Mastering Scala Machine Learning

Table of contents

1. Mastering Scala Machine Learning
   1. Table of Contents
   2. Mastering Scala Machine Learning
   3. Credits
   4. About the Author
   5. Acknowlegement
   6. www.PacktPub.com
      1. eBooks, discount offers, and more
         1. Why subscribe?
   7. Preface
      1. What this book covers
      2. What you need for this book
      3. Who this book is for
      4. Conventions
      5. Reader feedback
      6. Customer support
         1. Downloading the example code
         2. Downloading the color images of this book
         3. Errata
         4. Piracy
         5. Questions
   8. 1. Exploratory Data Analysis
      1. Getting started with Scala
      2. Distinct values of a categorical field
      3. Summarization of a numeric field
         1. Grepping across multiple fields
      4. Basic, stratified, and consistent sampling
      5. Working with Scala and Spark Notebooks
      6. Basic correlations
      7. Summary
   9. 2. Data Pipelines and Modeling
      1. Influence diagrams
      2. Sequential trials and dealing with risk
      3. Exploration and exploitation
      4. Unknown unknowns
      5. Basic components of a data-driven system
         1. Data ingest
         2. Data transformation layer
         3. Data analytics and machine learning
         4. UI component
         5. Actions engine
         6. Correlation engine
         7. Monitoring
      6. Optimization and interactivity
         1. Feedback loops
      7. Summary
   10. 3. Working with Spark and MLlib
       1. Setting up Spark
       2. Understanding Spark architecture
          1. Task scheduling
          2. Spark components
          3. MQTT, ZeroMQ, Flume, and Kafka
          4. HDFS, Cassandra, S3, and Tachyon
          5. Mesos, YARN, and Standalone
       3. Applications
          1. Word count
          2. Streaming word count
          3. Spark SQL and DataFrame
       4. ML libraries
          1. SparkR
          2. Graph algorithms – GraphX and GraphFrames
       5. Spark performance tuning
       6. Running Hadoop HDFS
       7. Summary
   11. 4. Supervised and Unsupervised Learning
       1. Records and supervised learning
          1. Iris dataset
          2. Labeled point
          3. SVMWithSGD
          4. Logistic regression
          5. Decision tree
          6. Bagging and boosting – ensemble learning methods
       2. Unsupervised learning
       3. Problem dimensionality
       4. Summary
   12. 5. Regression and Classification
       1. What regression stands for?
       2. Continuous space and metrics
       3. Linear regression
       4. Logistic regression
       5. Regularization
       6. Multivariate regression
       7. Heteroscedasticity
       8. Regression trees
       9. Classification metrics
       10. Multiclass problems
       11. Perceptron
       12. Generalization error and overfitting
       13. Summary
   13. 6. Working with Unstructured Data
       1. Nested data
       2. Other serialization formats
       3. Hive and Impala
       4. Sessionization
       5. Working with traits
       6. Working with pattern matching
       7. Other uses of unstructured data
       8. Probabilistic structures
       9. Projections
       10. Summary
   14. 7. Working with Graph Algorithms
       1. A quick introduction to graphs
       2. SBT
       3. Graph for Scala
          1. Adding nodes and edges
          2. Graph constraints
          3. JSON
       4. GraphX
          1. Who is getting e-mails?
          2. Connected components
          3. Triangle counting
          4. Strongly connected components
          5. PageRank
          6. SVD++
       5. Summary
   15. 8. Integrating Scala with R and Python
       1. Integrating with R
          1. Setting up R and SparkR
             1. Linux
             2. Mac OS
             3. Windows
             4. Running SparkR via scripts
             5. Running Spark via R's command line
          2. DataFrames
          3. Linear models
          4. Generalized linear model
          5. Reading JSON files in SparkR
          6. Writing Parquet files in SparkR
          7. Invoking Scala from R
             1. Using Rserve
       2. Integrating with Python
          1. Setting up Python
          2. PySpark
          3. Calling Python from Java/Scala
             1. Using sys.process._
             2. Spark pipe
             3. Jython and JSR 223
       3. Summary
   16. 9. NLP in Scala
       1. Text analysis pipeline
          1. Simple text analysis
       2. MLlib algorithms in Spark
          1. TF-IDF
          2. LDA
       3. Segmentation, annotation, and chunking
       4. POS tagging
       5. Using word2vec to find word relationships
          1. A Porter Stemmer implementation of the code
       6. Summary
   17. 10. Advanced Model Monitoring
       1. System monitoring
          1. Process monitoring
          2. Model monitoring
             1. Performance over time
             2. Criteria for model retiring
             3. A/B testing
       2. Summary
   18. Index