Now create a pipeline that includes a **final estimator**. This produces a trained prediction pipeline that can generate predictions for new instances using the `.predict()` method.

Since a predictor requires the target variable `y`, encode it separately from the pipeline built for `X`. Use `LabelEncoder` to encode the **target**.


Additionally, there are materials to review the syntax of `make_column_transformer` and `make_pipeline`.

Since the predictions are **encoded** as 0, 1, or 2, the `.inverse_transform()` method of `LabelEncoder` can be used to convert them back to the original labels: `'Adelie'`, `'Chinstrap'`, or `'Gentoo'`.


Note

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 TestPipelineKNN(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.csv'
        )
        cls.df = cls.df[cls.df.isna().sum(axis=1) < 2]
        import user_code
        cls.uc = user_code  # Ð¾ÑÑÐºÑÑÑÑÑÑ: X, y, ct, pipe, label_enc

    def test_label_encoding(self):
        from sklearn.preprocessing import LabelEncoder
        uc = self.uc
        y_arr = np.asarray(uc.y)
        is_int = np.issubdtype(y_arr.dtype, np.integer)
        le_ok = isinstance(getattr(uc, 'label_enc', None), LabelEncoder) and hasattr(uc.label_enc, 'classes_')
        cond = (y_arr.ndim == 1) and is_int and le_ok
        _dynamic_test(
            self,
            cond,
            "Target is label-encoded with LabelEncoder and integer dtype",
            "Target must be encoded with LabelEncoder to integer dtype and have classes_"
        )

    def test_column_transformer_targets_and_remainder(self):
        from sklearn.compose import ColumnTransformer
        from sklearn.preprocessing import OneHotEncoder
        uc = self.uc
        ct = getattr(uc, 'ct', None)
        cond_ct = isinstance(ct, ColumnTransformer)
        # ÑÑÐºÐ°ÑÐ¼Ð¾ ÑÑÐ°Ð½ÑÑÐ¾ÑÐ¼ÐµÑ Ð· OneHotEncoder, Ð·Ð°ÑÑÐ¾ÑÐ¾Ð²Ð°Ð½Ð¸Ð¹ Ð´Ð¾ 'island' Ñ 'sex' (Ñ Ð±ÑÐ´Ñ-ÑÐºÐ¾Ð¼Ñ Ð¿Ð¾ÑÑÐ´ÐºÑ)
        found_ohe = False
        if cond_ct:
            for _, trans, cols in ct.transformers:
                if isinstance(trans, OneHotEncoder):
                    cols_set = set(cols) if isinstance(cols, (list, tuple)) else set([cols])
                    if cols_set == {'island', 'sex'}:
                        found_ohe = True
                        break
        remainder_ok = cond_ct and getattr(ct, 'remainder', None) == 'passthrough'
        cond = cond_ct and found_ohe and remainder_ok
        _dynamic_test(
            self,
            cond,
            "ColumnTransformer applies OneHotEncoder to 'island' and 'sex' with remainder='passthrough'",
            "ColumnTransformer must apply OneHotEncoder to 'island' and 'sex' and set remainder='passthrough'"
        )

    def test_pipeline_structure_and_order(self):
        # Ð¼Ð°Ñ Ð±ÑÑÐ¸ ÑÐ°Ð¼Ðµ Ð¿Ð¾ÑÑÐ´Ð¾Ðº: ColumnTransformer -> SimpleImputer -> StandardScaler -> KNeighborsClassifier
        uc = self.uc
        step_names = [name for name, _ in uc.pipe.steps] if hasattr(uc, 'pipe') else []
        expected = ['columntransformer', 'simpleimputer', 'standardscaler', 'kneighborsclassifier']
        cond = step_names == expected
        _dynamic_test(
            self,
            cond,
            "Pipeline steps are in order: ColumnTransformer, SimpleImputer, StandardScaler, KNeighborsClassifier",
            "Pipeline steps must be in order: ColumnTransformer, SimpleImputer, StandardScaler, KNeighborsClassifier"
        )

    def test_imputer_strategy(self):
        # ÑÑÑÐ°ÑÐµÐ³ÑÑ Ð¼Ð°Ñ Ð±ÑÑÐ¸ 'most_frequent'
        uc = self.uc
        try:
            imputer = dict(uc.pipe.named_steps).get('simpleimputer', None)
            cond = getattr(imputer, 'strategy', None) == 'most_frequent'
        except Exception:
            cond = False
        _dynamic_test(
            self,
            cond,
            "SimpleImputer uses strategy='most_frequent'",
            "SimpleImputer must use strategy='most_frequent'"
        )

    def test_model_is_fitted_and_predicts(self):
        # ÑÐºÑÐ¾ Ð¿Ð°Ð¹Ð¿Ð»Ð°Ð¹Ð½ Ð½Ðµ Ð½Ð°Ð²ÑÐµÐ½Ð¸Ð¹, predict Ð²Ð¸ÐºÐ»Ð¸ÑÐµ Ð¿Ð¾Ð¼Ð¸Ð»ÐºÑ; Ð´Ð¾Ð´Ð°ÑÐºÐ¾Ð²Ð¾ Ð¿ÐµÑÐµÐ²ÑÑÐ¸Ð¼Ð¾ Ð´Ð¾Ð²Ð¶Ð¸Ð½Ñ
        uc = self.uc
        try:
            y_pred = uc.pipe.predict(uc.X)
            cond = isinstance(y_pred, (np.ndarray, list)) and len(y_pred) == len(uc.y)
        except Exception:
            cond = False
        _dynamic_test(
            self,
            cond,
            "Pipeline is fitted and can predict on X",
            "Pipeline must be fitted and able to predict on X"
        )

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: Creating a Complete ML Pipeline

Solution

Challenge: Creating a Complete ML Pipeline

Solution