From 97113fe9ab5023808cfbc62f9172ede63403fc29 Mon Sep 17 00:00:00 2001
From: junos <junos.lukan@ijs.si>
Date: Wed, 31 May 2023 17:27:49 +0200
Subject: [PATCH] Sum up confusion matrix and illustrate use with dummy.

---
 machine_learning/helper.py | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/machine_learning/helper.py b/machine_learning/helper.py
index 32ecc98..f008716 100644
--- a/machine_learning/helper.py
+++ b/machine_learning/helper.py
@@ -425,6 +425,15 @@ def confusion_matrix_scorer(clf, X, y):
     return {"tn": cm[0, 0], "fp": cm[0, 1], "fn": cm[1, 0], "tp": cm[1, 1]}
 
 
+def aggregate_confusion_matrix(scores_dict: dict) -> pd.DataFrame:
+    scores_aggregated = aggregate_and_transpose(
+        pd.DataFrame(scores_dict), statistics=["sum"]
+    )
+    return scores_aggregated[
+        ~scores_aggregated.test_metric.isin(["fit_time", "score_time"])
+    ]
+
+
 def run_all_classification_models(
     data_x: pd.DataFrame,
     data_y: pd.DataFrame,
@@ -455,10 +464,29 @@ def run_all_classification_models(
         error_score="raise",
         scoring=metrics,
     )
+    dummy_confusion_matrix = cross_validate(
+        dummy_class,
+        X=data_x,
+        y=data_y,
+        groups=data_groups,
+        cv=cross_validator,
+        n_jobs=-1,
+        error_score="raise",
+        scoring=confusion_matrix_scorer,
+    )
     print("Dummy")
 
     scores_df = pd.DataFrame(dummy_score)[test_metrics]
     scores_df = aggregate_and_transpose(scores_df, statistics=["max", "mean"])
+    scores_df = pd.concat(
+        [
+            scores_df,
+            aggregate_confusion_matrix(dummy_confusion_matrix).rename(
+                columns={"sum": "mean"}
+                # Note: the column is misleadingly renamed to get concise output.
+            ),
+        ]
+    )
     scores_df["method"] = "dummy_classifier"
     scores = pd.concat([scores, scores_df])
     del dummy_class