Missing data is a common issue in real-world datasets, where some entries may be absent, incomplete, or recorded as "not available." Before you analyze or model your data, it is essential to identify where these missing values occur. Failing to address missing data can lead to inaccurate results, biased insights, or errors in downstream processing. Recognizing the presence and location of missing values is the first step in ensuring your data is clean and reliable for analysis.

import pandas as pd
import numpy as np

# Create a sample DataFrame with missing values
data = {
    "Name": ["Alice", "Bob", "Charlie", "David"],
    "Age": [25, np.nan, 30, 22],
    "City": ["New York", "Los Angeles", np.nan, "Chicago"],
    "Score": [85, 90, np.nan, 88]
}

df = pd.DataFrame(data)
print(df)


import unittest
import user_code
import ast
import re   
import unittest
import pandas as pd
import numpy as np
import importlib
import io
from contextlib import redirect_stdout

class TestTask(unittest.TestCase):
    def test_shape_preserved(self):
        import user_code
        importlib.reload(user_code)
        data = {
            "A": [1, 2, np.nan],
            "B": [4, 5, 6],
            "C": [np.nan, 8, 9]
        }
        df = pd.DataFrame(data)
        result = user_code.detect_missing(df)
        _dynamic_test(
            self,
            isinstance(result, pd.DataFrame) and result.shape == df.shape,
            "Returned DataFrame has the same shape as input.",
            f"Returned DataFrame shape {getattr(result, 'shape', None)} does not match input shape {df.shape}."
        )

    def test_correct_missing_locations(self):
        import user_code
        importlib.reload(user_code)
        data = {
            "A": [1, 2, np.nan],
            "B": [4, np.nan, 6],
            "C": [np.nan, 8, 9]
        }
        df = pd.DataFrame(data)
        expected = df.isna()
        result = user_code.detect_missing(df)
        _dynamic_test(
            self,
            result.equals(expected),
            "Correct boolean DataFrame for missing values.",
            f"Expected:\\n{expected}\\nGot:\\n{result}"
        )

    def test_no_missing_values(self):
        import user_code
        importlib.reload(user_code)
        data = {
            "A": [1, 2, 3],
            "B": [4, 5, 6],
            "C": [7, 8, 9]
        }
        df = pd.DataFrame(data)
        expected = df.isna()
        result = user_code.detect_missing(df)
        _dynamic_test(
            self,
            result.equals(expected),
            "Returns all False DataFrame when no missing values.",
            f"Expected:\\n{expected}\\nGot:\\n{result}"
        )

    def test_all_missing_values(self):
        import user_code
        importlib.reload(user_code)
        data = {
            "A": [np.nan, np.nan],
            "B": [np.nan, np.nan]
        }
        df = pd.DataFrame(data)
        expected = df.isna()
        result = user_code.detect_missing(df)
        _dynamic_test(
            self,
            result.equals(expected),
            "Returns all True DataFrame when all values are missing.",
            f"Expected:\\n{expected}\\nGot:\\n{result}"
        )

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 normalize_text(text):
    text = text.lower()
    text = re.sub(r"\s{2,}", " ", text)
    text = re.sub(r"\s*([,:?])\s*", r"\1 ", text)
    return text.strip()

def change_var(code: str, var_name: str, value: str) -> str:
    tree = ast.parse(code)
    lines = code.splitlines()
    for i, node in enumerate(tree.body):
        if isinstance(node, ast.Assign):
            for target in node.targets:
                if isinstance(target, ast.Name) and target.id == var_name:
                    start_line = node.lineno - 1
                    line = lines[start_line]
                    indent = ' ' * (len(line) - len(line.lstrip()))
                    lines[start_line] = f"{indent}{var_name} = {value}"
                    next_line = len(lines)
                    for next_node in tree.body[i+1:]:
                        if hasattr(next_node, 'lineno'):
                            next_line = next_node.lineno - 1
                            break
                    if next_line > start_line + 1:
                        lines[start_line+1:next_line] = []
                    
                    return '\\n'.join(lines)
    return code

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


test_main.py

Master essential data cleaning techniques in Python using powerful libraries and practical tasks. This course is designed for learners with intermediate Python skills who want to efficiently prepare and clean data for analysis and machine learning.

Explore the core concepts of data cleaning, why it matters, and the essential tools and techniques in Python.

Delve deeper into techniques for managing missing and duplicate data using pandas and numpy.

Focus on techniques for making data consistent, correcting errors, and detecting outliers.

Challenge: Identify Missing Data

Ratkaisu

Awesome!

Challenge: Identify Missing Data

Ratkaisu