Summary  
Multi-class classification with k-NN selects the most frequent label among the k nearest neighbors and requires no changes to the KNeighborsClassifier beyond supplying a target variable with more than two classes.

General domain of usage  
Movie review rating classification

**Multi-class classification** with k-NN is as easy as binary classification. We just pick the class that prevails in the neighborhood.  


The `KNeighborsClassifier` automatically performs a multi-class classification if `y` has more than two features, so you **do not need to change anything**. The only thing that changes is the `y` variable fed to the `.fit()` method.

Now, you will perform a **multi-class classification with k-NN**. Consider the following dataset:

import pandas as pd

df = pd.read_csv('https://codefinity-content-media.s3.eu-west-1.amazonaws.com/b71ff7ac-3932-41d2-a4d8-060e24b00129/starwars_multiple.csv')
print(df.head())

It is the same as in the previous chapter's example, but now the target can take three values:
- **0**: "Hated it" (rating is less than 3/5);
- **1**: "Meh" (rating between 3/5 and 4/5);
- **2**: "Liked it" (rating is 4/5 or higher).

import unittest
import importlib
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)


def get_first_differing_index(expected_array, actual_array):
    for i, (val_1, val_2) in enumerate(zip(expected_array, actual_array)):
        if not np.array_equal(val_1, val_2):
            return i, expected_array[i], actual_array[i]

    if len(expected_array) > len(actual_array):
        return len(actual_array), expected_array[len(actual_array)], None
    else:
        return len(expected_array), None, actual_array[len(expected_array)]


class TestUserCode(unittest.TestCase):

    def test_scaler_is_declared(self):
        import user_code

        variable = 'scaler'
        _dynamic_test(
            self,
            hasattr(user_code, variable),
            f"The `{variable}` variable is declared.",
            f"Expected `{variable}` to be declared."
        )

    def test_scaler_is_standard_scaler(self):
        import user_code
        from sklearn.preprocessing import StandardScaler

        try:
            condition = isinstance(user_code.scaler, StandardScaler)
            failure_message = f"Expected `scaler` to be a `StandardScaler`, but got `{type(user_code.scaler).__name__}`."
        except AttributeError:
            condition = False
            failure_message = "The `scaler` variable is not declared."

        _dynamic_test(
            self,
            condition,
            "`scaler` is a `StandardScaler`.",
            failure_message
        )

    def test_X_train_is_scaled_correctly(self):
        import user_code
        from sklearn.preprocessing import StandardScaler

        df = user_code.pd.read_csv(
            'https://codefinity-content-media.s3.eu-west-1.amazonaws.com/b71ff7ac-3932-41d2-a4d8-060e24b00129/starwars_multiple.csv')
        X_train = df.drop('StarWars6', axis=1)

        scaler = StandardScaler()
        expected_value = scaler.fit_transform(X_train)

        variable = 'X_train'
        actual_value = getattr(user_code, variable, None)
        condition = False
        if actual_value is None:
            failure_message = f"The `{variable}` variable is not declared."
        elif not isinstance(actual_value, np.ndarray):
            failure_message = f"`{variable}` is not a `numpy.ndarray`."
        elif actual_value.size == 0:
            failure_message = f"`{variable}` is empty."
        elif np.array_equal(actual_value, expected_value):
            condition = True
            failure_message = None
        else:
            idx, expected_element, actual_element = get_first_differing_index(expected_value, actual_value)
            failure_message = f"Expected `{variable}` to contain `{expected_element}` at index {idx}, but got `{actual_element}`."

        _dynamic_test(
            self,
            condition,
            f"`{variable}` contains the correct data.",
            failure_message
        )

    def test_X_test_is_scaled_correctly(self):
        import user_code
        from sklearn.preprocessing import StandardScaler

        df = user_code.pd.read_csv(
            'https://codefinity-content-media.s3.eu-west-1.amazonaws.com/b71ff7ac-3932-41d2-a4d8-060e24b00129/starwars_multiple.csv')
        X_train = df.drop('StarWars6', axis=1)
        X_test = np.array([[5, 5], [4.5, 4]])

        scaler = StandardScaler()
        scaler.fit(X_train)
        expected_value = scaler.transform(X_test)

