Add comparison to Decision Tree Classifier.

app.py

@@ -47,13 +47,14 @@ def _(pl):
 
 @app.cell
 def _(mo):
-    mo.md("""## Naive Bayes' Classifier""")
+    mo.md("""## Testing Classifiers""")
     return
 
 
 @app.cell
 def _(dataset_prior_conditions, mo, pl):
     from sklearn.naive_bayes import BernoulliNB
+    from sklearn.tree import DecisionTreeClassifier
     from sklearn.model_selection import train_test_split
     from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
 
@@ -63,8 +64,12 @@ def _(dataset_prior_conditions, mo, pl):
     )
 
     bnb = BernoulliNB()
+    dtc = DecisionTreeClassifier()
     y_pred_priors = bnb.fit(X_train_priors, y_train_priors).predict(X_test_priors)
-    mo.md(f"""
+    y_pred_dtc = dtc.fit(X_train_priors, y_train_priors).predict(X_test_priors)
+    mo.accordion(
+        {
+            "Bernoulli NB Metrics": f"""    
         Accuracy             : {accuracy_score(y_test_priors, y_pred_priors)}
 
         Confusion Matrix:
@@ -78,9 +83,25 @@ def _(dataset_prior_conditions, mo, pl):
     ```
         {classification_report(y_test_priors, y_pred_priors)}
     ```
-        """)
+        """,
+        "Decision Tree Classifier": f"""    
+        Accuracy             : {accuracy_score(y_test_priors, y_pred_dtc)}
+
+        Confusion Matrix:
+
+    ```
+        {confusion_matrix(y_test_priors, y_pred_dtc)}
+    ```
+
+        Classification Report: 
+
+    ```
+        {classification_report(y_test_priors, y_pred_dtc)}
+    ```
+        """})
     return (
         BernoulliNB,
+        DecisionTreeClassifier,
         X_priors_NB,
         X_test_priors,
         X_train_priors,
@@ -88,7 +109,9 @@ def _(dataset_prior_conditions, mo, pl):
         bnb,
         classification_report,
         confusion_matrix,
+        dtc,
         train_test_split,
+        y_pred_dtc,
         y_pred_priors,
         y_priors_NB,
         y_test_priors,
@@ -97,43 +120,14 @@ def _(dataset_prior_conditions, mo, pl):
 
 
 @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,
-    )
+def _(mo):
+    mo.md(r"""Looks like Bernoulli Naive Bayes' performs better on this dataset, as even though the Decision Tree Classifier has a bit better accuracy, the other metrics do give a better score on the BNB overall.""")
+    return
 
 
 @app.cell
 def _(mo):
-    mo.md(r"""# Diabetes Predictor""")
+    mo.md(r"""# Diabetes Predictor using BNB""")
     return
 
 
@@ -165,10 +159,5 @@ def _(bnb, mo, priors_predict):
     return diabetes_or_not, prediction
 
 
-@app.cell
-def _():
-    return
-
-
 if __name__ == "__main__":
     app.run()