
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({
            'subject_id': [1, 2, 3, 4, 5, 6],
            'group': ['control', 'treatment', 'control', 'control', 'treatment', 'control'],
            'measurement': [10.5, 15.2, 13.1, 9.8, 16.4, 14.0]
        })

    def test_only_control_group(self):
        import user_code
        importlib.reload(user_code)
        result = user_code.extract_control_above_mean(self.df)
        _dynamic_test(
            self,
            all(result['group'] == 'control'),
            "All rows have group 'control'",
            f"Not all rows are from the 'control' group: {result['group'].tolist()}"
        )

    def test_measurement_above_mean(self):
        import user_code
        importlib.reload(user_code)
        mean_measurement = self.df['measurement'].mean()
        result = user_code.extract_control_above_mean(self.df)
        _dynamic_test(
            self,
            all(result['measurement'] > mean_measurement),
            "All measurements are above the mean",
            f"Some measurements are not above the mean: {result['measurement'].tolist()}"
        )

    def test_sorted_descending(self):
        import user_code
        importlib.reload(user_code)
        result = user_code.extract_control_above_mean(self.df)
        measurements = result['measurement'].tolist()
        _dynamic_test(
            self,
            measurements == sorted(measurements, reverse=True),
            "Measurements are sorted in descending order",
            f"Measurements are not sorted in descending order: {measurements}"
        )

    def test_empty_result(self):
        import user_code
        importlib.reload(user_code)
        # All control measurements below mean
        test_df = pd.DataFrame({
            'subject_id': [1, 2, 3],
            'group': ['control', 'control', 'treatment'],
            'measurement': [1.0, 2.0, 100.0]
        })
        result = user_code.extract_control_above_mean(test_df)
        _dynamic_test(
            self,
            result.empty,
            "Returns empty DataFrame when no control measurements are above mean",
            f"Expected empty DataFrame, got: {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()
    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: Extracting Experimental Groups

Solution