
import unittest
import user_code
import ast
import re   
import importlib
import csv
import unittest
import pandas as pd
import importlib

class TestTask(unittest.TestCase):
    def setUp(self):
        self.df = pd.DataFrame({
            'participant': ['A', 'B', 'C', 'D', 'E'],
            'age': [25, None, 30, 22, None],
            'score': [85, 90, None, 88, None]
        })

    def test_fill_missing_age_with_median(self):
        import user_code
        importlib.reload(user_code)
        cleaned = user_code.clean_survey_data(self.df.copy())
        median_age = self.df['age'].median()
        missing_age_indices = self.df[self.df['age'].isna()].index
        all_filled = all(cleaned.loc[i, 'age'] == median_age for i in missing_age_indices)
        _dynamic_test(
            self,
            all_filled,
            "All missing 'age' values filled with median",
            f"Not all missing 'age' values were filled with the median: {cleaned['age'].tolist()}"
        )

    def test_fill_missing_score_with_mean(self):
        import user_code
        importlib.reload(user_code)
        cleaned = user_code.clean_survey_data(self.df.copy())
        mean_score = self.df['score'].mean()
        missing_score_indices = self.df[self.df['score'].isna()].index
        all_filled = all(cleaned.loc[i, 'score'] == mean_score for i in missing_score_indices)
        _dynamic_test(
            self,
            all_filled,
            "All missing 'score' values filled with mean",
            f"Not all missing 'score' values were filled with the mean: {cleaned['score'].tolist()}"
        )

    def test_no_missing_values_in_cleaned_df(self):
        import user_code
        importlib.reload(user_code)
        cleaned = user_code.clean_survey_data(self.df.copy())
        no_missing_age = cleaned['age'].isna().sum() == 0
        no_missing_score = cleaned['score'].isna().sum() == 0
        _dynamic_test(
            self,
            no_missing_age and no_missing_score,
            "No missing values in 'age' or 'score' after cleaning",
            f"Missing values remain: age({cleaned['age'].isna().sum()}), score({cleaned['score'].isna().sum()})"
        )

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()
    changed = False
    # Collect all assignment nodes to modify
    assign_nodes = [
        (i, node)
        for i, node in enumerate(tree.body)
        if isinstance(node, ast.Assign)
        and any(isinstance(target, ast.Name) and target.id == var_name for target in node.targets)
    ]

    # If nothing to change, return unmodified code
    if not assign_nodes:
        return code

    # Perform replacements for all matching assignments (from last to first to not break line offsets)
    for i, node in reversed(assign_nodes):
        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] = []
        changed = True

    return '\\n'.join(lines) if changed else code

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


test_main.py

A practical course designed for researchers who want to leverage Python for data analysis, visualization, and scientific computation. The course focuses on real-world research scenarios, using Python and its scientific libraries to solve common research problems, analyze data, and present findings effectively.

Learn how to use Python and pandas to clean, manipulate, and summarize research data, preparing it for analysis and publication.

Master the art of visualizing research data using matplotlib and seaborn to communicate findings effectively.

Apply statistical methods and automate repetitive research tasks using Python, pandas, and scipy.

Challenge: Cleaning Survey Data

Ratkaisu

Challenge: Cleaning Survey Data

Ratkaisu