        variable = 'X_test'
        actual_value = getattr(user_code, variable, None)
        condition = False
        if actual_value is None:
            failure_message = f"The `{variable}` variable is not declared."
        elif not isinstance(actual_value, np.ndarray):
            failure_message = f"`{variable}` is not a `numpy.ndarray`."
        elif actual_value.size == 0:
            failure_message = f"`{variable}` is empty."
        elif np.array_equal(actual_value, expected_value):
            condition = True
            failure_message = None
        else:
            idx, expected_element, actual_element = get_first_differing_index(expected_value, actual_value)
            failure_message = f"Expected `{variable}` to contain `{expected_element}` at index {idx}, but got `{actual_element}`."

        _dynamic_test(
            self,
            condition,
            f"`{variable}` contains the correct data.",
            failure_message
        )

    def test_knn_is_declared(self):
        import user_code

        variable = 'knn'
        _dynamic_test(
            self,
            hasattr(user_code, variable),
            f"The `{variable}` variable is declared.",
            f"Expected `{variable}` to be declared."
        )

    def test_knn_is_initialized_correctly(self):
        import user_code
        from sklearn.neighbors import KNeighborsClassifier

        variable = 'knn'
        actual_value = getattr(user_code, variable, None)
        if actual_value is None:
            condition = False
            failure_message = f"The `{variable}` variable is not declared."
        elif isinstance(actual_value, KNeighborsClassifier):
            condition = actual_value.n_neighbors == 13
            failure_message = f"Expected `{variable}` to be a `KNeighborsClassifier` with `13` neighbors, but got `n_neighbors={actual_value.n_neighbors}`."
        else:
            condition = False
            failure_message = f"`{variable}` is not a `KNeighborsClassifier`."

        _dynamic_test(
            self,
            condition,
            f"`{variable}` is a `KNeighborsClassifier` with `13` neighbors.",
            failure_message
        )

    def test_y_pred_is_declared(self):
        import user_code

        variable = 'y_pred'
        _dynamic_test(
            self,
            hasattr(user_code, variable),
            f"The `{variable}` variable is declared.",
            f"Expected `{variable}` to be declared."
        )

    def test_y_pred_is_correct(self):
        import user_code

        expected_value = np.array([2, 1])

        variable = 'y_pred'
        actual_value = getattr(user_code, variable, None)
        condition = False
        if actual_value is None:
            failure_message = f"The `{variable}` variable is not declared."
        elif not isinstance(actual_value, np.ndarray):
            failure_message = f"`{variable}` is not a `numpy.ndarray`."
        elif actual_value.size == 0:
            failure_message = f"`{variable}` is empty."
        elif np.array_equal(actual_value, expected_value):
            condition = True
            failure_message = None
        else:
            idx, expected_element, actual_element = get_first_differing_index(expected_value, actual_value)
            failure_message = f"Expected `{variable}` to contain `{expected_element}` at index {idx}, but got `{actual_element}`."

        _dynamic_test(
            self,
            condition,
            f"`{variable}` contains the correct data.",
            failure_message
        )


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

test_main.py

Master the core classification algorithms that power modern machine learning. Explore how models like k-NN, logistic regression, decision trees, and random forests make predictions, evaluate their accuracy, and understand when to use each. Build the skills to compare models and choose the best one for your data.

Discover how the k-nearest neighbors algorithm makes predictions based on similarity. Learn to handle multiple features, tune parameters, and apply cross-validation to improve accuracy.

Understand how logistic regression models probabilities and classifies outcomes. Practice implementing it, interpreting decision boundaries, and applying regularization to prevent overfitting.

Learn how decision trees split data into meaningful groups based on feature values. Explore how parameters like tree depth and minimum samples per leaf affect model performance and generalization.

Explore how random forests combine multiple decision trees to improve accuracy and robustness. Understand the role of randomness and apply this ensemble method to real-world data.

Evaluate models using metrics such as accuracy, precision, recall, and F1-score. Learn to interpret confusion matrices and compare multiple classifiers to identify the best-performing model.

Multi-Class Classification

Solution

Awesome!

Multi-Class Classification

Solution