app.py

import marimo

__generated_with = "0.11.4"
app = marimo.App(width="medium")


@app.cell(hide_code=True)
def _(mo):
    mo.md(r"""# Diabetes Dataset Analysis""")
    return


@app.cell(hide_code=True)
def _():
    import marimo as mo
    import polars as pl
    return mo, pl


@app.cell(hide_code=True)
def _(mo):
    mo.accordion(
        {"Notes": """
    ## Dataset Column Notes

    > Only highlighted columns of interest 

    * Diabetes_binary: [ 0 (No diabetes) | 1 (Pre/diabetes) ]
    * HighBP: [ 0 (No High BP) | 1 (High BP) ]
    * HighChol: [ 0 (No High BP) | 1 (High BP) ]
    * Stroke: [ 0 (Never) | 1 (Had) ]
    * HeartDiseaseorAttack: [ 0 (No) | 1 (Yes) ]
    * Smoker: [ 0 (<100 cigs lifetime) | 1 (>100 cigs lifetime) 
    * HvyAlcohol: [ 0 (<14 🍺/week for men, <7 🍺/week for women) | 1 (otherwise) ]
        """}
    )
    return


@app.cell(hide_code=True)
def _(pl):
    dataset_raw = pl.read_csv("dataset/diabetes_binary_health_indicators_BRFSS2015.csv")
    dataset_prior_conditions = dataset_raw.select(["Diabetes_binary", "HighBP", "HighChol", "Stroke", "HeartDiseaseorAttack"])
    dataset_prior_conditions.head()
    return dataset_prior_conditions, dataset_raw


@app.cell
def _(mo):
    mo.md("""## Naive Bayes' Classifier""")
    return


@app.cell
def _(dataset_prior_conditions, mo, pl):
    from sklearn.naive_bayes import BernoulliNB
    from sklearn.model_selection import train_test_split
    from sklearn.metrics import accuracy_score, classification_report, confusion_matrix

    X_priors_NB, y_priors_NB = dataset_prior_conditions.select(pl.exclude("Diabetes_binary")), dataset_prior_conditions.select("Diabetes_binary")
    X_train_priors, X_test_priors, y_train_priors, y_test_priors = train_test_split(
        X_priors_NB, y_priors_NB, random_state=33, test_size=0.25
    )

    bnb = BernoulliNB()
    y_pred_priors = bnb.fit(X_train_priors, y_train_priors).predict(X_test_priors)
    mo.md(f"""
        Accuracy             : {accuracy_score(y_test_priors, y_pred_priors)}

        Confusion Matrix:

    ```
        {confusion_matrix(y_test_priors, y_pred_priors)}
    ```

        Classification Report: 

    ```
        {classification_report(y_test_priors, y_pred_priors)}
    ```
        """)
    return (
        BernoulliNB,
        X_priors_NB,
        X_test_priors,
        X_train_priors,
        accuracy_score,
        bnb,
        classification_report,
        confusion_matrix,
        train_test_split,
        y_pred_priors,
        y_priors_NB,
        y_test_priors,
        y_train_priors,
    )


@app.cell
def _(X_test_priors, pl, y_pred_priors, y_test_priors):
    import altair as alt
    alt.data_transformers.enable("vegafusion")

    # X_test_priors, y_pred_priors, y_test_priors
    dataset_result_priors = pl.concat([X_test_priors, y_test_priors, pl.DataFrame({"Predicted Diabetes_binary": y_pred_priors})], how="horizontal")
    dataset_result_priors1 = dataset_result_priors.select(
        (pl.col("HighBP") * 8),
        (pl.col("HighChol") * 4),
        (pl.col("Stroke") * 2),
        pl.exclude(["HighBP", "HighChol", "Stroke"])
    )
    dataset_result_priors1 = dataset_result_priors1.select(
        pl.sum_horizontal(pl.col("HighBP", "HighChol", "Stroke", "HeartDiseaseorAttack")),
        pl.col("Diabetes_binary", "Predicted Diabetes_binary")
    )
    dataset_result_priors2 = dataset_result_priors.select(
        pl.exclude(["Diabetes_binary", "Predicted Diabetes_binary"]),
        (pl.col("Diabetes_binary") * 2),
        pl.col("Predicted Diabetes_binary")
    )
    dataset_result_priors2 = dataset_result_priors2.select(
        pl.col("HighBP", "HighChol", "Stroke", "HeartDiseaseorAttack"),
        pl.sum_horizontal(pl.col("Diabetes_binary", "Predicted Diabetes_binary"))
    )
    dataset_result_priors2.head(10)
    return (
        alt,
        dataset_result_priors,
        dataset_result_priors1,
        dataset_result_priors2,
    )


@app.cell
def _():
    return


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