`pandas` offers the `count()` method, which counts all **non-null** cells (neither `None` nor `NaN`) for each column.
```python
df = pd.read_csv(file.csv)
number_of_cells = df.count()
```

To find the **count** of non-null values in a specific column, use the following syntax:
```python
df = pd.read_csv(file.csv)
number_of_cells = df['name of the column'].count()
```

`pandas` also provides the `sum()` method. This method calculates the sum of values for each column, but it only works with **numeric** or **boolean** columns.
```python
df = pd.read_csv(file.csv)
total = df.sum()
```

Since the `isna()` method returns a **boolean DataFrame**, you can use the following syntax to calculate the number of missing values for each of the columns:

```python
missing_values_count = df.isna().sum()
```

To find the sum of values in a particular column, use the following syntax:
```python
df = pd.read_csv(file.csv)
total = df['name of the column'].sum()
```

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)


class TestUserCode(unittest.TestCase):

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

    def test_number_of_cells_is_correct(self):
        import user_code
        cars_data = {'model': [None, 'audi A6', 'audi A4', None, 'audi A1'],
                     'year': [2017, 2016, 2017, None, 2016],
                     'fueltype': [None, 'diesel', 'diesel', 'petrol', 'petrol'],
                     'price': [12500, 16500, 16800, 17300, 16500]}
        audi_cars = pd.DataFrame(cars_data)
        expected_value = audi_cars.count()

        try:
            condition = user_code.number_of_cells.equals(expected_value)
            failure_message = f"Expected `number_of_cells` to be `{expected_value}`, but got `{user_code.number_of_cells}`."
        except AttributeError:
            condition = False
            if not getattr(user_code, 'number_of_cells', None):
                failure_message = "The `number_of_cells` variable is not declared."
            else:
                failure_message = "`number_of_cells` is not a `Series`."

        _dynamic_test(
            self,
            condition,
            f"`number_of_cells` contains the correct values.",
            failure_message
        )

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

    def test_total_price_is_correct(self):
        import user_code
        cars_data = {'model': [None, 'audi A6', 'audi A4', None, 'audi A1'],
                     'year': [2017, 2016, 2017, None, 2016],
                     'fueltype': [None, 'diesel', 'diesel', 'petrol', 'petrol'],
                     'price': [12500, 16500, 16800, 17300, 16500]}
        audi_cars = pd.DataFrame(cars_data)
        expected_value = audi_cars['price'].sum()

        try:
            condition = user_code.total_price == expected_value
            failure_message = f"Expected `total_price` to be `{expected_value}`, but got `{user_code.total_price}`."
        except AttributeError:
            condition = False
            failure_message = "The `total_price` variable is not declared."

        _dynamic_test(
            self,
            condition,
            f"`total_price` is correct.",
            failure_message
        )

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

    def test_null_count_is_series(self):
        import user_code

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

        _dynamic_test(
            self,
            condition,
            "The variable `null_count` is a `Series`.",
            failure_message
        )

    def test_null_count_is_correct(self):
        import user_code
        cars_data = {'model': [None, 'audi A6', 'audi A4', None, 'audi A1'],
                     'year': [2017, 2016, 2017, None, 2016],
                     'fueltype': [None, 'diesel', 'diesel', 'petrol', 'petrol'],
                     'price': [12500, 16500, 16800, 17300, 16500]}
        audi_cars = pd.DataFrame(cars_data)
        expected_value = audi_cars.isna().sum()

        variable = 'null_count'
        actual_value = getattr(user_code, variable, None)
        if actual_value is None:
            condition = False
            failure_message = f"The `{variable}` variable is not declared."
        elif isinstance(actual_value, pd.Series):
            condition = actual_value.equals(expected_value)
            if actual_value.empty:
                failure_message = f"`{variable}` is empty."
            else:
                failure_message = f"Expected `{variable}` to contain `{expected_value.values}`, but got `{actual_value.values}`."
        else:
            condition = False
            failure_message = f"`{variable}` is not a `Series`."

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

        _dynamic_test(
            self,
            condition,
            f"`null_count` contains the correct values.",
            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

sum() and count()

Lösning

sum() and count()

Lösning