Hands-On Recommendation Systems with Python: Start Building Powerful and Personalized, Recommendation Engines with Python

✍ Scribed by Banik, Rounak

• Publisher: Packt Publishing Ltd
• Year: 2018
• Tongue: English
• Category: Library

✦ Synopsis

Recommendation systems are at the heart of almost every internet business today; from Facebook to Netflix to Amazon. Providing good recommendations, whether it's friends, movies or groceries, goes a long way in defining user experience and enticing your customers to use and buy from your platform. This book teaches you to do just that.;Cover; Title Page; Copyright and Credits; Dedication; Packt Upsell; Contributors; Table of Contents; Preface; Chapter 1: Getting Started with Recommender Systems; Technical requirements; What is a recommender system?; The prediction problem; The ranking problem; Types of recommender systems; Collaborative filtering; User-based filtering; Item-based filtering; Shortcomings; Content-based systems; Knowledge-based recommenders; Hybrid recommenders; Summary; Chapter 2: Manipulating Data with the Pandas Library; Technical requirements; Setting up the environment; The Pandas library.

✦ Table of Contents

Cover
Title Page
Copyright and Credits
Dedication
Packt Upsell
Contributors
Table of Contents
Preface
Chapter 1: Getting Started with Recommender Systems
Technical requirements
What is a recommender system?
The prediction problem
The ranking problem
Types of recommender systems
Collaborative filtering
User-based filtering
Item-based filtering
Shortcomings
Content-based systems
Knowledge-based recommenders
Hybrid recommenders
Summary
Chapter 2: Manipulating Data with the Pandas Library
Technical requirements
Setting up the environment
The Pandas library. The Pandas DataFrameThe Pandas Series
Summary
Chapter 3: Building an IMDB Top 250 Clone with Pandas
Technical requirements
The simple recommender
The metric
The prerequisties
Calculating the score
Sorting and output
The knowledge-based recommender
Genres
The build_chart function
Summary
Chapter 4: Building Content-Based Recommenders
Technical requirements
Exporting the clean DataFrame
Document vectors
CountVectorizer
TF-IDFVectorizer
The cosine similarity score
Plot description-based recommender
Preparing the data
Creating the TF-IDF matrix. Computing the cosine similarity scoreBuilding the recommender function
Metadata-based recommender
Preparing the data
The keywords and credits datasets
Wrangling keywords, cast, and crew
Creating the metadata soup
Generating the recommendations
Suggestions for improvements
Summary
Chapter 5: Getting Started with Data Mining Techniques
Problem statement
Similarity measures
Euclidean distance
Pearson correlation
Cosine similarity
Clustering
k-means clustering
Choosing k
Other clustering algorithms
Dimensionality reduction
Principal component analysis. Other dimensionality reduction techniquesLinear-discriminant analysis
Singular value decomposition
Supervised learning
k-nearest neighbors
Classification
Regression
Support vector machines
Decision trees
Ensembling
Bagging and random forests
Boosting
Evaluation metrics
Accuracy
Root mean square error
Binary classification metrics
Precision
Recall
F1 score
Summary
Chapter 6: Building Collaborative Filters
Technical requirements
The framework
The MovieLens dataset
Downloading the dataset
Exploring the data
Training and test data
Evaluation. User-based collaborative filteringMean
Weighted mean
User demographics
Item-based collaborative filtering
Model-based approaches
Clustering
Supervised learning and dimensionality reduction
Singular-value decomposition
Summary
Chapter 7: Hybrid Recommenders
Technical requirements
Introduction
Case study --
Building a hybrid model
Summary
Other Books You May Enjoy
Index.

✦ Subjects

Python;Electronic books