In this challenge, build and evaluate a model using both the train-test split and cross-validation on the preprocessed **penguins dataset**.

The following functions will be useful:

* `cross_val_score()` from `sklearn.model_selection`;
* `train_test_split()` from `sklearn.model_selection`;
* `.fit()` and `.score()` methods of the model.


import unittest
import pandas as pd
import numpy as np

def _dynamic_test(test_case, condition, success_message, failure_message):
    if condition:
        test_case._testMethodName = success_message
        test_case.assertTrue(True, success_message)
    else:
        test_case._testMethodName = failure_message
        test_case.fail(failure_message)

class TestKNNWithCVAndSplit(unittest.TestCase):

    @classmethod
    def setUpClass(cls):
        cls.df = pd.read_csv(
            'https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a65bbc96-309e-4df9-a790-a1eb8c815a1c/penguins_pipelined.csv'
        )
        cls.X, cls.y = cls.df.drop('species', axis=1), cls.df['species']
        import user_code
        cls.uc = user_code  # Ð¾ÑÑÐºÑÑÑÑÑÑ: model, scores, X_train, X_test, y_train, y_test

    def test_model_is_knn_with_4_neighbors(self):
        from sklearn.neighbors import KNeighborsClassifier
        uc = self.uc
        cond = isinstance(getattr(uc, 'model', None), KNeighborsClassifier) and \
               getattr(uc.model, 'n_neighbors', None) == 4
        _dynamic_test(
            self,
            cond,
            "Model is KNeighborsClassifier with n_neighbors=4",
            "Model must be KNeighborsClassifier with n_neighbors=4"
        )

    def test_cross_val_scores_len_and_cv3(self):
        # ÐÐµÑÐµÐ²ÑÑÑÑÐ¼Ð¾, ÑÐ¾ Ð¾ÑÑÐ¸Ð¼Ð°Ð½Ð¾ ÑÑÐ²Ð½Ð¾ 3 Ð¾ÑÑÐ½ÐºÐ¸ Ñ Ð²Ð¾Ð½Ð¸ ÑÑÐ¼ÑÑÐ½Ñ Ð· cv=3 Ð´Ð»Ñ 4-NN
        from sklearn.model_selection import cross_val_score
        from sklearn.neighbors import KNeighborsClassifier
        uc = self.uc
        scores = getattr(uc, 'scores', None)
        try:
            ok_len = hasattr(scores, '__len__') and len(scores) == 3
            ref = cross_val_score(KNeighborsClassifier(n_neighbors=4), self.X, self.y, cv=3)
            ok_mean_close = np.isfinite(np.mean(scores)).item() and np.isclose(np.mean(scores), np.mean(ref), rtol=0, atol=1e-6)
            cond = ok_len and ok_mean_close
        except Exception:
            cond = False
        _dynamic_test(
            self,
            cond,
            "Cross-validation produced 3-fold scores with cv=3",
            "Cross-validation must use cv=3 and produce 3 scores"
        )

    def test_train_test_split_shapes(self):
        uc = self.uc
        has_vars = all(hasattr(uc, name) for name in ['X_train', 'X_test', 'y_train', 'y_test'])
        if has_vars:
            n_total = len(self.X)
            n_test = len(uc.X_test)
            # ÐÐ¾Ð¿ÑÑÐºÐ°ÑÐ¼Ð¾ Ð¿Ð¾ÑÐ¸Ð±ÐºÑ Ð¾ÐºÑÑÐ³Ð»ÐµÐ½Ð½Ñ Ð¿ÑÐ¸ test_size=0.33
            expected_test = int(round(0.33 * n_total))
            cond = uc.X_train.shape[0] + uc.X_test.shape[0] == n_total and \
                   uc.y_train.shape[0] + uc.y_test.shape[0] == n_total and \
                   abs(n_test - expected_test) <= 2
        else:
            cond = False
        _dynamic_test(
            self,
            cond,
            "Data was split into train and test with approximately 33% for test",
            "Data must be split into train and test with approximately 33% for test"
        )

    def test_model_fitted_and_predicts_on_test(self):
        uc = self.uc
        try:
            y_pred = uc.model.predict(uc.X_test)
            cond = isinstance(y_pred, (np.ndarray, list)) and len(y_pred) == len(uc.y_test)
        except Exception:
            cond = False
        _dynamic_test(
            self,
            cond,
            "Model is fitted and can predict on X_test",
            "Model must be fitted and able to predict on X_test"
        )

    def test_test_score_available(self):
        uc = self.uc
        try:
            score = uc.model.score(uc.X_test, uc.y_test)
            cond = isinstance(score, (float, np.floating)) and np.isfinite(score)
        except Exception:
            cond = False
        _dynamic_test(
            self,
            cond,
            "Test score is available via model.score(X_test, y_test)",
            "Test score must be computed via model.score(X_test, y_test)"
        )

if __name__ == "__main__":
    unittest.main()


test_code.py

Machine learning is now used everywhere. Want to learn it yourself? This course is an introduction to the world of Machine learning for you to learn basic concepts, work with Scikit-learn – the most popular library for ML and build your first Machine Learning project.
This course is intended for students with a basic knowledge of Python, Pandas, and Numpy.

Learn the Machine Learning concepts and the ML project workflow.

Preprocessing is probably the most important stage of an ML project. This chapter covers the preprocessing steps needed for almost any dataset.

A pipeline is a neat way to combine all the preprocessing steps as well as a model. Pipelines make it much easier to train and use a model.

Modeling is the most fun stage of an ML project. Let's learn to build, fine-tune and evaluate the model!

Challenge: Evaluating the Model with Cross-Validation

Solution

Awesome!

Challenge: Evaluating the Model with Cross-Validation

Solution