            for im, ax in zip(images, axes.flat):
+                ax.imshow(im, cmap="gray")
+                ax.set_yticks([])
+                ax.set_xticks([])
+        else:
+            axes.imshow(images[0], cmap="gray")
+            axes.set_yticks([])
+            axes.set_xticks([])
+        plt.tight_layout()
+        return fig
+
+    def show_selected():
+        return (
+            show_images(list(chart.value["index"]))
+            if not len(table.value)
+            else show_images(list(table.value["index"]))
+        )
 
-@app.cell(hide_code=True)
-def __(mo):
-    mo.md(
-        """
-        The name "marimo" is a reference to a type of algae that, under
-        the right conditions, clumps together to form a small sphere
-        called a "marimo moss ball". Made of just strands of algae, these
-        beloved assemblages are greater than the sum of their parts.
-        """
-    )
-    return
+    mo.hstack([chart, show_selected() if len(chart.value) else ""])
+    return show_images, show_selected
 
 
-@app.cell(hide_code=True)
-def __():
-    tips = {
-        "Saving": (
-            """
-            **Saving**
-
-            - _Name_ your app using the box at the top of the screen, or
-              with `Ctrl/Cmd+s`. You can also create a named app at the
-              command line, e.g., `marimo edit app_name.py`.
-
-            - _Save_ by clicking the save icon on the bottom right, or by
-              inputting `Ctrl/Cmd+s`. By default marimo is configured
-              to autosave.
-            """
-        ),
-        "Running": (
-            """
-            1. _Run a cell_ by clicking the play ( ▷ ) button on the top
-            right of a cell, or by inputting `Ctrl/Cmd+Enter`.
-
-            2. _Run a stale cell_  by clicking the yellow run button on the
-            right of the cell, or by inputting `Ctrl/Cmd+Enter`. A cell is
-            stale when its code has been modified but not run.
-
-            3. _Run all stale cells_ by clicking the play ( ▷ ) button on
-            the bottom right of the screen, or input `Ctrl/Cmd+Shift+r`.
-            """
-        ),
-        "Console Output": (
-            """
-            Console output (e.g., `print()` statements) is shown below a
-            cell.
-            """
-        ),
-        "Creating, Moving, and Deleting Cells": (
-            """
-            1. _Create_ a new cell above or below a given one by clicking
-                the plus button to the left of the cell, which appears on
-                mouse hover.
-
-            2. _Move_ a cell up or down by dragging on the handle to the 
-                right of the cell, which appears on mouse hover.
-
-            3. _Delete_ a cell by clicking the trash bin icon. Bring it
-                back by clicking the undo button on the bottom right of the
-                screen, or with `Ctrl/Cmd+Shift+z`.
-            """
-        ),
-        "Disabling Automatic Execution": (
-            """
-            Via the notebook settings (gear icon) or footer panel, you
-            can disable automatic execution. This is helpful when
-            working with expensive notebooks or notebooks that have
-            side-effects like database transactions.
-            """
-        ),
-        "Disabling Cells": (
-            """
-            You can disable a cell via the cell context menu.
-            marimo will never run a disabled cell or any cells that depend on it.
-            This can help prevent accidental execution of expensive computations
-            when editing a notebook.
-            """
-        ),
-        "Code Folding": (
-            """
-            You can collapse or fold the code in a cell by clicking the arrow
-            icons in the line number column to the left, or by using keyboard
-            shortcuts.
-
-            Use the command palette (`Ctrl/Cmd+k`) or a keyboard shortcut to
-            quickly fold or unfold all cells.
-            """
-        ),
-        "Code Formatting": (
-            """
-            If you have [ruff](https://github.com/astral-sh/ruff) installed,
-            you can format a cell with the keyboard shortcut `Ctrl/Cmd+b`.
-            """
-        ),
-        "Command Palette": (
-            """
-            Use `Ctrl/Cmd+k` to open the command palette.
-            """
-        ),
-        "Keyboard Shortcuts": (
-            """
-            Open the notebook menu (top-right) or input `Ctrl/Cmd+Shift+h` to
-            view a list of all keyboard shortcuts.
-            """
-        ),
-        "Configuration": (
-            """
-           Configure the editor by clicking the gears icon near the top-right
-           of the screen.
-           """
-        ),
-    }
-    return (tips,)
+@app.cell
+def _():
+    return
 
 
 if __name__ == "__main__":