Summary  
This chapter shows how to implement functions to compute covariance and correlation between numerical datasets by processing arrays and applying statistical formulas.  

General domain of usage  
Data analysis

import unittest
import pandas as pd
import numpy as np

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 TestCovariance(unittest.TestCase):
    def test_covariance(self):
        import user_code

        df = pd.read_csv(
            'https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/update/Stores.csv'
        )

        expected_cov = np.cov(df['Daily_Customer_Count'], df['Items_Available'])[0, 1]

        condition = abs(user_code.cov - expected_cov) < 1e-6

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


class TestCorrelation(unittest.TestCase):
    def test_correlation(self):
        import user_code

        df = pd.read_csv(
            'https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/update/Stores.csv'
        )

        expected_corr = np.corrcoef(df['Daily_Customer_Count'], df['Items_Available'])[0, 1]

        condition = abs(user_code.corr - expected_corr) < 1e-6

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


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


test_code.py

Pythonを用いたデータ分析で使用される主要な統計概念を学習します。本コースでは、平均、中央値、最頻値、分散、標準偏差などの記述統計に加え、サンプリング、確率分布、中心極限定理、外れ値検出についても取り上げます。

共分散と相関の計算

解答