From 3759dc82a54c203a647151ea609dbe2d5a1c0587 Mon Sep 17 00:00:00 2001
From: ZlaTanskY <janoroelandt@hotmail.com>
Date: Fri, 25 Nov 2022 15:52:55 +0100
Subject: [PATCH 1/2] fix: mutable objects copied locally

---
 cobra/preprocessing/preprocessor.py      |  3 +++
 tests/preprocessing/test_preprocessor.py | 31 ++++++++++++++++++++++++
 2 files changed, 34 insertions(+)

diff --git a/cobra/preprocessing/preprocessor.py b/cobra/preprocessing/preprocessor.py
index e03d352..f40ab5e 100644
--- a/cobra/preprocessing/preprocessor.py
+++ b/cobra/preprocessing/preprocessor.py
@@ -293,6 +293,9 @@ def transform(self, data: pd.DataFrame, continuous_vars: list,
 
         start = time.time()
 
+        # Ensure to operate on separate copy of data
+        data = data.copy()
+
         if not self._is_fitted:
             msg = ("This {} instance is not fitted yet. Call 'fit' with "
                    "appropriate arguments before using this method.")
diff --git a/tests/preprocessing/test_preprocessor.py b/tests/preprocessing/test_preprocessor.py
index 0dd6694..a21e03e 100644
--- a/tests/preprocessing/test_preprocessor.py
+++ b/tests/preprocessing/test_preprocessor.py
@@ -1,9 +1,11 @@
 
 from contextlib import contextmanager
 from typing import Any
+from unittest.mock import MagicMock
 import pytest
 import numpy as np
 import pandas as pd
+from pytest_mock import MockerFixture
 
 from cobra.preprocessing.preprocessor import PreProcessor
 
@@ -146,3 +148,32 @@ def test_get_variable_list(self, continuous_vars: list,
                                                      discrete_vars)
 
             assert actual == expected
+
+    @staticmethod
+    def mock_transform(df: pd.DataFrame, args):
+        """Mock the transform method."""
+        df["new_column"] = "Hello World"
+        return df
+
+    def test_mutable_train_data_fit_transform(self, mocker: MockerFixture):
+        """Test if the train_data input is not changed when performing fit_transform."""
+        train_data = pd.DataFrame([[1, "2", 3], [10, "20", 30], [100, "200", 300]], columns=["foo", "bar", "baz"])
+        preprocessor = PreProcessor.from_params(
+            model_type="classification",
+            n_bins=10,
+            weight= 0.8
+        )
+        preprocessor._categorical_data_processor = MagicMock()
+        preprocessor._categorical_data_processor.transform = self.mock_transform
+        preprocessor._discretizer = MagicMock()
+        preprocessor._discretizer.transform = self.mock_transform
+        preprocessor._target_encoder = MagicMock()
+        preprocessor._target_encoder.transform = self.mock_transform
+
+        _ = preprocessor.fit_transform(
+            train_data,
+            continuous_vars=["foo"],
+            discrete_vars=["bar"],
+            target_column_name=["baz"]
+            )
+        assert "new_column" not in train_data.columns

From 1ffe9ed7b8ecf5a8592e7359369d8f0de69130a3 Mon Sep 17 00:00:00 2001
From: ZlaTanskY <janoroelandt@hotmail.com>
Date: Fri, 25 Nov 2022 15:56:40 +0100
Subject: [PATCH 2/2] chore: assert the actual result

---
 tests/preprocessing/test_preprocessor.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tests/preprocessing/test_preprocessor.py b/tests/preprocessing/test_preprocessor.py
index a21e03e..7d4d46f 100644
--- a/tests/preprocessing/test_preprocessor.py
+++ b/tests/preprocessing/test_preprocessor.py
@@ -170,10 +170,11 @@ def test_mutable_train_data_fit_transform(self, mocker: MockerFixture):
         preprocessor._target_encoder = MagicMock()
         preprocessor._target_encoder.transform = self.mock_transform
 
-        _ = preprocessor.fit_transform(
+        result = preprocessor.fit_transform(
             train_data,
             continuous_vars=["foo"],
             discrete_vars=["bar"],
             target_column_name=["baz"]
             )
         assert "new_column" not in train_data.columns
+        assert "new_column" in result.columns