Visualizing relationships between variables is a key part of analyzing research data, especially when you want to understand how one variable may influence another. In research, a common task is to examine the connection between two continuous variables, such as the number of hours students spend studying and their resulting exam scores. Scatter plots are an effective way to display this relationship, and calculating the correlation coefficient quantifies the strength and direction of the association. Annotating the plot with the correlation value helps make your findings immediately clear to readers.


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

class TestTask(unittest.TestCase):
    def setUp(self):
        self.df = pd.DataFrame({
            'study_hours': [1, 2, 3, 4, 5],
            'exam_score': [10, 20, 30, 40, 50]
        })
        self.df2 = pd.DataFrame({
            'study_hours': [1, 2, 3, 4, 5, 6],
            'exam_score': [10, 11, 13, 18, 25, 36]
        })

    def test_scatter_plot_created(self):
        import user_code
        importlib.reload(user_code)
        plt.clf()
        user_code.plot_study_vs_score(self.df)
        found = any(isinstance(c, matplotlib.collections.PathCollection) for c in plt.gca().collections)
        _dynamic_test(
            self,
            found,
            "Scatter plot is created using plt.scatter",
            "No scatter plot found on axes. Did you use plt.scatter?"
        )

    def test_correlation_value_correct(self):
        import user_code
        importlib.reload(user_code)
        plt.clf()
        # Patch plt.annotate to capture annotation text
        annots = []
        orig_annotate = plt.annotate
        def fake_annotate(text, *args, **kwargs):
            annots.append(text)
            return orig_annotate(text, *args, **kwargs)
        plt.annotate = fake_annotate
        user_code.plot_study_vs_score(self.df)
        plt.annotate = orig_annotate
        expected_corr = self.df['study_hours'].corr(self.df['exam_score'])
        found = any(f"{expected_corr:.2f}" in a for a in annots)
        _dynamic_test(
            self,
            found,
            "Correlation coefficient is calculated and annotated correctly",
            f"Correlation annotation with value {expected_corr:.2f} not found in annotations: {annots}"
        )

    def test_axis_labels(self):
        import user_code
        importlib.reload(user_code)
        plt.clf()
        user_code.plot_study_vs_score(self.df)
        ax = plt.gca()
        xlab = ax.get_xlabel()
        ylab = ax.get_ylabel()
        _dynamic_test(
            self,
            xlab == "Study Hours",
            "x-axis label is set to 'Study Hours'",
            f"Expected x-axis label 'Study Hours', got '{xlab}'"
        )
        _dynamic_test(
            self,
            ylab == "Exam Score",
            "y-axis label is set to 'Exam Score'",
            f"Expected y-axis label 'Exam Score', got '{ylab}'"
        )

    def test_title(self):
        import user_code
        importlib.reload(user_code)
        plt.clf()
        user_code.plot_study_vs_score(self.df2)
        ax = plt.gca()
        title = ax.get_title()
        _dynamic_test(
            self,
            title == "Study Hours vs Exam Score",
            "Plot title is set to 'Study Hours vs Exam Score'",
            f"Expected plot title 'Study Hours vs Exam Score', got '{title}'"
        )

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: Exploring Variable Relationships

Ratkaisu

Challenge: Exploring Variable Relationships

Ratkaisu