Scatter plots are a powerful way to visualize the relationship between two numerical variables. In policy evaluation, you often want to see if higher education attainment in a region is associated with higher employment rates. By plotting each region as a point with its education rate on the x-axis and its employment rate on the y-axis, you can visually assess whether there is a correlation—such as whether regions with more education tend to have higher employment.

education_rates = [78.5, 82.3, 69.4, 91.2, 74.8, 88.1, 85.6]
employment_rates = [65.2, 70.1, 58.7, 80.3, 60.5, 75.4, 73.2]

When creating a scatter plot, it is important to clearly label each axis so that viewers understand what each point represents. The x-axis should indicate **education attainment rate**, while the y-axis should show **employment rate**. A descriptive title helps communicate the purpose of the visualization. Once the plot is created, you can interpret patterns: if the points trend upward from left to right, this suggests a **positive correlation** between education and employment—meaning higher education rates are associated with higher employment rates.


import unittest
import user_code
import ast
import re   
import importlib
import csv
import unittest
import importlib
import sys
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
import user_code

class TestTask(unittest.TestCase):
    def setUp(self):
        self.education_rates = [78.5, 82.3, 69.4, 91.2, 74.8, 88.1, 85.6]
        self.employment_rates = [65.2, 70.1, 58.7, 80.3, 60.5, 75.4, 73.2]

    def test_scatter_plot_points(self):
        plt.clf()
        user_code.plot_education_vs_employment(self.education_rates, self.employment_rates)
        found = False
        for ax in plt.get_fignums():
            fig = plt.figure(ax)
            for axes in fig.axes:
                for col in axes.collections:
                    offsets = col.get_offsets()
                    if len(offsets) == len(self.education_rates):
                        matches = all([
                            offsets[i,0] == self.education_rates[i] and offsets[i,1] == self.employment_rates[i]
                            for i in range(len(self.education_rates))
                        ])
                        if matches:
                            found = True
        _dynamic_test(
            self,
            found,
            "Scatter plot contains the correct points for education and employment rates.",
            "Scatter plot does not contain the correct points for education and employment rates.",
        )

    def test_x_axis_label(self):
        plt.clf()
        user_code.plot_education_vs_employment(self.education_rates, self.employment_rates)
        label = plt.gca().get_xlabel()
        _dynamic_test(
            self,
            label == "Education Attainment Rate (%)",
            "X-axis label is correctly set.",
            f"Expected x-axis label 'Education Attainment Rate (%)', got '{label}'.",
        )

    def test_y_axis_label(self):
        plt.clf()
        user_code.plot_education_vs_employment(self.education_rates, self.employment_rates)
        label = plt.gca().get_ylabel()
        _dynamic_test(
            self,
            label == "Employment Rate (%)",
            "Y-axis label is correctly set.",
            f"Expected y-axis label 'Employment Rate (%)', got '{label}'.",
        )

    def test_title(self):
        plt.clf()
        user_code.plot_education_vs_employment(self.education_rates, self.employment_rates)
        title = plt.gca().get_title()
        _dynamic_test(
            self,
            title == "Correlation Between Education and Employment Rates",
            "Plot title is correctly set.",
            f"Expected title 'Correlation Between Education and Employment Rates', got '{title}'.",
        )

    def test_plot_displayed(self):
        # Test that plt.show() is called by patching
        import builtins
        import types
        orig_show = plt.show
        self.show_called = False
        def fake_show(*args, **kwargs):
            self.show_called = True
        plt.show = fake_show
        try:
            user_code.plot_education_vs_employment(self.education_rates, self.employment_rates)
        finally:
            plt.show = orig_show
        _dynamic_test(
            self,
            self.show_called,
            "Plot is displayed using plt.show().",
            "plt.show() was not called to display the plot.",
        )

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 Python course tailored for government analysts, focusing on data analysis, visualization, and decision-making using real-world scenarios relevant to public sector work. Learn to harness Python's power to extract insights, visualize trends, and support evidence-based policy.

Explore how Python can be used to analyze government datasets, extract actionable insights, and support evidence-based policy decisions.

Apply statistical methods to government datasets to evaluate policies, measure impact, and support data-driven decisions.

Discover how Python can automate repetitive analytical tasks, streamline reporting, and improve efficiency in government operations.

Challenge: Visualize Correlation Between Education and Employment

Solution