Visualizaciones/pygwalker_visualizaciones.py

import marimo

__generated_with = "0.15.2"
app = marimo.App(width="medium")


@app.cell
def _():
    # Cell 1 — Imports y utilidades
    import marimo as mo

    return (mo,)


@app.cell
def _(mo):
    mo.md(r"""# PyGWalker: EDA rapido e interactivo con pygwalker""")
    return


@app.cell
def _():
    import os
    import pandas as pd
    import numpy as np
    import altair as alt
    import pygwalker as pyg
    from typing import Dict


    try:
        from vega_datasets import data as vega_data
    except Exception:
        vega_data = None


    DATASET_URLS: Dict[str, str] = {
        "Bike Sharing (DC)": "https://kanaries-app.s3.ap-northeast-1.amazonaws.com/public-datasets/bike_sharing_dc.csv",
    }
    return DATASET_URLS, pd, pyg, vega_data


@app.cell
def _(mo):
    options = [
        "cars",
        "iris",
        "seattle-weather",
        "stocks",
        "Bike Sharing (DC)",
    ]

    dataset_selector = mo.ui.dropdown(options=options, value="cars", label="Dataset")
    sample_toggle = mo.ui.checkbox(label="Muestrear filas", value=False)
    sample_size = mo.ui.number(value=1000, label="Filas a tomar")
    dark_mode = mo.ui.radio(options=["media", "light", "dark"], value="media", label="Tema")
    spec_path_input = mo.ui.text(value="", label="Ruta de spec (opcional)", full_width=True)

    mo.vstack([
        mo.md("## 1) Selecciona un dataset y preferencias"),
        mo.hstack([dataset_selector, sample_toggle, sample_size]),
        mo.hstack([dark_mode]),
        spec_path_input,
    ])
    return (
        dark_mode,
        dataset_selector,
        sample_size,
        sample_toggle,
        spec_path_input,
    )


@app.cell
def _(
    dark_mode,
    dataset_selector,
    sample_size,
    sample_toggle,
    spec_path_input,
):
    selected_name = dataset_selector.value
    use_sample = sample_toggle.value
    sample_n = sample_size.value
    selected_theme = dark_mode.value
    spec_path_val = spec_path_input.value.strip()
    return sample_n, selected_name, selected_theme, spec_path_val, use_sample


@app.cell
def _(
    DATASET_URLS: "Dict[str, str]",
    pd,
    sample_n,
    selected_name,
    use_sample,
    vega_data,
):
    def _load_dataset(name: str) -> pd.DataFrame:
        if name == "Bike Sharing (DC)":
            return pd.read_csv(DATASET_URLS["Bike Sharing (DC)"], parse_dates=["date"])
        if name == "cars":
            if vega_data is not None:
                return vega_data.cars()
            return pd.read_json("https://raw.githubusercontent.com/vega/vega-datasets/master/data/cars.json")
        if name == "iris":
            if vega_data is not None:
                return vega_data.iris()
            return pd.read_csv("https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv")
        if name == "seattle-weather":
            if vega_data is not None:
                return vega_data.seattle_weather()
            return pd.read_csv(
                "https://raw.githubusercontent.com/vega/vega-datasets/master/data/seattle-weather.csv",
                parse_dates=["date"],
            )
        if name == "stocks":
            if vega_data is not None:
                return vega_data.stocks()
            return pd.read_csv(
                "https://raw.githubusercontent.com/vega/vega-datasets/master/data/stocks.csv",
                parse_dates=["date"],
            )
        return pd.DataFrame()

    _df_raw = _load_dataset(selected_name)

    if use_sample and isinstance(sample_n, (int, float)) and sample_n > 0:
        _n = int(sample_n)
        df = _df_raw.sample(n=min(_n, len(_df_raw)), random_state=42).reset_index(drop=True)
    else:
        df = _df_raw

    df
    return (df,)


@app.cell
def _(df, mo):
    explorer = mo.ui.data_explorer(df)
    explorer
    return


@app.cell
def _(df, mo, pyg, selected_theme, spec_path_val):
    _gw_gid = "gwalker-main"
    _html = pyg.to_html(
        df,
        gid=_gw_gid,
        dark=selected_theme,
        spec=spec_path_val if spec_path_val != "" else "",
    )

    mo.Html(_html)
    return


if __name__ == "__main__":
    app.run()