To handle null values **while keeping all rows** in the `DataFrame`, use the `fillna()` method. It allows you to replace each empty cell with a **specific value** (such as a string or number) instead of removing 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

Focus on the core skills for wrangling tabular data with pandas in Python. Learn to build efficient data pipelines, manipulate DataFrames, filter and select records, handle missing values, perform aggregations, and merge datasets for data science workflows. Each chapter is action-oriented and ends with practical challenges.

Challenge: Filling Null Values

Challenge: Filling Null Values

Ratkaisu