Predictive modeling plays a crucial role in engineering maintenance, allowing you to anticipate equipment failures and schedule repairs before breakdowns occur. In the previous chapter, you learned how predictive models can use historical data to estimate when a system might need attention. Now, you will apply this knowledge to a practical scenario using scikit-learn's `LinearRegression`: you have data on total operating hours and corresponding time-to-failure in days for several machines. Your goal is to build a model that predicts how long a machine will last before failing, given its operating hours.


import unittest
import user_code
import ast
import re   
import importlib
import csv
import unittest
import importlib
import numpy as np
from sklearn.linear_model import LinearRegression

class TestTask(unittest.TestCase):
    def setUp(self):
        self.hours = [1000, 2000, 3000, 4000, 6000, 8000]
        self.failure_days = [120, 110, 100, 95, 80, 60]
        self.query = 5000
        # Train reference model
        X = np.array(self.hours).reshape(-1, 1)
        y = np.array(self.failure_days)
        self.ref_model = LinearRegression().fit(X, y)
        self.ref_coef = self.ref_model.coef_[0]
        self.ref_intercept = self.ref_model.intercept_
        self.ref_pred = self.ref_model.predict(np.array([[self.query]]))[0]

    def test_model_coefficient(self):
        import user_code
        importlib.reload(user_code)
        res = user_code.predict_failure_time(self.hours, self.failure_days, self.query)
        _dynamic_test(
            self,
            res is not None and isinstance(res, tuple) and np.isclose(res[0], self.ref_coef, atol=1e-8),
            f"Returned coefficient matches fitted model: {self.ref_coef}",
            f"Returned coefficient {res[0] if res else None} does not match expected: {self.ref_coef}",
        )

    def test_model_intercept(self):
        import user_code
        importlib.reload(user_code)
        res = user_code.predict_failure_time(self.hours, self.failure_days, self.query)
        _dynamic_test(
            self,
            res is not None and isinstance(res, tuple) and np.isclose(res[1], self.ref_intercept, atol=1e-8),
            f"Returned intercept matches fitted model: {self.ref_intercept}",
            f"Returned intercept {res[1] if res else None} does not match expected: {self.ref_intercept}",
        )

    def test_prediction(self):
        import user_code
        importlib.reload(user_code)
        res = user_code.predict_failure_time(self.hours, self.failure_days, self.query)
        _dynamic_test(
            self,
            res is not None and isinstance(res, tuple) and np.isclose(res[2], self.ref_pred, atol=1e-8),
            f"Predicted value for {self.query} matches fitted model: {self.ref_pred}",
            f"Predicted value {res[2] if res else None} does not match expected: {self.ref_pred}",
        )

    def test_fit_linear_regression(self):
        import user_code
        importlib.reload(user_code)
        res = user_code.predict_failure_time(self.hours, self.failure_days, self.query)
        _dynamic_test(
            self,
            res is not None and isinstance(res, tuple),
            "Function returns a tuple of results after fitting the model.",
            f"Function did not return a tuple. Got: {res}",
        )

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 engineers who want to leverage Python to solve real-world engineering problems. Explore data analysis, mathematical modeling, and simulation using Python's powerful libraries and tools, all through engaging, hands-on examples and challenges.

Learn how to use Python to analyze, summarize, and visualize engineering data. This section covers essential data handling and visualization techniques tailored for engineering applications.

Dive into mathematical modeling and simulation techniques for engineering systems using Python. Learn to model physical processes, solve equations, and simulate system behavior.

Apply data science techniques to engineering problems, including classification, clustering, and predictive modeling using Python's scikit-learn and seaborn libraries.

Challenge: Predict Equipment Failure Time

Ratkaisu

Challenge: Predict Equipment Failure Time

Ratkaisu