Summary  
This chapter covers techniques for locating and retrieving targeted pieces of information from larger data structures by using pattern matching, selectors, or parsing libraries.

General domain of usage  
Web scraping

import unittest
import pandas as pd
import io
import sys


def _dynamic_test(test_case, condition, success_msg, failure_msg):
    if condition:
        test_case._testMethodName = success_msg
        test_case.assertTrue(True, success_msg)
    else:
        test_case._testMethodName = failure_msg
        test_case.fail(failure_msg)


def frames_equal_ignore_col_order(df1, df2):
    """ÐÐµÑÐµÐ²ÑÑÑÑ ÑÑÐ²Ð½ÑÑÑÑ DataFrame Ð½ÐµÐ·Ð°Ð»ÐµÐ¶Ð½Ð¾ Ð²ÑÐ´ Ð¿Ð¾ÑÑÐ´ÐºÑ ÐºÐ¾Ð»Ð¾Ð½Ð¾Ðº."""
    if set(df1.columns) != set(df2.columns):
        return False
    common_cols = sorted(df1.columns)
    df1_sorted = df1[common_cols].reset_index(drop=True)
    df2_sorted = df2[common_cols].reset_index(drop=True)
    return df1_sorted.equals(df2_sorted)


class TestCondition1(unittest.TestCase):
    def test_condition_1(self):
        """
        1. 'condition_1' selects rows where 'Price' is between 15000 (inclusive) and 20000 (exclusive).
        """
        import user_code
        df = pd.read_csv(
            "https://codefinity-content-media.s3.eu-west-1.amazonaws.com/4bf24830-59ba-4418-969b-aaf8117d522e/cars.csv",
            index_col=0,
        )
        ref = df["Price"].between(15000, 20000, inclusive="left")

        condition = hasattr(user_code, "condition_1") and user_code.condition_1.equals(ref)
        _dynamic_test(
            self,
            condition,
            "The variable 'condition_1' is defined correctly for Price between 15000 (inclusive) and 20000 (exclusive).",
            "'condition_1' is incorrect. Check the .between() bounds or inclusive parameter."
        )


class TestCondition2(unittest.TestCase):
    def test_condition_2(self):
        """
        2. 'condition_2' selects rows where 'Year' is between 2015 (exclusive) and 2020 (exclusive).
        """
        import user_code
        df = pd.read_csv(
            "https://codefinity-content-media.s3.eu-west-1.amazonaws.com/4bf24830-59ba-4418-969b-aaf8117d522e/cars.csv",
            index_col=0,
        )
        ref = df["Year"].between(2015, 2020, inclusive="neither")

        condition = hasattr(user_code, "condition_2") and user_code.condition_2.equals(ref)
        _dynamic_test(
            self,
            condition,
            "The variable 'condition_2' is defined correctly for Year between 2015 and 2020 (exclusive).",
            "'condition_2' is incorrect. Check the .between() bounds or inclusive parameter."
        )


class TestCondition3(unittest.TestCase):
    def test_condition_3(self):
        """
        3. 'condition_3' selects rows where 'Fuel_type' is in ['Plug-in Hybrid', 'Hybrid'].
        """
        import user_code
        df = pd.read_csv(
            "https://codefinity-content-media.s3.eu-west-1.amazonaws.com/4bf24830-59ba-4418-969b-aaf8117d522e/cars.csv",
            index_col=0,
        )
        ref = df["Fuel_type"].isin(["Plug-in Hybrid", "Hybrid"])

        condition = hasattr(user_code, "condition_3") and user_code.condition_3.equals(ref)
        _dynamic_test(
            self,
            condition,
            "The variable 'condition_3' is defined correctly for Fuel_type in ['Plug-in Hybrid', 'Hybrid'].",
            "'condition_3' is incorrect. Check the .isin() list or variable name."
        )


class TestCombinedCondition(unittest.TestCase):
    def test_data_extracted(self):
        """
        4. Combine all three conditions using '&' operator and extract data with .loc[].
        """
        import user_code
        df = pd.read_csv(
            "https://codefinity-content-media.s3.eu-west-1.amazonaws.com/4bf24830-59ba-4418-969b-aaf8117d522e/cars.csv",
            index_col=0,
        )
        ref = df.loc[
            df["Price"].between(15000, 20000, inclusive="left")
            & df["Year"].between(2015, 2020, inclusive="neither")
            & df["Fuel_type"].isin(["Plug-in Hybrid", "Hybrid"])
        ]

        condition = (
            hasattr(user_code, "data_extracted")
            and isinstance(user_code.data_extracted, pd.DataFrame)
            and frames_equal_ignore_col_order(user_code.data_extracted, ref)
        )
        _dynamic_test(
            self,
            condition,
            "The DataFrame 'data_extracted' correctly combines all three conditions with '&'.",
            "The combination of conditions or the .loc[] filtering is incorrect."
        )


class TestOutput(unittest.TestCase):
    def test_print_output(self):
        """
        5. Print the first few rows of 'data_extracted' using .head().
        """
        import user_code

        captured_output = io.StringIO()
        sys.stdout = captured_output
        print(user_code.data_extracted.head())
        sys.stdout = sys.__stdout__

        output_text = captured_output.getvalue().strip()
        condition = len(output_text) > 0
        _dynamic_test(
            self,
            condition,
            "The output displays the first few rows of 'data_extracted' using .head().",
            "The 'data_extracted' DataFrame is not printed correctly. Use print(data_extracted.head())."
        )


if __name__ == "__main__":
    unittest.main()

test_code.py

Deze cursus bevat veel nuttige functies voor een toekomstige data-analist. Je leert verschillende manieren om data te extraheren en zelfs voorwaarden hierop toe te passen. Daarna raak je vertrouwd met methoden voor het groeperen van data. Ook leer je hoe je data kunt preprocessen. Elke sectie heeft zijn eigen dataset, waardoor de cursus boeiend blijft.

In deze sectie leert u hoe u specifieke kolommen kunt weergeven op basis van hun titels of indexen. Ook maakt u kennis met de methoden om rijen te selecteren op basis van indexen.

Hier leert u hoe u gegevens extraheert die aan specifieke voorwaarden voldoen. Daarnaast leert u hoe u deze voorwaarden kunt combineren en zelfs uw eigen voorwaarden kunt creëren.

In deze sectie breidt u uw kennis uit over het instellen van verschillende gegevenscondities. U leert controleren of uw gegevens zich in een gedefinieerde lijst met waarden bevinden of tussen twee waarden liggen. U leert ook hoe u de grootste en kleinste waarden kunt vinden.

Deze sectie behoort tot de meest boeiende van de cursus. Hier leert u hoe u gegevens op verschillende manieren kunt groeperen. Dit helpt u als data-analist om informatie over specifieke gegevensgroepen te achterhalen.

Deze sectie is een van de belangrijkste voor een data-analist, omdat het onmogelijk is om met gegevens te werken als deze ontbrekende waarden of een onjuist formaat bevatten. Hier leert u hoe u met dergelijke ongeschikte waarden omgaat.

Specifieke Gegevens Extraheren

Oplossing

Awesome!

Specifieke Gegevens Extraheren

Oplossing