In this challenge, you will use the **Titanic dataset**, which contains information about passengers on the Titanic, including their age, sex, family size, and more. The goal is to predict whether a passenger survived or not.

import pandas as pd

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

To implement the Decision Tree, you can use the `DecisionTreeClassifier` from `sklearn`:

Your task is to build a Decision Tree and find the best `max_depth` and `min_samples_leaf` using grid search.

import unittest
import importlib


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 TestUserCode(unittest.TestCase):
    def test_param_grid_is_declared(self):
        import user_code

        _dynamic_test(
            self,
            hasattr(user_code, 'param_grid'),
            "The `param_grid` variable is declared.",
            "Expected `param_grid` to be declared."
        )

    def test_param_grid_is_correct(self):
        import user_code
        expected_value = {'max_depth': [1, 2, 3, 4, 5, 6, 7], 'min_samples_leaf': [1, 2, 4, 6]}

        variable = 'param_grid'
        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, dict):
            condition = actual_value == expected_value
            failure_message = f"Expected `{variable}` to contain `{expected_value}`, but got `{actual_value}`."
        else:
            condition = False
            failure_message = f"`{variable}` is not a `dict`."

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

    def test_grid_cv_is_declared(self):
        import user_code

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

    def test_grid_cv_is_correct(self):
        import user_code
        from sklearn.model_selection import GridSearchCV
        from sklearn.tree import DecisionTreeClassifier

        param_grid = {'max_depth': [1, 2, 3, 4, 5, 6, 7], 'min_samples_leaf': [1, 2, 4, 6]}

        variable = 'grid_cv'
        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, GridSearchCV):
            condition = isinstance(actual_value.estimator,
                                   DecisionTreeClassifier) and actual_value.param_grid == param_grid and actual_value.cv is 10
            failure_message = f"Expected `{variable}` to be a `GridSearchCV` with `estimator=DecisionTreeClassifier()`, `param_grid={param_grid}`, and `cv=10`, but got `estimator={actual_value.estimator}`, `param_grid={actual_value.param_grid}`, and `cv={actual_value.cv}`."
        else:
            condition = False
            failure_message = f"`{variable}` is not a `GridSearchCV`."

        _dynamic_test(
            self,
            condition,
            "`grid_cv` is a `GridSearchCV` with `estimator=lr`, `param_grid=param_grid`, and `cv=None`.",
            failure_message
        )

    def test_best_score_is_correct(self):
        import user_code
        expected_value = 0.8316978776529339

        variable = 'best_score'
        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, float):
            condition = actual_value == expected_value
            failure_message = f"Expected `{variable}` to contain `{expected_value}`, but got `{actual_value}`."
        else:
            condition = False
            failure_message = f"`{variable}` is not a `float`."

        _dynamic_test(
            self,
            condition,
            f"`{variable}` is correct.",
            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.

Challenge: Implementing a Decision Tree

Solution

Awesome!

Challenge: Implementing a Decision Tree

Solution