
import unittest
import user_code
import ast
import re   
import importlib
import csv
import unittest
import importlib
import sys
import io

class TestTask(unittest.TestCase):
    def test_groupby_segment(self):
        import user_code
        importlib.reload(user_code)
        data = {
            "customer_id": [1, 2, 3, 4, 5, 6],
            "segment": ["A", "B", "A", "B", "C", "C"],
            "spend": [120.0, 80.0, 150.0, 60.0, 200.0, 180.0]
        }
        df = user_code.pd.DataFrame(data)
        segment_summary = df.groupby("segment")["spend"].mean().reset_index()
        expected_groups = set(["A", "B", "C"])
        actual_groups = set(segment_summary["segment"])
        _dynamic_test(
            self,
            actual_groups == expected_groups,
            "Data correctly grouped by segment.",
            f"Expected segments {expected_groups}, got {actual_groups}.",
        )

    def test_average_spend_per_segment(self):
        import user_code
        importlib.reload(user_code)
        data = {
            "customer_id": [1, 2, 3, 4, 5, 6],
            "segment": ["A", "B", "A", "B", "C", "C"],
            "spend": [120.0, 80.0, 150.0, 60.0, 200.0, 180.0]
        }
        df = user_code.pd.DataFrame(data)
        segment_summary = df.groupby("segment")["spend"].mean().reset_index()
        expected = {"A": 135.0, "B": 70.0, "C": 190.0}
        actual = dict(zip(segment_summary["segment"], segment_summary["spend"]))
        _dynamic_test(
            self,
            all(abs(actual[k] - v) < 0.001 for k, v in expected.items()),
            "Average spend per segment is calculated correctly.",
            f"Expected averages {expected}, got {actual}.",
        )

    def test_output_contains_summary(self):
        import user_code
        importlib.reload(user_code)
        f = io.StringIO()
        sys_stdout = sys.stdout
        sys.stdout = f
        user_code.summarize_customer_segments()
        sys.stdout = sys_stdout
        output = normalize_text(f.getvalue())
        # Check all segments and their averages appear in output
        checks = [
            "a 135.0" in output,
            "b 70.0" in output,
            "c 190.0" in output,
        ]
        _dynamic_test(
            self,
            all(checks),
            "Output summary contains all segments and correct averages.",
            f"Output summary missing expected segment averages: {output}",
        )

    def test_data_used_is_provided(self):
        import user_code
        importlib.reload(user_code)
        # Check that the function uses the provided data
        data = {
            "customer_id": [1, 2, 3, 4, 5, 6],
            "segment": ["A", "B", "A", "B", "C", "C"],
            "spend": [120.0, 80.0, 150.0, 60.0, 200.0, 180.0]
        }
        df = user_code.pd.DataFrame(data)
        segment_summary = df.groupby("segment")["spend"].mean().reset_index()
        expected = {"A": 135.0, "B": 70.0, "C": 190.0}
        actual = dict(zip(segment_summary["segment"], segment_summary["spend"]))
        _dynamic_test(
            self,
            all(abs(actual[k] - v) < 0.001 for k, v in expected.items()),
            "Provided data is used for processing.",
            f"Expected averages from provided data {expected}, got {actual}.",
        )

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

Advance your Python automation skills by learning to generate analytical summaries, business reports, and visual dashboards automatically. This course guides you through practical workflows for automating data analysis, reporting, and visualization tasks using Python, pandas, matplotlib, and seaborn.

Learn to automate the generation of analytical summaries, business reports, and visual dashboards using Python. Alternate between concept introduction and hands-on automation tasks for real-world reporting scenarios.

Challenge: Segment Customers and Summarize Spend

Ratkaisu