To handle null values **while retaining each row** of the DataFrame, we can utilize the `fillna()` method. This allows us to populate each empty cell with a **specific value** (like a string or number) rather than eliminating it.

To replace null values with the number 0, the `fillna()` method is used:
```python
import pandas as pd
df = pd.read_csv(file.csv)
new_df = df.fillna(0)
```

import unittest
import importlib
import pandas as pd


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


def get_first_differing_row(expected_df, actual_df):
    expected_list = expected_df.astype(str).apply(tuple, axis=1)
    actual_list = actual_df.astype(str).apply(tuple, axis=1)

    for i, (row1, row2) in enumerate(zip(expected_list, actual_list)):
        if row1 != row2:
            return i, expected_df.iloc[i].values, actual_df.iloc[i].values

    if len(expected_df) > len(actual_df):
        return len(actual_df), expected_df.iloc[len(actual_df)].values, None
    else:
        return len(expected_df), None, actual_df.iloc[len(expected_df)].values


class TestUserCode(unittest.TestCase):

    def test_wine_data_is_declared(self):
        import user_code
        _dynamic_test(
            self,
            hasattr(user_code, 'wine_data'),
            "The `wine_data` variable is declared.",
            "Expected `wine_data` to be declared."
        )

    def test_wine_data_is_dataframe(self):
        import user_code

        try:
            condition = isinstance(user_code.wine_data, pd.DataFrame)
            failure_message = f"Expected `wine_data` to be a `DataFrame`, but got `{type(user_code.wine_data).__name__}`."
        except AttributeError:
            condition = False
            failure_message = "The `wine_data` variable is not declared."

        _dynamic_test(
            self,
            condition,
            "The variable `wine_data` is a `DataFrame`.",
            failure_message
        )

    def test_wine_data_has_no_nulls(self):
        import user_code

        try:
            condition = not user_code.wine_data.isnull().values.any()
            failure_message = "Expected `wine_data` to have no null values, but null values are still present."
        except AttributeError:
            condition = False
            if not getattr(user_code, 'wine_data', None):
                failure_message = "The `wine_data` variable is not declared."
            else:
                failure_message = f"`wine_data` is not a `DataFrame`."
        _dynamic_test(
            self,
            condition,
            "`wine_data` has no null values after cleaning.",
            failure_message
        )

    def test_nulls_replaced_with_no(self):
        import user_code

        try:
            condition = (user_code.wine_data.values == 'no').sum() == 7
            failure_message = "Expected all null values in `wine_data` to be replaced with 'no', but they were not."
        except AttributeError:
            condition = False
            if not getattr(user_code, 'wine_data', None):
                failure_message = "The `wine_data` variable is not declared."
            else:
                failure_message = f"`wine_data` is not a `DataFrame`."
        _dynamic_test(
            self,
            condition,
            "Null values in `wine_data` are replaced with 'no'.",
            failure_message
        )

    def test_wine_data_has_correct_values(self):
        import user_code

        wine_data = pd.read_csv(
            'https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a43d24b6-df61-4e11-9c90-5b36552b3437/wine_with_nan.csv')
        expected_df = wine_data.fillna('no')

        variable = 'wine_data'
        actual_df = getattr(user_code, variable, None)
        condition = False
        if actual_df is None:
            failure_message = f"The `{variable}` variable is not declared."
        elif not isinstance(actual_df, pd.DataFrame):
            failure_message = f"`{variable}` is not a `DataFrame`."
        elif actual_df.empty:
            failure_message = f"`{variable}` is empty."
        elif actual_df.equals(expected_df):
            condition = True
            failure_message = None
        else:
            idx, expected_row, actual_row = get_first_differing_row(expected_df, actual_df)
            failure_message = f"Expected `{variable}` to contain `{expected_row}` at row {idx}, but got `{actual_row}`."

        _dynamic_test(
            self,
            condition,
            f"`{variable}` contains the correct data.",
            failure_message
        )


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

test_main.py

Pandas is an extremely user-friendly library for data analysis. It's also designed to handle large datasets, using data structures like DataFrame and Series. This makes it an invaluable tool for Data Science. In this guide, you'll get acquainted with a range of statistical functions, including how to find correlations, modes, medians, and maximum and minimum values within a dataset. You'll also learn how to handle missing values and manipulate specific values, as well as how to remove them.

In this section, we'll explore the fundamentals of Series and DataFrame structures. You'll also learn about the distinctions between these two types of structures.

Data can be sourced in various formats, such as CSV, JSON, SQL, HTML, and more. With Pandas, you're not limited to a single format — you can work with data across a multitude of file types. In this chapter, we'll specifically focus on the CSV and TXT formats.

Here, you'll learn how to process raw data by removing extraneous information and managing null values in a dataset.

Pandas First Steps

Challenge: Filling Null Values

Ratkaisu

Challenge: Filling Null Values

Ratkaisu