Summary  
This chapter explains how to use conditional expressions to select or filter elements based on boolean conditions.

General domain of usage  
Data processing

To excel in programming, you always need to practice. So, in this task, you must also memorize functions from the previous chapter. If you aren't solid on the functions from the last chapter, look at the hints to revise them.

import unittest
import pandas as pd
import io
import sys


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)


def frames_equal_ignore_col_order(df1, df2):
    """ÐÐµÑÐµÐ²ÑÑÑÑ ÑÑÐ²Ð½ÑÑÑÑ DataFrame Ð½ÐµÐ·Ð°Ð»ÐµÐ¶Ð½Ð¾ Ð²ÑÐ´ Ð¿Ð¾ÑÑÐ´ÐºÑ ÐºÐ¾Ð»Ð¾Ð½Ð¾Ðº."""
    if set(df1.columns) != set(df2.columns):
        return False
    common_cols = sorted(df1.columns)
    df1_sorted = df1[common_cols].reset_index(drop=True)
    df2_sorted = df2[common_cols].reset_index(drop=True)
    return df1_sorted.equals(df2_sorted)


class TestExtraction(unittest.TestCase):
    def test_extract_columns(self):
        """
        1. Extract all rows from columns 'name' and 'hazardous' using .loc[].
        """
        import user_code
        df = pd.read_csv(
            "https://codefinity-content-media.s3.eu-west-1.amazonaws.com/4bf24830-59ba-4418-969b-aaf8117d522e/planet"
        )
        ref = df.loc[:, ["name", "hazardous"]]

        condition = (
            hasattr(user_code, "data_extracted")
            and isinstance(user_code.data_extracted, pd.DataFrame)
            and frames_equal_ignore_col_order(user_code.data_extracted, ref)
        )
        _dynamic_test(
            self,
            condition,
            "Columns 'name' and 'hazardous' are extracted correctly using .loc[].",
            "The extraction of 'name' and 'hazardous' columns is incorrect."
        )


class TestFiltering(unittest.TestCase):
    def test_filter_true_rows(self):
        """
        2. Filter rows where 'hazardous' is True.
        """
        import user_code
        ref = user_code.data_extracted.loc[user_code.data_extracted["hazardous"] == True]

        condition = (
            hasattr(user_code, "data_filtered")
            and isinstance(user_code.data_filtered, pd.DataFrame)
            and frames_equal_ignore_col_order(user_code.data_filtered, ref)
        )
        _dynamic_test(
            self,
            condition,
            "Rows where 'hazardous' == True are filtered correctly.",
            "Filtering by 'hazardous' == True is incorrect."
        )


class TestOutput(unittest.TestCase):
    def test_print_output(self):
        """
        3. Output the first five rows of data_filtered using .head().
        """
        import user_code

        captured_output = io.StringIO()
        sys.stdout = captured_output
        print(user_code.data_filtered.head())
        sys.stdout = sys.__stdout__

        output_text = captured_output.getvalue().strip()
        condition = len(output_text) > 0
        _dynamic_test(
            self,
            condition,
            "The output displays the first five rows of 'data_filtered' correctly.",
            "The 'data_filtered' dataset is not printed correctly. Use print(data_filtered.head())."
        )


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


Selecting by Condition

解答