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.

Om de eerste paar rijen van een dataset te bekijken, gebruik de methode `head()`. Deze methode accepteert een **geheel getal** als argument dat aangeeft hoeveel rijen getoond worden (standaard worden de **eerste 5 rijen** weergegeven). Toon de eerste 10 rijen van de dataset:

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

Om de **laatste paar rijen** van een `DataFrame` te bekijken, gebruik de methode `tail()`. Deze werkt op dezelfde manier als de `head()`-methode:

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

Een andere nuttige methode voor het verkennen van DataFrames is `sample()`. Deze methode haalt willekeurige records uit een DataFrame op. Standaard wordt **één willekeurig record** opgehaald, tenzij anders opgegeven.
```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 een uiterst gebruiksvriendelijke bibliotheek voor data-analyse. Het is ook ontworpen om grote datasets te verwerken, met behulp van datastructuren zoals DataFrame en Series. Dit maakt het een onmisbaar hulpmiddel voor Data Science. In deze gids maak je kennis met diverse statistische functies, waaronder het vinden van correlaties, modi, medianen en maximale en minimale waarden binnen een dataset. Je leert ook hoe je omgaat met ontbrekende waarden en specifieke waarden kunt manipuleren of verwijderen.

Verdiep je in de basisprincipes van de pandas-bibliotheek. Leer het aanmaken en manipuleren van Series en DataFrames, onderzoek hun structuur en ontwikkel vertrouwen in het uitvoeren van essentiële data-operaties.

Beheers het laden en beheren van gegevens uit CSV- en TXT-bestanden. Praktische ervaring opdoen met het importeren van datasets en het voorbereiden ervan voor verdere analyse met behulp van pandas-tools.

Leer gegevens effectief te verkennen, opschonen en samenvatten. Begrijp hoe ontbrekende waarden te behandelen, inzichten te verkrijgen en basisstatistische bewerkingen uit te voeren met pandas.

Gegevens Bekijken

Oplossing

Awesome!

Gegevens Bekijken

Oplossing