In research, predicting outcomes based on multiple variables is a common task. **Linear regression** is a widely used method for modeling the relationship between one or more features and a continuous outcome. By using the `scikit-learn` library, you can efficiently fit a regression model, extract its coefficients, and evaluate its performance with the `R^2` score. This challenge provides you with a `DataFrame` containing `feature1`, `feature2`, and `outcome` columns. Your goal is to fit a linear regression model using both features to predict the outcome, return the model's coefficients and `R^2` score, and print a brief interpretation of the results.


import unittest
import user_code
import ast
import re   
import importlib
import csv
import unittest
import importlib
import io
from contextlib import redirect_stdout
import numpy as np
import pandas as pd

class TestTask(unittest.TestCase):
    def setUp(self):
        self.df = pd.DataFrame({
            'feature1': [1, 2, 3, 4, 5],
            'feature2': [2, 1, 4, 3, 5],
            'outcome': [2, 3, 6, 8, 11]
        })

    def test_model_fits_both_features(self):
        import user_code
        importlib.reload(user_code)
        # Run function and check coefficients length
        result = user_code.fit_and_interpret_regression(self.df)
        _dynamic_test(
            self,
            result is not None and hasattr(result, "__getitem__") and len(result[0]) == 2,
            "Function returns coefficients for both features",
            f"Expected 2 coefficients, got: {result[0] if result is not None else None}"
        )

    def test_returns_r2_score(self):
        import user_code
        importlib.reload(user_code)
        result = user_code.fit_and_interpret_regression(self.df)
        r2 = result[1] if result is not None and len(result) > 1 else None
        _dynamic_test(
            self,
            isinstance(r2, float) and 0.0 <= r2 <= 1.0,
            "Function returns R^2 score as a float",
            f"Expected float R^2 between 0 and 1, got: {r2}"
        )

    def test_interpretation_printed(self):
        import user_code
        importlib.reload(user_code)
        f = io.StringIO()
        with redirect_stdout(f):
            user_code.fit_and_interpret_regression(self.df)
        output = f.getvalue()
        has_feature1 = "feature1 coefficient" in output.lower()
        has_feature2 = "feature2 coefficient" in output.lower()
        has_r2 = "r^2 score" in output.lower()
        _dynamic_test(
            self,
            has_feature1 and has_feature2 and has_r2,
            "Interpretation string includes coefficients and R^2 score",
            f"Interpretation missing required components: {output}"
        )

    def test_coefficients_are_correct_shape(self):
        import user_code
        importlib.reload(user_code)
        result = user_code.fit_and_interpret_regression(self.df)
        coeffs = result[0] if result is not None else None
        _dynamic_test(
            self,
            (isinstance(coeffs, (list, np.ndarray)) and len(coeffs) == 2),
            "Coefficients are a sequence of length 2",
            f"Coefficients shape/type incorrect: {coeffs}"
        )

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: Predicting Research Outcomes

Ratkaisu

Challenge: Predicting Research Outcomes

Ratkaisu