Summary  
This chapter covers how to access a DataFrame’s metadata by retrieving its column names and the data types of each column using the `columns` and `dtypes` attributes.

General domain of usage  
Data analysis

To display all column names as a list, use the following line of code:

```python
column_names = df.columns
```

To get a summary of all data types in the `DataFrame`, use the following attribute:
`.dtypes`.
```python
data_types = df.dtypes
```

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

    def test_column_names_is_index(self):
        import user_code

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

        _dynamic_test(
            self,
            condition,
            "The variable `column_names` is an `Index`.",
            failure_message
        )

    def test_column_names_is_correct(self):
        import user_code

        try:
            wine_data = pd.read_csv(
                'https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a43d24b6-df61-4e11-9c90-5b36552b3437/wine.csv')
            expected_value = wine_data.columns
            condition = user_code.column_names.equals(expected_value)
            failure_message = f"Expected `column_names` to be `{expected_value}`, but got `{user_code.column_names}`."
        except AttributeError:
            condition = False
            if not getattr(user_code, 'column_names', None):
                failure_message = "The `column_names` variable is not declared."
            else:
                failure_message = f"`column_names` is not an `Index`."

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

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

    def test_data_types_is_series(self):
        import user_code

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

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

    def test_data_types_is_correct(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.csv')
        expected_value = wine_data.dtypes
        
        variable = 'data_types'
        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"`first_row` 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.

Dive into the fundamentals of the pandas library. Learn to create and manipulate Series and DataFrames, explore their structure, and build confidence in performing essential data operations.

Master how to load and manage data from CSV and TXT files. Gain practical experience importing datasets and preparing them for further analysis using pandas tools.

Learn to explore, clean, and summarize data effectively. Understand how to handle missing values, extract insights, and perform basic statistical operations with pandas.

Column Names and Data Types

Solution

Awesome!

Column Names and Data Types

Solution