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

class TestTask(unittest.TestCase):
    def setUp(self):
        self.df = pd.DataFrame({
            'experiment': ['A', 'A', 'A', 'B', 'B', 'B', 'B'],
            'group': ['control', 'treatment', 'control', 'treatment', 'control', 'control', 'treatment'],
            'score': [88, 92, 85, 78, 90, 87, 80]
        })
        self.df_single = pd.DataFrame({
            'experiment': ['A', 'A', 'B'],
            'group': ['control', 'treatment', 'control'],
            'score': [100, 95, 70]
        })
        self.df_mixed = pd.DataFrame({
            'experiment': ['X', 'X', 'Y', 'Y', 'Y'],
            'group': ['g1', 'g1', 'g2', 'g2', 'g2'],
            'score': [10, 20, 30, 30, 30]
        })
        import user_code
        importlib.reload(user_code)
        self.user_code = user_code

    def test_returns_dataframe_with_multiindex(self):
        result = self.user_code.grouped_summary_table(self.df)
        is_df = isinstance(result, pd.DataFrame)
        is_multiindex = isinstance(result.index, pd.MultiIndex)
        correct_names = list(result.index.names) == ['experiment', 'group']
        _dynamic_test(
            self,
            is_df and is_multiindex and correct_names,
            "Returns DataFrame with MultiIndex ['experiment', 'group']",
            f"Returned type: {type(result)}, index names: {result.index.names}"
        )

    def test_column_names(self):
        result = self.user_code.grouped_summary_table(self.df)
        columns = list(result.columns)
        _dynamic_test(
            self,
            'mean' in columns and 'std' in columns,
            "DataFrame contains 'mean' and 'std' columns",
            f"Columns found: {columns}"
        )

    def test_mean_computation(self):
        result = self.user_code.grouped_summary_table(self.df)
        # (A, control): (88+85)/2=86.5
        mean_a_control = result.loc[('A','control'),'mean']
        _dynamic_test(
            self,
            np.isclose(mean_a_control, 86.5),
            "Mean for (A, control) is correct",
            f"Expected 86.5, got {mean_a_control}"
        )
        # (B, treatment): (78+80)/2=79
        mean_b_treatment = result.loc[('B','treatment'),'mean']
        _dynamic_test(
            self,
            np.isclose(mean_b_treatment, 79.0),
            "Mean for (B, treatment) is correct",
            f"Expected 79.0, got {mean_b_treatment}"
        )

    def test_std_computation(self):
        result = self.user_code.grouped_summary_table(self.df)
        # (A, control): std of [88,85]
        std_a_control = result.loc[('A','control'),'std']
        expected_std = np.std([88,85], ddof=1)
        _dynamic_test(
            self,
            np.isclose(std_a_control, expected_std),
            f"Std for (A, control) is correct ({expected_std})",
            f"Expected {expected_std}, got {std_a_control}"
        )
        # (B, control): std of [90,87]
        std_b_control = result.loc[('B','control'),'std']
        expected_std_b = np.std([90,87], ddof=1)
        _dynamic_test(
            self,
            np.isclose(std_b_control, expected_std_b),
            f"Std for (B, control) is correct ({expected_std_b})",
            f"Expected {expected_std_b}, got {std_b_control}"
        )

    def test_single_observation_nan_std(self):
        result = self.user_code.grouped_summary_table(self.df_single)
        # (B, control) only one observation
        std_b_control = result.loc[('B','control'),'std']
        _dynamic_test(
            self,
            pd.isna(std_b_control),
            "Std is NaN for single observation group",
            f"Expected NaN for std, got {std_b_control}"
        )

    def test_handles_multiple_groups(self):
        result = self.user_code.grouped_summary_table(self.df_mixed)
        # (X, g1): mean 15, std 7.071...; (Y, g2): mean 30, std 0
        mean_x_g1 = result.loc[('X','g1'),'mean']
        std_x_g1 = result.loc[('X','g1'),'std']
        mean_y_g2 = result.loc[('Y','g2'),'mean']
        std_y_g2 = result.loc[('Y','g2'),'std']
        _dynamic_test(
            self,
            np.isclose(mean_x_g1, 15.0) and np.isclose(std_x_g1, 7.0710678118654755),
            "Correct mean and std for (X, g1)",
            f"Expected mean 15.0, std 7.071, got mean {mean_x_g1}, std {std_x_g1}"
        )
        _dynamic_test(
            self,
            np.isclose(mean_y_g2, 30.0) and np.isclose(std_y_g2, 0.0),
            "Correct mean and std for (Y, g2)",
            f"Expected mean 30.0, std 0.0, got mean {mean_y_g2}, std {std_y_g2}"
        )

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: Grouped Summary Table

Ratkaisu