|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/100-exercises-python-data-science-scikit-learn/
课程评论：没有评论
课程名称：Python中的Scikit-learn：100多项数据科学练习 课程概述：本课程是一个全面的实战指南，专注于Python中最重要的机器学习库之一——Scikit-learn。课程采用实践驱动的学习方法，帮助学习者理解和应用各种机器学习算法和技术。课程分为不同的模块，每个模块专注于Scikit-learn库的特定方面，涵盖数据预处理（包括特征提取和选择）、多种机器学习模型（如线性回归、决策树、支持向量机和集成方法）以及模型评估和超参数调整等内容。 每个模块都配有精心设计的练习，以加深对概念的理解，并提供将所学知识应用于实际问题的机会。这些练习模拟了数据科学家在实际工作中面临的挑战，同时提供详尽的解决方案，让学习者能够对照自己的解决方案，深入理解如何最好地使用Scikit-learn进行机器学习任务。 该课程非常适合希望扩展数据科学工具箱的任何人。无论您是希望进入机器学习领域的初学者，还是希望提升技能的资深数据科学家，本课程都提供了丰富的学习体验。通过Scikit-learn，您可以充分利用Python的强大能力，建立和实施各种机器学习模型。 课程主题包括： - 准备数据以适应机器学习模型 - 处理缺失值，使用SimpleImputer类 - 分类、回归和聚类 - 离散化和特征提取 - 使用PolynomialFeatures、LabelEncoder和OneHotEncoder类 - 标准化处理，使用StandardScaler类 - 数据划分为训练集和测试集 - 使用LogisticRegression类进行逻辑回归 - 混淆矩阵和分类报告 - 使用DecisionTreeClassifier类和RandomForestClassifier类进行 classification - 网格搜索，使用GridSearchCV类 - 文本处理工具，如CountVectorizer和TfidfVectorizer类 - 聚类算法，如KMeans、HierarchicalClustering、DBSCAN - 降维技术，如PCA分析 - 关联规则和局部异常因子分析 - 使用IsolationForest和KNeighborsClassifier类 - 使用MultinomialNB和GradientBoostingRegressor类进行模型训练与评估 无论您是想要入门还是提升技能，Scikit-learn都能帮助您释放机器学习的潜力！
This course is a comprehensive, hands-on guide to one of the most essential libraries for machine learning in Python, Scikit-learn. This course employs a practical, exercise-driven approach that helps learners understand and apply various machine learning algorithms and techniques.The course is organized into different sections, each devoted to a specific aspect of the Scikit-learn library. It covers everything from data preprocessing, including feature extraction and selection, to various machine learning models such as linear regression, decision trees, support vector machines, and ensemble methods, to model evaluation and hyperparameter tuning.Each section is packed with carefully designed exercises that reinforce each concept and give you the chance to apply what you've learned. You will solve real-world problems that mirror the challenges faced by data scientists in the field. Detailed solutions accompany each exercise, enabling you to compare your work and gain a better understanding of how to best use Scikit-learn for machine learning tasks.This course is perfect for anyone interested in expanding their data science toolkit. Whether you're a beginner looking to dive into machine learning, or a seasoned data scientist wanting to refine your skills, this course offers an enriching learning experience.Scikit-learn - Unleash the Power of Machine Learning!Scikit-learn is a versatile machine learning library in Python that provides a wide range of algorithms and tools for building and implementing machine learning models. It is widely used by data scientists, researchers, and developers to solve complex problems through classification, regression, clustering, and more. With Scikit-learn, you can efficiently preprocess data, select appropriate features, train and evaluate models, and perform model selection and hyperparameter tuning. It offers a consistent API, making it easy to experiment with different algorithms and techniques. Scikit-learn also provides useful utilities for data preprocessing, model evaluation, and model persistence. Its user-friendly interface and extensive documentation make it a go-to choice for machine learning practitioners looking to leverage the power of Python for their projects.Topics you will find in this course:preparing data to machine learning modelsworking with missing values, SimpleImputer classclassification, regression, clusteringdiscretizationfeature extractionPolynomialFeatures classLabelEncoder classOneHotEncoder classStandardScaler classdummy encodingsplitting data into train and test setLogisticRegression classconfusion matrixclassification reportLinearRegression classMAE - Mean Absolute ErrorMSE - Mean Squared Errorsigmoid() functionentorpyaccuracy scoreDecisionTreeClassifier classGridSearchCV classRandomForestClassifier classCountVectorizer classTfidfVectorizer classKMeans classAgglomerativeClustering classHierarchicalClustering classDBSCAN classdimensionality reduction, PCA analysisAssociation RulesLocalOutlierFactor classIsolationForest classKNeighborsClassifier classMultinomialNB classGradientBoostingRegressor class
