Refactor logistic regression (#171)

* replace regression test with classification test

* refactor code to use classifcation test same as the other classification models

* remove logistic regression specific dataset preparation

* `CHANGELOG.md` updated

* Update CHANGELOG.md

Author: AHReccese

CHANGELOG.md

@@ -5,7 +5,9 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
 ## [Unreleased]
+### Added
 ### Changed
+- testcase for LogisticRegressionCV, LogisticRegression
 - `README.md` updated
 - `AUTHORS.md` updated
 ## [1.1] - 2024-11-25

pymilo/utils/data_exporter.py

@@ -56,16 +56,3 @@ def prepare_simple_clustering_datasets():
     X = iris.data  # Features
     y = iris.target  # Target (labels)
     return X, y
-
-
-def prepare_logistic_regression_datasets(threshold=None):
-    """
-    Generate a dataset for logistic regression (the iris).
-
-    :param threshold: threshold for train/test splitting
-    :int threshold: int
-    :return: splitted dataset for logistic regression
-    """
-    iris_X, iris_y = datasets.load_iris(return_X_y=True)
-    threshold = threshold if threshold else len(iris_y) // 2
-    return _split_X_y(iris_X, iris_y, threshold)

tests/test_linear_models/logistic/logistic_regression.py

@@ -1,17 +1,17 @@
 from sklearn.linear_model import LogisticRegression
-from pymilo.utils.test_pymilo import pymilo_regression_test
-from pymilo.utils.data_exporter import prepare_simple_regression_datasets
+from pymilo.utils.test_pymilo import pymilo_classification_test
+from pymilo.utils.data_exporter import prepare_simple_classification_datasets
 
 MODEL_NAME = "Logistic-Regression"
 
 
 def logistic_regression():
-    x_train, y_train, x_test, y_test = prepare_simple_regression_datasets()
+    x_train, y_train, x_test, y_test = prepare_simple_classification_datasets()
     # Create Logistic regression object
     logistic_regression_random_state = 4
     logistic_regression = LogisticRegression(
         random_state=logistic_regression_random_state)
     # Train the model using the training sets
     logistic_regression.fit(x_train, y_train)
-    assert pymilo_regression_test(
+    assert pymilo_classification_test(
         logistic_regression, MODEL_NAME, (x_test, y_test)) == True

tests/test_linear_models/logistic/logistic_regression_cv.py

@@ -1,12 +1,12 @@
 from sklearn.linear_model import LogisticRegressionCV
-from pymilo.utils.test_pymilo import pymilo_regression_test
-from pymilo.utils.data_exporter import prepare_logistic_regression_datasets
+from pymilo.utils.test_pymilo import pymilo_classification_test
+from pymilo.utils.data_exporter import prepare_simple_classification_datasets
 
 MODEL_NAME = "Logistic-Regression-CV"
 
 
 def logistic_regression_cv():
-    x_train, y_train, x_test, y_test = prepare_logistic_regression_datasets()
+    x_train, y_train, x_test, y_test = prepare_simple_classification_datasets()
     # Create Logistic regression cv object
     logistic_regression_cv = 5
     logistic_regression_random_state = 0
@@ -15,5 +15,5 @@ def logistic_regression_cv():
         random_state=logistic_regression_random_state)
     # Train the model using the training sets
     logistic_regression_cv.fit(x_train, y_train)
-    assert pymilo_regression_test(
+    assert pymilo_classification_test(
         logistic_regression_cv, MODEL_NAME, (x_test, y_test)) == True