Practical Data Science with Sap. Machine Learning Chorzów

Learn how to fuse today's data science tools and techniques with your SAP enterprise resource planning (ERP) system. With this practical guide, SAP veterans Greg Foss and Paul Modderman demonstrate how to use several data analysis tools to solve interesting problems with your SAP data.Data engineers and scientists will explore ways to add SAP data to their analysis processes, while SAP business analysts will learn practical methods for answering questions about the business. By focusing on grounded explanations of both SAP processes and data science tools, this book gives data scientists and business analysts powerful methods for discovering deep data truths.You'll explore:Examples of how data analysis can help you solve several SAP challengesNatural language processing for unlocking the secrets in textData science techniques for data clustering and segmentationMethods for detecting anomalies in your SAP dataData visualization techniques for making your data come to life Spis treści: Preface How to Read This Book Conventions Used in This Book Using Code Examples OReilly Online Learning How to Contact Us Acknowledgments 1. Introduction Telling Better Stories with Data A Quick Look: Data Science for SAP Professionals A Quick Look: SAP Basics for Data Scientists Getting Data Out of SAP BAPIs: Using the NetWeaver RFC Library OData Other ways to get data Web services Direct database access Screen dumps to Excel Roles and Responsibilities Summary 2. Data Science for SAP Professionals Machine Learning Supervised Machine Learning Linear regression Logistic regression Decision trees Random forest Unsupervised Machine Learning k-means clustering Naive Bayes Hierarchical clustering Semi-Supervised Machine Learning Reinforcement Machine Learning Hidden Markov models Q-learning Neural Networks Feed-forward propagation Backward propagation Gradient descent Learning rate Neuron Functions Single layer perceptron Multilayer perceptron Convolutional network Recursive neural network Temporal networks Autoencoder Generative adversarial network Summary 3. SAP for Data Scientists Getting Started with SAP The ABAP Data Dictionary Tables Structures Data Elements and Domains Where-Used ABAP QuickViewer SE16 Export OData Services Core Data Services Summary 4. Exploratory Data Analysis with R The Four Phases of EDA Phase 1: Collecting Our Data Importing with R Phase 2: Cleaning Our Data Null Removal Binary Indicators Removing Extraneous Columns Whitespace Numbers Phase 3: Analyzing Our Data DataExplorer Discrete Features Continuous Features Phase 4: Modeling Our Data TensorFlow and Keras Training and Testing Split Shaping and One-Hot Encoding Recipes Preparing Data for the Neural Network Results Summary 5. Anomaly Detection with R and Python Types of Anomalies Tools in R AnomalyDetection Anomalize Getting the Data SAP ECC System SAP NetWeaver Gateway SQL Server SQL Server Integration Services (SSIS) Finding Anomalies PowerBI and R PowerBI and Python Summary 6. Predictive Analytics in R and Python Predicting Sales in R Step 1: Identify Data Step 2: Gather Data Step 3: Explore Data Step 4: Model Data Plots for prediction Step 5: Evaluate Model Predicting Sales in Python Step 1: Identify Data Step 2: Gather Data Step 3: Explore Data Step 4: Model Data Step 5: Evaluate Model Summary 7. Clustering and Segmentation in R Understanding Clustering and Segmentation RFM Pareto Principle k-Means k-Medoid Hierarchical Clustering Time-Series Clustering Step 1: Collecting the Data Step 2: Cleaning the Data Step 3: Analyzing the Data Revisiting the Pareto Principle Finding Optimal Clusters k-Means Clustering k-Medoid Clustering Hierarchical Clustering Manual RFM Step 4: Report the Findings R Markdown Code R Markdown Knit Summary 8. Association Rule Mining Understanding Association Rule Mining Support Confidence Lift Apriori Algorithm Operationalization Overview Collecting the Data Cleaning the Data Analyzing the Data Fiori Summary 9. Natural Language Processing with the Google Cloud Natural Language API Understanding Natural Language Processing Sentiment Analysis Translation Preparing the Cloud API Collecting the Data Analyzing the Data Summary 10. Conclusion Original Mission Recap Chapter 1: Introduction Chapter 2: Data Science for SAP Professionals Chapter 3: SAP for Data Scientists Chapter 4: Exploratory Data Analysis Chapter 5: Anomaly Detection with R and Python Chapter 6: Prediction with R Chapter 7: Clustering and Segmentation in R Chapter 8: Association Rule Mining Chapter 9: Natural Language Processing with the Google Cloud Natural Language API Tips and Recommendations Be Creative Be Practical Enjoy the Ride Stay in Touch Index