Machine learning model evaluation in Python

在本实践课程中，我们将重点关注使用 Python 编程语言对监督机器学习模型进行性能评估。

在训练模型或在超参数调整期间，我们必须检查其性能以评估它是否过拟合。这就是为什么，根据特定的项目和需求，我们需要仔细选择性能指标。事实上，选择错误的指标可能会给我们一个不可靠的模型。相反，使用适当的绩效指标可以使我们的项目获得更高的价值。

通过本课程，您将学习

回归模型的性能指标（R 平方、平均绝对误差、平均绝对百分比误差）

二元分类模型的性能指标（混淆矩阵、精度、召回率、准确率、平衡准确率、ROC 曲线及其面积）

多类分类模型的性能指标（准确度、平衡准确度、宏观平均准确度）

本课程的所有课程都以简要介绍开始，以 Python 编程语言及其强大的 scikit-learn 库的实际示例结束。将使用的环境是 Jupyter，它是数据科学行业的标准。所有的 Jupyter 笔记本都可以下载。

本课程是我在 Python 在线课程中的监督机器学习的一部分，因此您会发现一些课程已经包含在更大的课程中。

A practical course on how to evaluate the performance of a machine learning model using Python

Published 05/2022
MP4 | Video: h264, 1280×720 | Audio: AAC, 44.1 KHz, 2 Ch
Genre: eLearning | Language: English + srt | Duration: 11 lectures (1h 18m) | Size: 420.4 MB

What you’ll learn
Regression metrics (R-squared, MAE, MAPE)
Confusion matrix
ROC curve and its area
Precision, Recall, F1 score
Accuracy, balanced accuracy

Requirements
Python porgramming language

Description
In this practical course, we are going to focus on the performance evaluation of supervised machine learning models using Python programming language.

After a model has been trained or during hyperparameter tuning, we have to check its performance in order to assess whether it overfits or not. That’s why, according to particular projects and needs, we need to select performance metrics carefully. In fact, the choice of the wrong metrics may give us an unreliable model. On the contrary, using the proper performance indicators can lead our project to a higher value.

With this course, you are going to learn

Performance metrics for regression models (R-squared, Mean Absolute Error, Mean Absolute Percentage Error)

Performance metrics for binary classification models (confusion matrix, precision, recall, accuracy, balanced accuracy, ROC curve and its area)

Performance metrics for multi-class classification models (accuracy, balanced accuracy, macro averaged precision)

All the lessons of this course start with a brief introduction and end with a practical example in Python programming language and its powerful scikit-learn library. The environment that will be used is Jupyter, which is a standard in the data science industry. All the Jupyter notebooks are downloadable.

This course is part of my Supervised Machine Learning in Python online course, so you’ll find some lessons that are already included in the larger course.

Who this course is for
Python developers
Data Scientists
Computer engineers
Researchers
Students