
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.df1 = pd.DataFrame({'id': [1, 2, 3], 'score': [90, None, 85]})
        self.df2 = pd.DataFrame({'id': [4, 5, 6], 'score': [None, 78, 80]})
        self.df3 = pd.DataFrame({'id': [7, 8], 'score': [None, None]})
        self.site_data = [self.df1, self.df2, self.df3]

    def test_returns_list_of_same_length(self):
        import user_code
        importlib.reload(user_code)
        cleaned = user_code.clean_scores_batch(self.site_data)
        _dynamic_test(
            self,
            isinstance(cleaned, list) and len(cleaned) == len(self.site_data),
            "Returned list has correct length.",
            f"Expected list of length {len(self.site_data)}, got {len(cleaned)}."
        )

    def test_missing_scores_filled_with_mean(self):
        import user_code
        importlib.reload(user_code)
        cleaned = user_code.clean_scores_batch(self.site_data)
        # df1: mean is (90+85)/2 = 87.5
        expected1 = pd.Series([90.0, 87.5, 85.0], name='score')
        # df2: mean is (78+80)/2 = 79
        expected2 = pd.Series([79.0, 78.0, 80.0], name='score')
        # df3: mean is nan, so should remain nan
        expected3 = pd.Series([None, None], name='score', dtype='float64')
        # Check values for each cleaned df
        _dynamic_test(
            self,
            cleaned[0] is not None and cleaned[1] is not None and cleaned[2] is not None,
            "Cleaned DataFrames are not None.",
            "Some cleaned DataFrames are None."
        )
        pd.testing.assert_series_equal(cleaned[0]['score'], expected1, check_names=False)
        pd.testing.assert_series_equal(cleaned[1]['score'], expected2, check_names=False)
        pd.testing.assert_series_equal(cleaned[2]['score'], expected3, check_names=False)

    def test_non_missing_scores_unchanged(self):
        import user_code
        importlib.reload(user_code)
        cleaned = user_code.clean_scores_batch(self.site_data)
        # For df1, first and last should remain 90 and 85
        _dynamic_test(
            self,
            cleaned[0]['score'].iloc[0] == 90.0 and cleaned[0]['score'].iloc[2] == 85.0,
            "Non-missing scores are unchanged.",
            f"Non-missing scores were altered: {cleaned[0]['score'].tolist()}"
        )
        # For df2, second and third should remain 78 and 80
        _dynamic_test(
            self,
            cleaned[1]['score'].iloc[1] == 78.0 and cleaned[1]['score'].iloc[2] == 80.0,
            "Non-missing scores in second DataFrame are unchanged.",
            f"Non-missing scores were altered: {cleaned[1]['score'].tolist()}"
        )

    def test_original_dataframes_not_modified(self):
        import user_code
        importlib.reload(user_code)
        # Make deep copies of originals
        orig1 = self.df1.copy(deep=True)
        orig2 = self.df2.copy(deep=True)
        orig3 = self.df3.copy(deep=True)
        _ = user_code.clean_scores_batch([self.df1, self.df2, self.df3])
        pd.testing.assert_frame_equal(self.df1, orig1)
        pd.testing.assert_frame_equal(self.df2, orig2)
        pd.testing.assert_frame_equal(self.df3, orig3)

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: Batch Data Cleaning

Solution

Challenge: Batch Data Cleaning

Solution