Python Machine Learning Blueprints - Second Edition

Table of contents

1. Title Page
2. Copyright and Credits
   1. Python Machine Learning Blueprints Second Edition
3. About Packt
   1. Why subscribe?
   2. Packt.com
4. Contributors
   1. About the authors
   2. About the reviewer
   3. Packt is searching for authors like you
5. Preface
   1. Who this book is for
   2. What this book covers
   3. To get the most out of this book
      1. Download the example code files
      2. Download the color images
      3. Conventions used
   4. Get in touch
      1. Reviews
6. The Python Machine Learning Ecosystem
   1. Data science/machine learning workflow
      1. Acquisition
      2. Inspection
      3. Preparation
      4. Modeling
      5. Evaluation
      6. Deployment
   2. Python libraries and functions for each stage of the data science workflow
      1. Acquisition
      2. Inspection
         1. The Jupyter Notebook
         2. Pandas
         3. Visualization
            1. The matplotlib library
            2. The seaborn library
      3. Preparation
         1. map
         2. apply
         3. applymap
         4. groupby
      4. Modeling and evaluation
         1. Statsmodels
         2. Scikit-learn
      5. Deployment
   3. Setting up your machine learning environment
   4. Summary
7. Build an App to Find Underpriced Apartments
   1. Sourcing apartment listing data
      1. Pulling down listing data
      2. Pulling out the individual data points
      3. Parsing data
   2. Inspecting and preparing the data
      1. Sneak-peek at the data types
   3. Visualizing our data
   4. Visualizing the data
   5. Modeling the data
      1. Forecasting
   6. Extending the model
   7. Summary
8. Build an App to Find Cheap Airfares
   1. Sourcing airfare pricing data
   2. Retrieving fare data with advanced web scraping
      1. Creating a link
   3. Parsing the DOM to extract pricing data
      1. Parsing
   4. Identifying outlier fares with anomaly detection techniques
   5. Sending real-time alerts using IFTTT
   6. Putting it all together
   7. Summary
9. Forecast the IPO Market Using Logistic Regression
   1. The IPO market
      1. What is an IPO?
      2. Recent IPO market performance
      3. Working on the DataFrame
      4. Analyzing the data
      5. Summarizing the performance of the stocks
      6. Baseline IPO strategy
   2. Data cleansing and feature engineering
      1. Adding features to influence the performance of an IPO
   3. Binary classification with logistic regression
      1. Creating the target for our model
      2. Dummy coding
      3. Examining the model performance
   4. Generating the importance of a feature from our model
      1. Random forest classifier method
   5. Summary
10. Create a Custom Newsfeed
    1. Creating a supervised training set with Pocket
       1. Installing the Pocket Chrome Extension
       2. Using the Pocket API to retrieve stories
    2. Using the Embedly API to download story bodies
    3. Basics of Natural Language Processing
    4. Support Vector Machines
    5. IFTTT integration with feeds, Google Sheets, and email
       1. Setting up news feeds and Google Sheets through IFTTT
    6. Setting up your daily personal newsletter
    7. Summary
11. Predict whether Your Content Will Go Viral
    1. What does research tell us about virality?
    2. Sourcing shared counts and content
    3. Exploring the features of shareability
       1. Exploring image data
       2. Clustering
       3. Exploring the headlines
       4. Exploring the story content
    4. Building a predictive content scoring model
       1. Evaluating the model
       2. Adding new features to our model
    5. Summary
12. Use Machine Learning to Forecast the Stock Market
    1. Types of market analysis
    2. What does research tell us about the stock market?
       1. So, what exactly is a momentum strategy?
    3. How to develop a trading strategy
       1. Analysis of the data
       2. Volatility of the returns
       3. Daily returns
       4. Statistics for the strategies
       5. The mystery strategy
    4. Building the regression model
       1. Performance of the model
       2. Dynamic time warping
       3. Evaluating our trades
    5. Summary
13. Classifying Images with Convolutional Neural Networks
    1. Image-feature extraction
    2. Convolutional neural networks
       1. Network topology
       2. Convolutional layers and filters
       3. Max pooling layers
       4. Flattening
       5. Fully-connected layers and output
    3. Building a convolutional neural network to classify images in the Zalando Research dataset, using Keras
    4. Summary
14. Building a Chatbot
    1. The Turing Test
    2. The history of chatbots
    3. The design of chatbots
    4. Building a chatbot
    5. Sequence-to-sequence modeling for chatbots
    6. Summary
15. Build a Recommendation Engine
    1. Collaborative filtering
       1. So, what's collaborative filtering?
       2. Predicting the rating for the product
    2. Content-based filtering
    3. Hybrid systems
       1. Collaborative filtering
       2. Content-based filtering
    4. Building a recommendation engine
    5. Summary
16. What's Next?
    1. Summary of the projects
    2. Summary
17. Other Books You May Enjoy
    1. Leave a review - let other readers know what you think