Predicting student performance based on study habits is a practical application of **regression analysis** in education. By examining the relationship between the number of hours a student studies and their exam scores, you can model how changes in study time might affect outcomes. **Linear regression** is a statistical technique that fits a straight line to data points, allowing you to make predictions about one variable based on another. In this context, you will use Python's `scikit-learn` library to build a simple linear regression model, visualize the results using `matplotlib`, and predict the exam score for a student who studies a specific number of hours.

import matplotlib.pyplot as plt
import numpy as np
from sklearn.linear_model import LinearRegression

# Example data: hours studied and corresponding exam scores
hours = [2, 3, 5, 6, 8, 10]
scores = [50, 55, 65, 70, 80, 90]

# Prepare the data for regression (reshape for sklearn)
X = np.array(hours).reshape(-1, 1)
y = np.array(scores)

# Fit the linear regression model
model = LinearRegression()
model.fit(X, y)

# Predict scores for the training data
predicted_scores = model.predict(X)

# Plot the data and the regression line
plt.scatter(hours, scores, color='blue', label='Actual Scores')
plt.plot(hours, predicted_scores, color='red', label='Regression Line')
plt.xlabel('Hours Studied')
plt.ylabel('Exam Score')
plt.title('Student Scores vs Study Hours')
plt.legend()
plt.show()


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 matplotlib
matplotlib.use('Agg')

class TestTask(unittest.TestCase):
    def test_model_fits_and_predicts(self):
        import user_code
        importlib.reload(user_code)
        hours = [1, 2, 3, 4.5, 5, 6, 7.5, 8, 9]
        scores = [35, 45, 50, 60, 62, 70, 78, 80, 88]
        f = io.StringIO()
        with redirect_stdout(f):
            user_code.analyze_and_predict(hours, scores, 7)
        output = f.getvalue()
        try:
            predicted = float(output.strip().split('\\n')[-1])
        except Exception:
            predicted = None
        # The expected value is close to 75.0 based on the data
        _dynamic_test(
            self,
            predicted is not None and abs(predicted - 75.0) < 3.0,
            "Prediction for 7 hours is within expected range.",
            f"Predicted value for 7 hours is not within expected range: {predicted}",
        )

    def test_plot_generated(self):
        import user_code
        importlib.reload(user_code)
        hours = [1, 2, 3, 4.5, 5, 6, 7.5, 8, 9]
        scores = [35, 45, 50, 60, 62, 70, 78, 80, 88]
        import matplotlib.pyplot as plt
        plt.close('all')
        f = io.StringIO()
        with redirect_stdout(f):
            user_code.analyze_and_predict(hours, scores, 7)
        # Check that a figure was created
        figs = [fig for fig in map(plt.figure, plt.get_fignums())]
        _dynamic_test(
            self,
            len(figs) > 0,
            "Plot is generated by the function.",
            "No plot was generated.",
        )

    def test_function_signature(self):
        import user_code
        importlib.reload(user_code)
        func = getattr(user_code, 'analyze_and_predict', None)
        _dynamic_test(
            self,
            callable(func),
            "Function 'analyze_and_predict' is defined and callable.",
            "Function 'analyze_and_predict' is not defined or not callable.",
        )
        import inspect
        sig = inspect.signature(func)
        params = list(sig.parameters.keys())
        _dynamic_test(
            self,
            params == ['hours', 'scores', 'predict_hours'],
            "Function signature matches required parameters.",
            f"Expected parameters ['hours', 'scores', 'predict_hours'], got {params}",
        )

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

This focused course introduces the fundamental concepts of statistics using Python. Learners will explore how to calculate mean, median, and mode, and perform basic data analysis using lists. The course is designed for beginners who want a practical and hands-on introduction to descriptive statistics in Python.

Challenge: Predict Student Scores Based on Study Hours

Solution