When preparing research for publication, it is essential to present results in a clear and visually appealing manner. Visualizing trends over time, such as the number of publications and citations per year, can reveal important patterns and support your findings. Using a line plot is a common way to compare such metrics simultaneously, but to make the figure publication-ready, you must carefully customize its appearance. This includes choosing distinct colors and markers for each line, adding a legend for clarity, and labeling axes and the plot title appropriately so that the figure is self-explanatory even outside the context of your paper. In this challenge, you will apply your data visualization skills to create a polished figure that could appear in a research article.


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

class TestTask(unittest.TestCase):
    def setUp(self):
        self.df = pd.DataFrame({
            'year': [2018, 2019, 2020, 2021, 2022],
            'publications': [10, 15, 20, 25, 30],
            'citations': [50, 80, 120, 200, 300]
        })
        import user_code
        importlib.reload(user_code)
        self.user_code = user_code

    def test_returns_fig_ax(self):
        result = self.user_code.plot_publications_vs_citations(self.df)
        _dynamic_test(
            self,
            result is not None and isinstance(result, tuple) and len(result) == 2,
            "Function returns a tuple (fig, ax)",
            f"Expected a tuple (fig, ax), got {result}"
        )
        fig, ax = result
        _dynamic_test(
            self,
            hasattr(fig, "savefig") and hasattr(ax, "plot"),
            "Returned objects are matplotlib Figure and Axes",
            f"Returned objects do not appear to be Figure and Axes: {type(fig)}, {type(ax)}"
        )

    def test_plot_lines_properties(self):
        result = self.user_code.plot_publications_vs_citations(self.df)
        fig, ax = result
        lines = ax.get_lines()
        # There should be two lines
        _dynamic_test(
            self,
            len(lines) == 2,
            "There are two lines plotted.",
            f"Expected 2 lines, got {len(lines)}"
        )
        # Check properties of each line
        found_pub = found_cit = False
        for line in lines:
            ydata = list(line.get_ydata())
            color = line.get_color()
            marker = line.get_marker()
            label = line.get_label()
            if ydata == [10, 15, 20, 25, 30]:
                # Publications
                _dynamic_test(
                    self,
                    color in ('b', 'blue'),
                    "Publications line is blue.",
                    f"Publications line color is {color}"
                )
                _dynamic_test(
                    self,
                    marker == 'o',
                    "Publications line uses circle marker.",
                    f"Publications line marker is {marker}"
                )
                _dynamic_test(
                    self,
                    label == 'Publications',
                    "Publications line label is correct.",
                    f"Publications line label is {label}"
                )
                found_pub = True
            elif ydata == [50, 80, 120, 200, 300]:
                # Citations
                _dynamic_test(
                    self,
                    color in ('g', 'green'),
                    "Citations line is green.",
                    f"Citations line color is {color}"
                )
                _dynamic_test(
                    self,
                    marker == 's',
                    "Citations line uses square marker.",
                    f"Citations line marker is {marker}"
                )
                _dynamic_test(
                    self,
                    label == 'Citations',
                    "Citations line label is correct.",
                    f"Citations line label is {label}"
                )
                found_cit = True
        _dynamic_test(
            self,
            found_pub and found_cit,
            "Both Publications and Citations lines found.",
            "Did not find both Publications and Citations lines."
        )

    def test_legend_labels(self):
        result = self.user_code.plot_publications_vs_citations(self.df)
        fig, ax = result
        legend = ax.get_legend()
        _dynamic_test(
            self,
            legend is not None,
            "Legend is present on the plot.",
            "Legend is missing from the plot."
        )
        texts = [t.get_text() for t in legend.get_texts()]
        _dynamic_test(
            self,
            'Publications' in texts and 'Citations' in texts,
            "Legend contains correct labels.",
            f"Legend labels found: {texts}"
        )

    def test_axis_labels_and_title(self):
        result = self.user_code.plot_publications_vs_citations(self.df)
        fig, ax = result
        xlabel = ax.get_xlabel()
        ylabel = ax.get_ylabel()
        title = ax.get_title()
        _dynamic_test(
            self,
            xlabel == 'Year',
            "X-axis label is set to 'Year'.",
            f"Expected x-axis label 'Year', got '{xlabel}'"
        )
        _dynamic_test(
            self,
            ylabel == 'Count',
            "Y-axis label is set to 'Count'.",
            f"Expected y-axis label 'Count', got '{ylabel}'"
        )
        _dynamic_test(
            self,
            title == 'Publications and Citations Over Time',
            "Plot title is set correctly.",
            f"Expected title 'Publications and Citations Over Time', 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: Publication-Ready Figure

Ratkaisu