Summary  
This chapter covers how to implement code that computes a 95% confidence interval by calculating the sample mean, sample standard deviation, standard error, determining the critical z-score, margin of error, and then printing the lower and upper interval bounds.

General domain of usage  
Statistical data analysis

import unittest
import pandas as pd
import numpy as np
import scipy.stats as st

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


class TestConfidenceInterval(unittest.TestCase):
    def test_confidence_interval(self):
        import user_code

        # ÐÐ°Ð²Ð°Ð½ÑÐ°Ð¶ÑÑÐ¼Ð¾ ÑÑ ÑÐ°Ð¼Ñ Ð´Ð°Ð½Ñ
        data = pd.read_csv(
            'https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/section_1/mean_mass.csv'
        )

        # ÐÑÑÐºÑÐ²Ð°Ð½Ñ ÑÐµÐ·ÑÐ»ÑÑÐ°ÑÐ¸
        mean_list = data['mass']
        expected_confidence = st.norm.interval(
            confidence=0.95,
            loc=np.mean(mean_list),
            scale=st.sem(mean_list)
        )

        # ÐÐµÑÐµÐ²ÑÑÐºÐ° ÑÐ¸Ð¿ÑÐ² Ñ ÑÐ¾ÑÐ½Ð¾ÑÑÑ
        condition = (
            isinstance(user_code.mean_list, pd.Series)
            and isinstance(user_code.confidence, tuple)
            and abs(user_code.confidence[0] - expected_confidence[0]) < 1e-6
            and abs(user_code.confidence[1] - expected_confidence[1]) < 1e-6
        )

        _dynamic_test(
            self,
            condition,
            "The confidence interval is calculated correctly.",
            "The confidence interval is incorrect. Check your calculation parameters."
        )


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


test_code.py

Learn core statistical concepts used in data analysis with Python. The course covers descriptive statistics, including mean, median, mode, variance, and standard deviation, as well as sampling, probability distributions, the Central Limit Theorem, and outlier detection.

Calculate 95% Confidence Interval

Oplossing