Summary  
This chapter covers data exploration techniques such as loading a dataset into memory, inspecting its structure and contents, printing sample records, and computing basic summary statistics to understand the data.  

General domain of usage  
Data analysis

import unittest
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

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 TestDataReading(unittest.TestCase):
    def test_data_loaded(self):
        import user_code

        expected_data = pd.read_csv(
            'https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a849660e-ddfa-4033-80a6-94a1b7772e23/section_1/confidence.csv',
            index_col=0
        )

        condition = (
            isinstance(user_code.data, pd.DataFrame)
            and user_code.data.shape == expected_data.shape
        )

        _dynamic_test(
            self,
            condition,
            "The CSV file is correctly read into the 'data' variable.",
            "The CSV file is not read correctly into the 'data' variable."
        )


class TestPlot(unittest.TestCase):
    def test_histplot(self):
        import user_code

        # ÐÐµÑÐµÐ²ÑÑÑÑÐ¼Ð¾, ÑÐ¸ ÑÑÐ²Ð¾ÑÐµÐ½Ð¾ Ð³ÑÐ°ÑÑÐº Ð· seaborn.histplot
        plot_obj = user_code.plot

        condition = (
            hasattr(plot_obj, "get_xlabel")
            and plot_obj.get_xlabel() == "The Mass"
            and plot_obj.get_ylabel() == "The Quantity"
        )

        _dynamic_test(
            self,
            condition,
            "The histplot is created with correct parameters.",
            "The histplot parameters are incorrect."
        )


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.

Explore the Data Set

Solution