## Table of Contents

1. Introduction to Data Science

1.1 Historical overview

1.2 Why data science?

1.3 Careers in data science

1.4 Data science lifecycle

1.5 Ethics in data science

1.6 Case study: Netflix

2. Probability and Statistics

2.1 Data collection

2.2 Descriptive statistics

2.3 Probability

2.4 Probability distributions

2.5 Inferential statistics

2.6 Inference for proportions and means

3. Data Wrangling

3.1 Data wrangling

3.2 Structuring data

3.3 Cleaning data

3.4 Enriching data

4. Data Exploration

4.1 Visualizing data with one feature

4.2 Visualizing data with multiple features

4.3 Best practices for visualizing data

4.4 Tools for visualizing data

4.5 Performing exploratory data analysis

4.6 Detecting outliers

5. Regression

5.1 Introduction to regression

5.2 Simple linear regression

5.3 Linear regression assumptions

5.4 Multiple linear regression

5.5 Logistic regression

6. Evaluating Model Performance

6.1 Model error

6.2 Binary classification metrics

6.3 Regression metrics

6.4 Training, validation, and test sets

6.5 Cross-validation

6.6 Bootstrap method

6.7 Comparing models

7. Supervised Learning

7.1 Introduction to supervised learning

7.2 K-nearest neighbors

7.3 Naive Bayes classification

7.4 Support vector machines

8. Unsupervised Learning

8.1 Introduction to unsupervised learning

8.2 K-means clustering

8.3 Hierarchical clustering

8.4 Detecting outliers using DBSCAN

8.5 Analyzing factors

8.6 Analyzing factors using PCA

9. Decision Trees

9.1 Introduction to decision trees

9.2 Regression trees

9.3 Classification trees

9.4 Random forests

10: Artificial Neural Networks

10.1 Introduction to artificial neural networks

10.2 Single-layer perceptron

10.3 Nonlinear activation functions

10.4 Multilayer perceptron

11. Ensemble Techniques

11.1 Introduction to ensemble models

11.2 Boosting

11.3 Bagging

11.4 Stacking

## What You’ll Find In This zyBook:

### More action with less text.

- Builds student understanding and confidence through learning questions and coding activities
- Students learn the necessary skills required for the more quantitative and technical aspects of data science and machine learning
- Each section covers topics from a conceptual standpoint without assuming prerequisite knowledge in statistics and programming
- Test bank with more than 260 questions

## The zyBooks Approach

### Less text doesn’t mean less learning.

Data Science Foundations provides an interactive introduction to common algorithms and techniques in data science. This zyBook covers data preprocessing, regression techniques, supervised and unsupervised learning algorithms, decision trees, neural networks, ensemble methods, and model evaluation techniques.

## Authors

**Chris Chan**

*Senior Manager, Content Development in Math, Stats, and Data Science / zyBooks / M.A. in Mathematics / San Francisco State University*

**Matt Rissler**

*Data Science Content Developer / Ph.D. in Mathematics / University of Notre Dame*

**Aimee Schwab-McCoy**

*Data Science Content Developer / Ph.D. in Statistics / University of Nebraska–Lincoln*