Summary  
This chapter covers how to apply multiple boolean conditions to filter data using logical and (&) and or (|) operators.  

General domain of usage  
Astronomy data analysis

Sometimes we need several conditions to be applied. For instance, we want to extract data on **hazardous** asteroids with a **small minimum diameter**. But how do we write two conditions simultaneously? Look at the table:

The example was included to help you deal with this topic. This code extracts data on large and hazardous asteroids, where the minimum estimated diameter is larger than `3.5` kilometers and `'hazardous'` is `True`.

import pandas as pd
data = pd.read_csv('https://codefinity-content-media.s3.eu-west-1.amazonaws.com/4bf24830-59ba-4418-969b-aaf8117d522e/planet', index_col = 0)
data_extracted = data.loc[(data['est_diameter_min'] > 3.5) & (data['hazardous'] == True)]
print(data_extracted)

In the output, you can see all the rows that satisfy these two conditions:
- `est_diameter_min` > 3.5;
- `hazardous` == True.

Look at the following example with the  `or` statement. This code will extract data on extremely small or large asteroids with a minimum estimated diameter less than `0.0005` kilometers and a maximum estimated diameter larger than `20` kilometers:

import pandas as pd
data = pd.read_csv('https://codefinity-content-media.s3.eu-west-1.amazonaws.com/4bf24830-59ba-4418-969b-aaf8117d522e/planet', index_col = 0)
data_extracted = data.loc[(data['est_diameter_min'] < 0.0005) | (data['est_diameter_max'] > 20)]
print(data_extracted)

In the output, you can see all the rows that satisfy one of these two conditions:
- `est_diameter_min` < 0.0005;
- `est_diameter_max` > 20.

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ÐºÐ° ÑÑÐ²Ð½Ð¾Ñ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 TestExtraction(unittest.TestCase):
    def test_filter_conditions(self):
        """
        1. Extract data where 'absolute_magnitude' >= 25 and 'hazardous' == False.
        """
        import user_code

        # ÐÐ°Ð²Ð°Ð½ÑÐ°Ð¶ÑÑÐ¼Ð¾ Ð¾ÑÐ¸Ð³ÑÐ½Ð°Ð»ÑÐ½Ð¸Ð¹ Ð´Ð°ÑÐ°ÑÑÐµÐ¹Ð¼
        df = pd.read_csv(
            "https://codefinity-content-media.s3.eu-west-1.amazonaws.com/4bf24830-59ba-4418-969b-aaf8117d522e/planet",
            index_col=0
        )

        # Ð¤Ð¾ÑÐ¼ÑÑÐ¼Ð¾ ÐµÑÐ°Ð»Ð¾Ð½
        ref = df.loc[(df["absolute_magnitude"] >= 25) & (df["hazardous"] == False)]

        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 is filtered correctly for bright and not hazardous asteroids.",
            "Filtering conditions are incorrect. Check both conditions and the use of '&' inside .loc[]."
        )


class TestOutput(unittest.TestCase):
    def test_output_sample(self):
        """
        2. Output 5 random rows from the resulting DataFrame using .sample(5).
        """
        import user_code

        captured_output = io.StringIO()
        sys.stdout = captured_output
        print(user_code.data_extracted.sample(5))
        sys.stdout = sys.__stdout__

        output_text = captured_output.getvalue().strip()
        condition = len(output_text) > 0
        _dynamic_test(
            self,
            condition,
            "The output displays 5 random rows from 'data_extracted' using .sample(5).",
            "The output is missing or incorrect. Use print(data_extracted.sample(5))."
        )


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


Multiple Conditions

Oplossing