Summary
Demonstrates how to use DataFrame methods to preview and explore subsets of data—specifically, printing the first or last N rows with `head()` and `tail()`, and fetching random rows with `sample()`.

General domain of usage
Exploratory data analysis in tabular datasets.

To view the first few rows of a dataset, use the `head()` method. This method accepts an **integer** argument that specifies how many rows to display (by default, it shows the **first 5 rows**). Display the first 10 rows of the dataset:

```python
df = pd.read_csv('file.csv')
# Extracting the first 10 rows
first_lines = df.head(10)
```

To see the **last few rows** of a `DataFrame`, use the `tail()` method. It works the same way as the `head()` method:

```python
df = pd.read_csv('file.csv')
# Extracting the last 10 rows
last_lines = df.tail(10)
```

Another useful method for exploring DataFrames is `sample()`. This method fetches random records from a DataFrame. By default, it retrieves a **single random record** unless specified otherwise.
```python
df = pd.read_csv('file.csv')
# Extracting 10 random rows
random_lines = df.sample(10)
```

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

    def test_first_lines_is_dataframe(self):
        import user_code

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

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

    def test_first_lines_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.csv')
        expected_df = wine_data.head(10)

        variable = 'first_lines'
        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
        )

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

    def test_last_lines_is_dataframe(self):
        import user_code

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

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

    def test_last_lines_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.csv')
        expected_df = wine_data.tail(15)

        variable = 'last_lines'
        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
        )

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

    def test_random_rows_is_dataframe(self):
        import user_code

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

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

    def test_random_rows_has_correct_values(self):
        import user_code
        import numpy as np
        np.random.seed(5)
        wine_data = pd.read_csv(
            'https://codefinity-content-media.s3.eu-west-1.amazonaws.com/a43d24b6-df61-4e11-9c90-5b36552b3437/wine.csv')
        expected_df = wine_data.sample(12)

        variable = 'random_rows'
        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.

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.

Viewing the Data

解答