Preface
Acknowledgments
Contents
Part I Python
1 Python for Artificial Intelligence
1.1 Common Uses
1.1.1 Relative Popularity
1.1.2 Features
1.1.3 Syntax and Design
1.2 Scientific Programming
1.3 Why Python for Artificial Intelligence
2 Getting Started
2.1 Setting up Your Python Environment
2.2 Anaconda
2.2.1 Installing Anaconda
2.2.2 Further Installation Steps
2.2.3 Updating Anaconda
2.3 Installing Packages
2.4 Virtual Environment
2.5 Jupyter Notebooks
2.5.1 Starting the Jupyter Notebook
2.5.2 Notebook Basics
Running Cells
Modal Editing
Inserting Unicode (e.g., Greek Letters)
A Test Program
2.5.3 Working with the Notebook
Tab Completion
On-Line Help
Other Content
2.5.4 Sharing Notebooks
3 An Introductory Example
3.1 Overview
3.2 The Task: Plotting a White Noise Process
3.3 Our First Program
3.3.1 Imports
Why So Many Imports?
Packages
Subpackages
3.3.2 Importing Names Directly
3.3.3 Random Draws
3.4 Alternative Implementations
3.4.1 A Version with a for Loop
3.4.2 Lists
3.4.3 The for Loop
3.4.4 A Comment on Indentation
3.4.5 While Loops
3.5 Another Application
3.6 Exercises
3.6.1 Exercise 1
3.6.2 Exercise 2
3.6.3 Exercise 3
3.6.4 Exercise 4
3.6.5 Exercise 5
3.7 Solutions
3.7.1 Exercise 1
3.7.2 Exercise 2
3.7.3 Exercise 3
3.7.4 Exercise 4
3.7.5 Exercise 5
4 Basic Python
4.1 Hello, World!
4.2 Indentation
4.3 Variables and Types
4.3.1 Numbers
4.3.2 Strings
4.3.3 Lists
4.3.4 Dictionaries
4.4 Basic Operators
4.4.1 Arithmetic Operators
4.4.2 List Operators
4.4.3 String Operators
4.5 Logical Conditions
4.6 Loops
4.7 List Comprehensions
4.8 Exception Handling
4.8.1 Sets
5 Intermediate Python
5.1 Functions
5.2 Classes and Objects
5.3 Modules and Packages
5.3.1 Writing Modules
5.4 Built-in Modules
5.5 Writing Packages
5.6 Closures
5.7 Decorators
6 Advanced Python
6.1 Python Magic Methods
6.1.1 Exercise
6.1.2 Solution
6.2 Comprehension
6.3 Functional Parts
6.4 Iterables
6.5 Decorators
6.6 More on Object Oriented Programming
6.6.1 Mixins
6.6.2 Attribute Access Hooks
6.6.3 Callable Objects
6.6.4 new vs init
6.7 Properties
6.8 Metaclasses
7 Python for Data Analysis
7.1 Ethics
7.2 Data Analysis
7.2.1 Numpy Arrays
7.2.2 Pandas
Selections
7.2.3 Matplotlib
7.3 Sample Code
Part II Artificial Intelligence Basics
8 Introduction to Artificial Intelligence
8.1 Data Exploration
8.2 Problems with Data
8.3 A Language and Approach to Data-Driven Story-Telling
8.4 Example: Telling Story with Data
9 Data Wrangling
9.1 Handling Missing Data
9.1.1 Missing Data
9.1.2 Removing Missing Data
9.2 Transformation
9.2.1 Duplicates
9.2.2 Mapping
9.3 Outliers
9.4 Permutation
9.5 Merging and Combining
9.6 Reshaping and Pivoting
9.7 Wide to Long
10 Regression
10.1 Linear Regression
10.2 Decision Tree Regression
10.3 Random Forests
10.4 Neural Network
10.5 How to Improve Our Regression Model
10.5.1 Boxplot
10.5.2 Remove Outlier
10.5.3 Remove NA
10.6 Feature Importance
10.7 Sample Code
11 Classification
11.1 Logistic Regression
11.2 Decision Tree and Random Forest
11.3 Neural Network
11.4 Logistic Regression
11.5 Decision Tree
11.6 Feature Importance
11.7 Remove Outlier
11.8 Use Top 3 Features
11.9 SVM
11.9.1 Important Hyper Parameters
11.10 Naive Bayes
11.11 Sample Code
12 Clustering
12.1 What Is Clustering?
12.2 K-Means
12.3 The Elbow Method
13 Association Rules
13.1 What Are Association Rules
13.2 Apriori Algorithm
13.3 Measures for Association Rules
Part III Artificial Intelligence Implementations
14 Text Mining
14.1 Read Data
14.2 Date Range
14.3 Category Distribution
14.4 Texts for Classification
14.5 Vectorize
14.6 CountVectorizer
14.7 TF-IDF
14.8 Feature Extraction with TF-IDF
14.9 Sample Code
15 Image Processing
15.1 Load the Dependencies
15.2 Load Image from urls
15.3 Image Analysis
15.4 Image Histogram
15.5 Contour
15.6 Grayscale Transformation
15.7 Histogram Equalization
15.8 Fourier Transformation
15.9 High pass Filtering in FFT
15.10 Pattern Recognition
15.11 Sample Code
16 Convolutional Neural Networks
16.1 The Convolution Operation
16.2 Pooling
16.3 Flattening
16.4 Exercise
16.5 CNN Architectures
16.5.1 VGG16
16.5.2 Inception Net
16.5.3 ResNet
16.6 Finetuning
16.7 Other Tasks That Use CNNs
16.7.1 Object Detection
16.7.2 Semantic Segmentation
17 Chatbot, Speech, and NLP
17.1 Speech to Text
17.2 Importing the Packages for Chatbot
17.3 Preprocessing the Data for Chatbot
17.3.1 Download the Data
17.3.2 Reading the Data from the Files
17.3.3 Preparing Data for Seq2Seq Model
17.4 Defining the Encoder-Decoder Model
17.5 Training the Model
17.6 Defining Inference Models
17.7 Talking with Our Chatbot
17.8 Sample Code
18 Deep Convolutional Generative Adversarial Network
18.1 What Are GANs?
18.2 Setup
18.2.1 Load and Prepare the Dataset
18.3 Create the Models
18.3.1 The Generator
18.3.2 The Discriminator
18.4 Define the Loss and Optimizers
18.4.1 Discriminator Loss
18.4.2 Generator Loss
18.5 Save Checkpoints
18.6 Define the Training Loop
18.6.1 Train the Model
18.6.2 Create a GIF
19 Neural Style Transfer
19.1 Setup
19.1.1 Import and Configure Modules
19.2 Visualize the Input
19.3 Fast Style Transfer Using TF-Hub
19.4 Define Content and Style Representations
19.4.1 Intermediate Layers for Style and Content
19.5 Build the Model
19.6 Calculate Style
19.7 Extract Style and Content
19.8 Run Gradient Descent
19.9 Total Variation Loss
19.10 Re-run the Optimization
20 Reinforcement Learning
20.1 Reinforcement Learning Analogy
20.2 Q-learning
20.3 Running a Trained Taxi
Bibliography
Index