
import unittest
import user_code
import ast
import re   
import importlib
import csv
import unittest
import importlib
import io
import sys
import pandas as pd
from contextlib import redirect_stdout
from scipy.stats import ttest_ind

class TestTask(unittest.TestCase):
    def setUp(self):
        self.df = pd.DataFrame({
            'group': ['A', 'A', 'A', 'B', 'B', 'B'],
            'outcome': [5.1, 4.9, 5.0, 6.2, 6.0, 6.1]
        })
        self.df_ns = pd.DataFrame({
            'group': ['A', 'A', 'A', 'B', 'B', 'B'],
            'outcome': [5.1, 4.9, 5.0, 5.2, 5.0, 5.1]
        })

    def test_returns_tuple_of_tstat_and_pval(self):
        import user_code
        importlib.reload(user_code)
        result = user_code.compare_groups_ttest(self.df)
        _dynamic_test(
            self,
            isinstance(result, tuple) and len(result) == 2,
            "Function returns a tuple (t-statistic, p-value)",
            f"Expected a tuple of length 2, got: {result}"
        )
        tstat, pval = result
        _dynamic_test(
            self,
            isinstance(tstat, float) and isinstance(pval, float),
            "Returned t-statistic and p-value are floats",
            f"Returned types: {type(tstat)}, {type(pval)}"
        )

    def test_correct_extraction_of_groups(self):
        import user_code
        importlib.reload(user_code)
        # We can check if the t-test result matches scipy's ttest_ind on the correct groups
        expected_a = self.df[self.df['group'] == 'A']['outcome']
        expected_b = self.df[self.df['group'] == 'B']['outcome']
        expected_t, expected_p = ttest_ind(expected_a, expected_b, nan_policy='omit')
        result_t, result_p = user_code.compare_groups_ttest(self.df)
        _dynamic_test(
            self,
            abs(result_t - expected_t) < 1e-8 and abs(result_p - expected_p) < 1e-8,
            "T-test values match scipy's ttest_ind on correct group extraction",
            f"Expected t: {expected_t}, p: {expected_p}; got t: {result_t}, p: {result_p}"
        )

    def test_uses_ttest_ind(self):
        import user_code
        importlib.reload(user_code)
        # This test is implicit in the above: if the output matches scipy's, it's used
        result_t, result_p = user_code.compare_groups_ttest(self.df)
        expected_a = self.df[self.df['group'] == 'A']['outcome']
        expected_b = self.df[self.df['group'] == 'B']['outcome']
        expected_t, expected_p = ttest_ind(expected_a, expected_b, nan_policy='omit')
        _dynamic_test(
            self,
            abs(result_t - expected_t) < 1e-8 and abs(result_p - expected_p) < 1e-8,
            "Function uses scipy.stats.ttest_ind correctly",
            f"Expected t: {expected_t}, p: {expected_p}; got t: {result_t}, p: {result_p}"
        )

    def test_prints_interpretation_significant(self):
        import user_code
        importlib.reload(user_code)
        f = io.StringIO()
        with redirect_stdout(f):
            user_code.compare_groups_ttest(self.df)
        output = normalize_text(f.getvalue())
        _dynamic_test(
            self,
            "statistically significant" in output and "p < 0.05" in output,
            "Prints correct interpretation for significant result",
            f"Expected interpretation for p < 0.05 in output, got: {output}"
        )

    def test_prints_interpretation_not_significant(self):
        import user_code
        importlib.reload(user_code)
        f = io.StringIO()
        with redirect_stdout(f):
            user_code.compare_groups_ttest(self.df_ns)
        output = normalize_text(f.getvalue())
        _dynamic_test(
            self,
            "not statistically significant" in output and "p >= 0.05" in output,
            "Prints correct interpretation for not significant result",
            f"Expected interpretation for p >= 0.05 in output, got: {output}"
        )

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: Comparing Experimental Groups

解答