Summary  
This chapter covers label-based selection and slicing of rows and columns in a two-dimensional data structure using a dedicated indexing attribute.

General domain of usage  
Data analysis

Okay, you've dealt with the previous chapters, and now is the right time to combine your knowledge. You can specify both rows and columns; to do so, you just need to be familiar with the `.loc[]` attribute.

This function allows us to do plenty of different slicing operations, but for now, we will just consolidate knowledge from the previous chapters.

As usual, look at the example and then at the output.

- `data.loc[2:5, ['Director', 'ReleaseYear']]` - outputs rows with the indices `2`, `3`, `4`, `5`(but remember that the indices start from `0`) from the columns `'Director'` and `'ReleaseYear'`(`.loc[]` includes the last index that you put into `[]`);
- `data.loc[:5, ['Director', 'ReleaseYear']]` - outputs rows with the indices `0`, `1`, `2`, `3`, `4`, `5` from the columns `'Director'` and `'ReleaseYear'`;
- `data.loc[997:, ['Director', 'ReleaseYear']]` - outputs rows with the indices `997`, `998`, `999` (`999` is the index of the last row) from the columns `'Director'` and `'ReleaseYear'`;
- `data.loc[:, ['Director', 'ReleaseYear']]` or  `data[['Director', 'ReleaseYear']]` - outputs all rows from the columns `'Director'` and `'ReleaseYear'`.

import unittest
import pandas as pd

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 TestPandasImport(unittest.TestCase):
    def test_import_pandas_as_pd(self):
        """
        1. Import the pandas library with the pd alias.
        """
        import user_code
        condition = "pd" in user_code.__dict__ and user_code.pd is pd
        _dynamic_test(
            self,
            condition,
            "The pandas library is imported correctly with the alias 'pd'.",
            "Pandas is not imported correctly. Use 'import pandas as pd'."
        )


class TestCSVRead(unittest.TestCase):
    def test_csv_read(self):
        """
        2. Read the CSV file.
        """
        import user_code
        condition = hasattr(user_code, "data") and isinstance(user_code.data, pd.DataFrame)
        _dynamic_test(
            self,
            condition,
            "The CSV file is read correctly into the 'data' DataFrame.",
            "The CSV file is not read correctly or not assigned to 'data'."
        )


class TestDataExtraction(unittest.TestCase):
    def test_data_extracted_slice(self):
        """
        3. Assign to data_extracted variable correct slice.
        """
        import user_code
        df_user = user_code.data_extracted
        ref = pd.read_csv(
            "https://codefinity-content-media.s3.eu-west-1.amazonaws.com/4bf24830-59ba-4418-969b-aaf8117d522e/IMDb_Data_final.csv"
        ).loc[15:85, ["Title", "Stars", "Category"]]
        condition = (
            isinstance(df_user, pd.DataFrame)
            and list(df_user.columns) == ["Title", "Stars", "Category"]
            and df_user.equals(ref)
        )
        _dynamic_test(
            self,
            condition,
            "The variable 'data_extracted' contains the correct rows and columns.",
            "The slice for 'data_extracted' is incorrect. Check the indices and column order."
        )


class TestOutput(unittest.TestCase):
    def test_print_output(self):
        """
        4. Output the data_extracted variable.
        """
        import user_code
        import io
        import sys

        captured_output = io.StringIO()
        sys.stdout = captured_output
        # re-run print part
        if hasattr(user_code, "data_extracted"):
            print(user_code.data_extracted)
        sys.stdout = sys.__stdout__

        output_text = captured_output.getvalue()
        condition = len(output_text.strip()) > 0
        _dynamic_test(
            self,
            condition,
            "The 'data_extracted' variable is printed as output.",
            "The 'data_extracted' variable is not printed. Use print(data_extracted)."
        )


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


Selecting Rows and Columns

Solução